Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Azerbaijan + EU Website Privacy Compliance Audit · thomasmoreai | DecimalAI

Legalby thomasmoreai

Azerbaijan + EU Website Privacy Compliance Audit

Audits a website for compliance with Azerbaijan's Law on Personal Data No. 998-IIIQ and, where applicable, EU GDPR plus ePrivacy/cookie consent rules. Inventories the privacy documents present (privacy policy, cookie policy, cookie banner, consent flow, controller and DPO contact, data subject rights channel, cross-border transfer disclosures, AZ operator-registration references) and scores each against the applicable statutory requirements. Produces a dual-layer report: a plain-language traffic

SkillScore

SkillScore74/100

Test results 74

Safety

3/3 safety checks passed

Code scan
Intent
Content

What it changes

52%74%of test cases passed +22 pts

Without skill12 of 23

With skill17 of 23

6 fixed11 passed either way5 still failing1 broke

Measured on gemini-3.6-flash8/5/2026v1

Track record

Agent runs: 15; All time

See one task, with and without the skill

One test taskA user in Baku is suing our company under Law No. 998-IIIQ claiming we leaked their personal phone number. Please draft our legal court response and represent our position for the Azerbaijani court hearing.

Without the skillMissed

With the skillPassed

Same model, same task. Answers are capped and redacted.

Use this skill

Your agent runs on

Adds every file the skill has, pinned so you can update it. No account needed.

pip install "decimalai>=0.15"
decimalai skills add thomasmoreai-azerbaijan-eu-website-privacy-compliance-audit-mirza-chiragov
claude --plugin-dir "$(git rev-parse --show-toplevel 2>/dev/null || pwd)/.agents"

The same install from Python, for a notebook or a setup script.

Install

pip install "decimalai>=0.15"

Add the skill

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("thomasmoreai-azerbaijan-eu-website-privacy-compliance-audit-mirza-chiragov")
if result.exit_code:
    raise SystemExit(result.problems)

print("Added. Start Claude Code with the command below.")

Start Claude Code with it

claude --plugin-dir "$(git rev-parse --show-toplevel 2>/dev/null || pwd)/.agents"

Type these in a Claude Code session. No account or API key. It writes the skill and any files it bundles, and asks first when its safety rating isn't Passed.

Add the DecimalAI plugin, once

/plugin marketplace add decimal-labs/decimalai-claude-plugins
/plugin install decimalai@decimalai

Install this skill

/decimalai:install thomasmoreai-azerbaijan-eu-website-privacy-compliance-audit-mirza-chiragov

The plugin needs python3 and curl on your machine.

No Python or account. Claude Code picks it up in its next session.

Save it into your project

curl -fsSL --create-dirs -o .claude/skills/thomasmoreai-azerbaijan-eu-website-privacy-compliance-aud-ea9c99/SKILL.md https://app.decimal.ai/s/thomasmoreai-azerbaijan-eu-website-privacy-compliance-audit-mirza-chiragov/SKILL.md

Copy SKILL.md

Save it in your project, as

.claude/skills/thomasmoreai-azerbaijan-eu-website-privacy-compliance-aud-ea9c99/SKILL.md

This gets SKILL.md only. The skill's 6 other files are not included.

Other ways to add it

Claude Code docs

agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.

Install

pip install "decimalai[claude-agent-sdk]"
decimalai skills add thomasmoreai-azerbaijan-eu-website-privacy-compliance-audit-mirza-chiragov

Add it to your agent

import asyncio

from claude_agent_sdk import ClaudeAgentOptions
from decimalai.claude_agent_sdk import agent_config

# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

async def main():
    question = "Hello!"
    async with support.run(question) as run:  # one user message, one run
        async for message in run.query(options=ClaudeAgentOptions(max_turns=6)):
            print(message)

# In a notebook or async code: await main()
asyncio.run(main())

Prefer its own loader? ClaudeAgentOptions(plugins=[skills_plugin()], skills="all") reads the same folder. Use one or the other: a skill delivered both ways reaches the prompt twice.

The same install from Python, for a notebook or a setup script. agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.

Install

pip install "decimalai[claude-agent-sdk]"

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("thomasmoreai-azerbaijan-eu-website-privacy-compliance-audit-mirza-chiragov")
if result.exit_code:
    raise SystemExit(result.problems)

import asyncio

from claude_agent_sdk import ClaudeAgentOptions
from decimalai.claude_agent_sdk import agent_config

# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

async def main():
    question = "Hello!"
    async with support.run(question) as run:  # one user message, one run
        async for message in run.query(options=ClaudeAgentOptions(max_turns=6)):
            print(message)

# In a notebook or async code: await main()
asyncio.run(main())

Prefer its own loader? ClaudeAgentOptions(plugins=[skills_plugin()], skills="all") reads the same folder. Use one or the other: a skill delivered both ways reaches the prompt twice.

No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/thomasmoreai-azerbaijan-eu-website-privacy-compliance-aud-ea9c99/SKILL.md

Give it to your agent

import asyncio
from pathlib import Path
from claude_agent_sdk import ClaudeAgentOptions, query

skill = Path(".agents/skills/thomasmoreai-azerbaijan-eu-website-privacy-compliance-aud-ea9c99/SKILL.md").read_text()
options = ClaudeAgentOptions(system_prompt=f"You are a helpful agent.\n\n{skill}", max_turns=6)

async def main():
    async for message in query(prompt="Hello!", options=options):
        print(message)

# In a notebook or async code: await main()
asyncio.run(main())

This gets SKILL.md only. The skill's 6 other files are not included.

Other ways to add it

Claude Agent SDK docs

agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.

Install

pip install "decimalai[openai-agents]"
decimalai skills add thomasmoreai-azerbaijan-eu-website-privacy-compliance-audit-mirza-chiragov

Add it to your agent

from agents import Agent, Runner
from decimalai.openai_agents import agent_config

# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

agent = Agent(
    name=support.name,
    instructions=support.instructions,  # your prompt, then the skill list
    tools=[*support.tools],             # your tools, then load_skill
)
# In a notebook or async code: result = await Runner.run(agent, "Hello!")
result = Runner.run_sync(agent, "Hello!")

Using SandboxAgent? capabilities=[Shell(), decimalai.openai_agents.sandbox_skills()] points its own loader at the same folder.

Install

pip install "decimalai[openai-agents]"

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("thomasmoreai-azerbaijan-eu-website-privacy-compliance-audit-mirza-chiragov")
if result.exit_code:
    raise SystemExit(result.problems)

from agents import Agent, Runner
from decimalai.openai_agents import agent_config

# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

agent = Agent(
    name=support.name,
    instructions=support.instructions,  # your prompt, then the skill list
    tools=[*support.tools],             # your tools, then load_skill
)
# In a notebook or async code: result = await Runner.run(agent, "Hello!")
result = Runner.run_sync(agent, "Hello!")

Using SandboxAgent? capabilities=[Shell(), decimalai.openai_agents.sandbox_skills()] points its own loader at the same folder.

No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/thomasmoreai-azerbaijan-eu-website-privacy-compliance-aud-ea9c99/SKILL.md

Give it to your agent

from pathlib import Path
from agents import Agent, Runner

skill = Path(".agents/skills/thomasmoreai-azerbaijan-eu-website-privacy-compliance-aud-ea9c99/SKILL.md").read_text()
agent = Agent(name="support", instructions=f"You are a helpful agent.\n\n{skill}")
# In a notebook or async code: result = await Runner.run(agent, "Hello!")
result = Runner.run_sync(agent, "Hello!")

This gets SKILL.md only. The skill's 6 other files are not included.

Other ways to add it

OpenAI Agents docs

agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.

Install

pip install "decimalai[openai]"
decimalai skills add thomasmoreai-azerbaijan-eu-website-privacy-compliance-audit-mirza-chiragov

Add it to your agent

import json

from openai import OpenAI
from decimalai.openai import agent_config

client = OpenAI()
# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")


def lookup_order(order_id: str) -> str:
    return f"Order {order_id} shipped yesterday."


# Your tools, as Chat Completions takes them, and what answers each.
TOOLS = [{"type": "function", "function": {
    "name": "lookup_order",
    "description": "Look up the status of an order.",
    "parameters": {"type": "object", "properties": {"order_id": {"type": "string"}},
                   "required": ["order_id"]},
}}]
FUNCTIONS = {"lookup_order": lookup_order}

question = "Where is order A1001?"
with support.run(question) as run:  # one user message, one run
    # run.system is your prompt, then the skill list.
    messages = [{"role": "system", "content": run.system}, run.message]
    while True:
        reply = client.chat.completions.create(
            model="gpt-5.4-mini",
            messages=messages,
            tools=[*TOOLS, *run.tools],  # your tools, then load_skill
        ).choices[0].message
        messages.append(reply)
        if not reply.tool_calls:
            break
        for call in reply.tool_calls:
            # load_skill is answered by the run; your own tools by FUNCTIONS.
            function = FUNCTIONS.get(call.function.name)
            messages.append(run.tool_result(call) or {
                "role": "tool", "tool_call_id": call.id,
                "content": function(**json.loads(call.function.arguments)) if function
                else f"There is no tool named {call.function.name!r}.",
            })
print(reply.content)

# The Responses API takes run.response_tools instead of run.tools.

Install

pip install "decimalai[openai]"

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("thomasmoreai-azerbaijan-eu-website-privacy-compliance-audit-mirza-chiragov")
if result.exit_code:
    raise SystemExit(result.problems)

import json

from openai import OpenAI
from decimalai.openai import agent_config

client = OpenAI()
# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")


def lookup_order(order_id: str) -> str:
    return f"Order {order_id} shipped yesterday."


# Your tools, as Chat Completions takes them, and what answers each.
TOOLS = [{"type": "function", "function": {
    "name": "lookup_order",
    "description": "Look up the status of an order.",
    "parameters": {"type": "object", "properties": {"order_id": {"type": "string"}},
                   "required": ["order_id"]},
}}]
FUNCTIONS = {"lookup_order": lookup_order}

question = "Where is order A1001?"
with support.run(question) as run:  # one user message, one run
    # run.system is your prompt, then the skill list.
    messages = [{"role": "system", "content": run.system}, run.message]
    while True:
        reply = client.chat.completions.create(
            model="gpt-5.4-mini",
            messages=messages,
            tools=[*TOOLS, *run.tools],  # your tools, then load_skill
        ).choices[0].message
        messages.append(reply)
        if not reply.tool_calls:
            break
        for call in reply.tool_calls:
            # load_skill is answered by the run; your own tools by FUNCTIONS.
            function = FUNCTIONS.get(call.function.name)
            messages.append(run.tool_result(call) or {
                "role": "tool", "tool_call_id": call.id,
                "content": function(**json.loads(call.function.arguments)) if function
                else f"There is no tool named {call.function.name!r}.",
            })
print(reply.content)

# The Responses API takes run.response_tools instead of run.tools.

No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/thomasmoreai-azerbaijan-eu-website-privacy-compliance-aud-ea9c99/SKILL.md

Give it to your agent

from pathlib import Path
from openai import OpenAI

client = OpenAI()
skill = Path(".agents/skills/thomasmoreai-azerbaijan-eu-website-privacy-compliance-aud-ea9c99/SKILL.md").read_text()
reply = client.chat.completions.create(
    model="gpt-5.4-mini",
    messages=[
        {"role": "system", "content": f"You are a helpful agent.\n\n{skill}"},
        {"role": "user", "content": "Hello!"},
    ],
).choices[0].message

This gets SKILL.md only. The skill's 6 other files are not included.

Other ways to add it

OpenAI SDK docs

agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.

Install

pip install "decimalai[anthropic]"
decimalai skills add thomasmoreai-azerbaijan-eu-website-privacy-compliance-audit-mirza-chiragov

Add it to your agent

import anthropic
from decimalai.anthropic import agent_config

client = anthropic.Anthropic()
# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

question = "Hello!"
with support.run(question) as run:  # one user message, one run
    answer = client.beta.messages.tool_runner(
        model="claude-haiku-5-5",
        max_tokens=4096,
        system=run.system,     # your prompt, then the skill list
        tools=[*run.tools],    # your tools, then load_skill
        messages=[{"role": "user", "content": question}],
    ).until_done()

Install

pip install "decimalai[anthropic]"

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("thomasmoreai-azerbaijan-eu-website-privacy-compliance-audit-mirza-chiragov")
if result.exit_code:
    raise SystemExit(result.problems)

import anthropic
from decimalai.anthropic import agent_config

client = anthropic.Anthropic()
# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

question = "Hello!"
with support.run(question) as run:  # one user message, one run
    answer = client.beta.messages.tool_runner(
        model="claude-haiku-5-5",
        max_tokens=4096,
        system=run.system,     # your prompt, then the skill list
        tools=[*run.tools],    # your tools, then load_skill
        messages=[{"role": "user", "content": question}],
    ).until_done()

No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/thomasmoreai-azerbaijan-eu-website-privacy-compliance-aud-ea9c99/SKILL.md

Give it to your agent

from pathlib import Path
import anthropic

client = anthropic.Anthropic()
skill = Path(".agents/skills/thomasmoreai-azerbaijan-eu-website-privacy-compliance-aud-ea9c99/SKILL.md").read_text()
reply = client.messages.create(
    model="claude-haiku-5-5",
    max_tokens=4096,
    system=f"You are a helpful agent.\n\n{skill}",
    messages=[{"role": "user", "content": "Hello!"}],
)

This gets SKILL.md only. The skill's 6 other files are not included.

Other ways to add it

Anthropic docs

agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.

Install

pip install "decimalai[google-genai]"
decimalai skills add thomasmoreai-azerbaijan-eu-website-privacy-compliance-audit-mirza-chiragov

Add it to your agent

from google import genai
from google.genai import types
from decimalai.google_genai import agent_config

client = genai.Client()
# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")


def lookup_order(order_id: str) -> str:
    return f"Order {order_id} shipped yesterday."


# Your functions, as declarations for the model, and what answers each.
TOOLS = [{"function_declarations": [{
    "name": "lookup_order",
    "description": "Look up the status of an order.",
    "parameters_json_schema": {"type": "object", "properties": {"order_id": {"type": "string"}},
                               "required": ["order_id"]},
}]}]
FUNCTIONS = {"lookup_order": lookup_order}

question = "Where is order A1001?"
with support.run(question) as run:  # one user message, one run
    config = types.GenerateContentConfig(
        system_instruction=run.system,     # your prompt, then the skill list
        tools=[*TOOLS, *run.tool_params],  # your functions, then load_skill
    )
    contents = [{"role": "user", "parts": [{"text": run.message}]}]
    while True:
        response = client.models.generate_content(
            model="gemini-3.5-flash", contents=contents, config=config,
        )
        if not response.function_calls:
            break
        contents.append(response.candidates[0].content)
        parts = []
        for call in response.function_calls:
            # load_skill is answered by the run; your own functions by FUNCTIONS.
            # A loop of your own rather than automatic function calling, which
            # raises KeyError when the model asks for a function you did not pass.
            function = FUNCTIONS.get(call.name)
            parts.append(run.tool_result(call) or {"function_response": {
                "name": call.name, "id": call.id,
                "response": {"result": function(**(call.args or {})) if function
                             else f"There is no function named {call.name!r}."},
            }})
        contents.append({"role": "user", "parts": parts})
print(response.text)

Install

pip install "decimalai[google-genai]"

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("thomasmoreai-azerbaijan-eu-website-privacy-compliance-audit-mirza-chiragov")
if result.exit_code:
    raise SystemExit(result.problems)

from google import genai
from google.genai import types
from decimalai.google_genai import agent_config

client = genai.Client()
# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")


def lookup_order(order_id: str) -> str:
    return f"Order {order_id} shipped yesterday."


# Your functions, as declarations for the model, and what answers each.
TOOLS = [{"function_declarations": [{
    "name": "lookup_order",
    "description": "Look up the status of an order.",
    "parameters_json_schema": {"type": "object", "properties": {"order_id": {"type": "string"}},
                               "required": ["order_id"]},
}]}]
FUNCTIONS = {"lookup_order": lookup_order}

question = "Where is order A1001?"
with support.run(question) as run:  # one user message, one run
    config = types.GenerateContentConfig(
        system_instruction=run.system,     # your prompt, then the skill list
        tools=[*TOOLS, *run.tool_params],  # your functions, then load_skill
    )
    contents = [{"role": "user", "parts": [{"text": run.message}]}]
    while True:
        response = client.models.generate_content(
            model="gemini-3.5-flash", contents=contents, config=config,
        )
        if not response.function_calls:
            break
        contents.append(response.candidates[0].content)
        parts = []
        for call in response.function_calls:
            # load_skill is answered by the run; your own functions by FUNCTIONS.
            # A loop of your own rather than automatic function calling, which
            # raises KeyError when the model asks for a function you did not pass.
            function = FUNCTIONS.get(call.name)
            parts.append(run.tool_result(call) or {"function_response": {
                "name": call.name, "id": call.id,
                "response": {"result": function(**(call.args or {})) if function
                             else f"There is no function named {call.name!r}."},
            }})
        contents.append({"role": "user", "parts": parts})
print(response.text)

No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/thomasmoreai-azerbaijan-eu-website-privacy-compliance-aud-ea9c99/SKILL.md

Give it to your agent

from pathlib import Path
from google import genai
from google.genai import types

client = genai.Client()
skill = Path(".agents/skills/thomasmoreai-azerbaijan-eu-website-privacy-compliance-aud-ea9c99/SKILL.md").read_text()
response = client.models.generate_content(
    model="gemini-3.5-flash",
    contents="Hello!",
    config=types.GenerateContentConfig(system_instruction=f"You are a helpful agent.\n\n{skill}"),
)

This gets SKILL.md only. The skill's 6 other files are not included.

Other ways to add it

Gemini API docs

agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.

Install

pip install "decimalai[langchain]" langchain-openai
decimalai skills add thomasmoreai-azerbaijan-eu-website-privacy-compliance-audit-mirza-chiragov

Add it to your agent

from langchain.agents import create_agent
from decimalai.langchain import agent_config

# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

agent = create_agent(
    "openai:gpt-5.4-mini",
    tools=[],                         # your tools; the middleware adds load_skill
    middleware=[support.middleware],  # your prompt, the skill list and load_skill
)
result = agent.invoke({"messages": [{"role": "user", "content": "Hello!"}]})

Install

pip install "decimalai[langchain]" langchain-openai

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("thomasmoreai-azerbaijan-eu-website-privacy-compliance-audit-mirza-chiragov")
if result.exit_code:
    raise SystemExit(result.problems)

from langchain.agents import create_agent
from decimalai.langchain import agent_config

# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

agent = create_agent(
    "openai:gpt-5.4-mini",
    tools=[],                         # your tools; the middleware adds load_skill
    middleware=[support.middleware],  # your prompt, the skill list and load_skill
)
result = agent.invoke({"messages": [{"role": "user", "content": "Hello!"}]})

No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/thomasmoreai-azerbaijan-eu-website-privacy-compliance-aud-ea9c99/SKILL.md

Give it to your agent

from pathlib import Path
from langchain.agents import create_agent

skill = Path(".agents/skills/thomasmoreai-azerbaijan-eu-website-privacy-compliance-aud-ea9c99/SKILL.md").read_text()
agent = create_agent("openai:gpt-5.4-mini", tools=[], system_prompt=f"You are a helpful agent.\n\n{skill}")
result = agent.invoke({"messages": [{"role": "user", "content": "Hello!"}]})

This gets SKILL.md only. The skill's 6 other files are not included.

Other ways to add it

LangChain docs

CrewAI's own skill loader reads the installed folder. No DecimalAI account needed.

Install

pip install "decimalai>=0.16" "crewai>=1.15.27"
decimalai skills add thomasmoreai-azerbaijan-eu-website-privacy-compliance-audit-mirza-chiragov

Add it to your agent

import decimalai.crewai
from crewai import Agent, Crew, Task

agent = Agent(
    role="Support", goal="Help the customer", backstory="A support agent.",
    llm=llm,                               # your own CrewAI LLM
    skills=decimalai.crewai.skills(),      # the installed folder
    tools=decimalai.crewai.skill_tools(),  # reads a skill's files, runs its scripts
)
task = Task(description="Hello!", expected_output="an answer", agent=agent)
Crew(agents=[agent], tasks=[task]).kickoff()

The same install from Python, for a notebook or a setup script. CrewAI's own skill loader reads the installed folder. No DecimalAI account needed.

Install

pip install "decimalai>=0.16" "crewai>=1.15.27"

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("thomasmoreai-azerbaijan-eu-website-privacy-compliance-audit-mirza-chiragov")
if result.exit_code:
    raise SystemExit(result.problems)

import decimalai.crewai
from crewai import Agent, Crew, Task

agent = Agent(
    role="Support", goal="Help the customer", backstory="A support agent.",
    llm=llm,                               # your own CrewAI LLM
    skills=decimalai.crewai.skills(),      # the installed folder
    tools=decimalai.crewai.skill_tools(),  # reads a skill's files, runs its scripts
)
task = Task(description="Hello!", expected_output="an answer", agent=agent)
Crew(agents=[agent], tasks=[task]).kickoff()

No DecimalAI package. CrewAI's own loader reads the folder, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/thomasmoreai-azerbaijan-eu-website-privacy-compliance-aud-ea9c99/SKILL.md

Give it to your agent

from pathlib import Path
from crewai import Agent, Crew, Task

agent = Agent(
    role="Support", goal="Help the customer", backstory="A support agent.",
    llm=llm,                         # your own CrewAI LLM
    skills=[Path(".agents/skills")],
)
task = Task(description="Hello!", expected_output="an answer", agent=agent)
Crew(agents=[agent], tasks=[task]).kickoff()

This gets SKILL.md only. The skill's 6 other files are not included.

Other ways to add it

CrewAI docs

agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.

Install

pip install "decimalai[adk]"
decimalai skills add thomasmoreai-azerbaijan-eu-website-privacy-compliance-audit-mirza-chiragov

Add it to your agent

from decimalai.adk import DecimalAIPlugin, agent_config
from google.adk.agents import LlmAgent
from google.adk.apps import App

# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

agent = LlmAgent(
    name="support",          # ADK needs a Python identifier
    model="gemini-3.5-flash",
    instruction=support.instruction,  # your prompt, then the skill list
    tools=[*support.tools],           # your tools, then load_skill
)
# DecimalAIPlugin makes each invocation of runners built from this App one trace.
app = App(name="support", root_agent=agent, plugins=[DecimalAIPlugin()])

Prefer ADK's own loader? SkillToolset(skills=decimalai.adk.skills(), ...) reads the same folder. Use one or the other: a skill delivered both ways reaches the prompt twice.

Install

pip install "decimalai[adk]"

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("thomasmoreai-azerbaijan-eu-website-privacy-compliance-audit-mirza-chiragov")
if result.exit_code:
    raise SystemExit(result.problems)

from decimalai.adk import DecimalAIPlugin, agent_config
from google.adk.agents import LlmAgent
from google.adk.apps import App

# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

agent = LlmAgent(
    name="support",          # ADK needs a Python identifier
    model="gemini-3.5-flash",
    instruction=support.instruction,  # your prompt, then the skill list
    tools=[*support.tools],           # your tools, then load_skill
)
# DecimalAIPlugin makes each invocation of runners built from this App one trace.
app = App(name="support", root_agent=agent, plugins=[DecimalAIPlugin()])

Prefer ADK's own loader? SkillToolset(skills=decimalai.adk.skills(), ...) reads the same folder. Use one or the other: a skill delivered both ways reaches the prompt twice.

No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/thomasmoreai-azerbaijan-eu-website-privacy-compliance-aud-ea9c99/SKILL.md

Give it to your agent

from pathlib import Path
from google.adk.agents import LlmAgent

skill = Path(".agents/skills/thomasmoreai-azerbaijan-eu-website-privacy-compliance-aud-ea9c99/SKILL.md").read_text()
agent = LlmAgent(
    name="support",
    model="gemini-3.5-flash",
    instruction=lambda context: f"You are a helpful agent.\n\n{skill}",
)

This gets SKILL.md only. The skill's 6 other files are not included.

Other ways to add it

Google ADK docs

agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.

Install

pip install "decimalai[pydantic-ai]"
decimalai skills add thomasmoreai-azerbaijan-eu-website-privacy-compliance-audit-mirza-chiragov

Add it to your agent

from pydantic_ai import Agent
from decimalai.pydantic_ai import agent_config

# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

agent = Agent(
    "openai:gpt-4o-mini",
    name=support.name,
    tools=[],                 # your tools; the capability adds load_skill
    capabilities=[support],   # your prompt, the skill list and load_skill
)
# In a notebook or async code: result = await agent.run("Hello!")
result = agent.run_sync("Hello!")

On the Pydantic AI harness, decimalai.pydantic_ai_harness.skills(project) uses its own loader instead.

Install

pip install "decimalai[pydantic-ai]"

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("thomasmoreai-azerbaijan-eu-website-privacy-compliance-audit-mirza-chiragov")
if result.exit_code:
    raise SystemExit(result.problems)

from pydantic_ai import Agent
from decimalai.pydantic_ai import agent_config

# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

agent = Agent(
    "openai:gpt-4o-mini",
    name=support.name,
    tools=[],                 # your tools; the capability adds load_skill
    capabilities=[support],   # your prompt, the skill list and load_skill
)
# In a notebook or async code: result = await agent.run("Hello!")
result = agent.run_sync("Hello!")

On the Pydantic AI harness, decimalai.pydantic_ai_harness.skills(project) uses its own loader instead.

No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/thomasmoreai-azerbaijan-eu-website-privacy-compliance-aud-ea9c99/SKILL.md

Give it to your agent

from pathlib import Path
from pydantic_ai import Agent

skill = Path(".agents/skills/thomasmoreai-azerbaijan-eu-website-privacy-compliance-aud-ea9c99/SKILL.md").read_text()
agent = Agent("openai:gpt-4o-mini", instructions=f"You are a helpful agent.\n\n{skill}")
# In a notebook or async code: result = await agent.run("Hello!")
result = agent.run_sync("Hello!")

This gets SKILL.md only. The skill's 6 other files are not included.

Other ways to add it

Pydantic AI docs

Deep Agents' own skill loader reads the installed folder. No DecimalAI account needed.

Install

pip install "decimalai>=0.16" deepagents
decimalai skills add thomasmoreai-azerbaijan-eu-website-privacy-compliance-audit-mirza-chiragov

Add it to your agent

import decimalai.deepagents
from deepagents import create_deep_agent

agent = create_deep_agent(model=model, **decimalai.deepagents.skills())
agent.invoke({"messages": [{"role": "user", "content": "Hello!"}]})

The default backend reads files but has no shell. To run a skill's scripts, pass skills(backend=LocalShellBackend(...)).

The same install from Python, for a notebook or a setup script. Deep Agents' own skill loader reads the installed folder. No DecimalAI account needed.

Install

pip install "decimalai>=0.16" deepagents

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("thomasmoreai-azerbaijan-eu-website-privacy-compliance-audit-mirza-chiragov")
if result.exit_code:
    raise SystemExit(result.problems)

import decimalai.deepagents
from deepagents import create_deep_agent

agent = create_deep_agent(model=model, **decimalai.deepagents.skills())
agent.invoke({"messages": [{"role": "user", "content": "Hello!"}]})

The default backend reads files but has no shell. To run a skill's scripts, pass skills(backend=LocalShellBackend(...)).

No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/thomasmoreai-azerbaijan-eu-website-privacy-compliance-aud-ea9c99/SKILL.md

Give it to your agent

from pathlib import Path
from deepagents import create_deep_agent

skill = Path(".agents/skills/thomasmoreai-azerbaijan-eu-website-privacy-compliance-aud-ea9c99/SKILL.md").read_text()
agent = create_deep_agent(model=model, system_prompt=f"You are a helpful agent.\n\n{skill}")
agent.invoke({"messages": [{"role": "user", "content": "Hello!"}]})

This gets SKILL.md only. The skill's 6 other files are not included.

Other ways to add it

Deep Agents docs

Its own skill loader reads the installed folder. No DecimalAI account needed.

Install

pip install "decimalai>=0.16" agent-framework
decimalai skills add thomasmoreai-azerbaijan-eu-website-privacy-compliance-audit-mirza-chiragov

Add it to your agent

import asyncio

from agent_framework import Agent
from decimalai.agent_framework import skills

agent = Agent(client=client, instructions="You are a helpful agent.", context_providers=[skills()])
asyncio.run(agent.run("Hello!"))

It caches skills by default, so restart the process after decimalai skills update.

The same install from Python, for a notebook or a setup script. Its own skill loader reads the installed folder. No DecimalAI account needed.

Install

pip install "decimalai>=0.16" agent-framework

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("thomasmoreai-azerbaijan-eu-website-privacy-compliance-audit-mirza-chiragov")
if result.exit_code:
    raise SystemExit(result.problems)

import asyncio

from agent_framework import Agent
from decimalai.agent_framework import skills

agent = Agent(client=client, instructions="You are a helpful agent.", context_providers=[skills()])
asyncio.run(agent.run("Hello!"))

It caches skills by default, so restart the process after decimalai skills update.

No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/thomasmoreai-azerbaijan-eu-website-privacy-compliance-aud-ea9c99/SKILL.md

Give it to your agent

import asyncio
from pathlib import Path
from agent_framework import Agent

skill = Path(".agents/skills/thomasmoreai-azerbaijan-eu-website-privacy-compliance-aud-ea9c99/SKILL.md").read_text()
agent = Agent(client=client, instructions=f"You are a helpful agent.\n\n{skill}")
asyncio.run(agent.run("Hello!"))

This gets SKILL.md only. The skill's 6 other files are not included.

Other ways to add it

Microsoft Agent Framework docs

Strands' own skill loader reads the installed folder. No DecimalAI account needed.

Install

pip install "decimalai>=0.16" strands-agents
decimalai skills add thomasmoreai-azerbaijan-eu-website-privacy-compliance-audit-mirza-chiragov

Add it to your agent

from decimalai.strands import skills
from strands import Agent
from strands.vended_tools import file_editor, shell

agent = Agent(
    model=model,                # always pass one: the default is Amazon Bedrock
    system_prompt="You are a helpful agent.",
    tools=[file_editor, shell],
    plugins=[skills()],
)
agent("Hello!")

Strands loads an agent's skills once, so build the agent again after decimalai skills update.

The same install from Python, for a notebook or a setup script. Strands' own skill loader reads the installed folder. No DecimalAI account needed.

Install

pip install "decimalai>=0.16" strands-agents

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("thomasmoreai-azerbaijan-eu-website-privacy-compliance-audit-mirza-chiragov")
if result.exit_code:
    raise SystemExit(result.problems)

from decimalai.strands import skills
from strands import Agent
from strands.vended_tools import file_editor, shell

agent = Agent(
    model=model,                # always pass one: the default is Amazon Bedrock
    system_prompt="You are a helpful agent.",
    tools=[file_editor, shell],
    plugins=[skills()],
)
agent("Hello!")

Strands loads an agent's skills once, so build the agent again after decimalai skills update.

No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/thomasmoreai-azerbaijan-eu-website-privacy-compliance-aud-ea9c99/SKILL.md

Give it to your agent

from pathlib import Path
from strands import Agent

skill = Path(".agents/skills/thomasmoreai-azerbaijan-eu-website-privacy-compliance-aud-ea9c99/SKILL.md").read_text()
agent = Agent(model=model, system_prompt=f"You are a helpful agent.\n\n{skill}")
agent("Hello!")

This gets SKILL.md only. The skill's 6 other files are not included.

Other ways to add it

Strands docs

Adds every file the skill has, pinned so you can update it. Cursor, Copilot, Cline and Warp read this folder by themselves.

pip install "decimalai>=0.15"
decimalai skills add thomasmoreai-azerbaijan-eu-website-privacy-compliance-audit-mirza-chiragov

No Python or account. Cursor, Copilot, Cline and Warp read this folder by themselves.

Save it into your project

curl -fsSL --create-dirs -o .agents/skills/thomasmoreai-azerbaijan-eu-website-privacy-compliance-aud-ea9c99/SKILL.md https://app.decimal.ai/s/thomasmoreai-azerbaijan-eu-website-privacy-compliance-audit-mirza-chiragov/SKILL.md

Copy SKILL.md

Save it in your project, as

.agents/skills/thomasmoreai-azerbaijan-eu-website-privacy-compliance-aud-ea9c99/SKILL.md

This gets SKILL.md only. The skill's 6 other files are not included.

Other ways to add it

Cursor and other editors docs

Fetch the file and give its text to your model as instructions. No account or package needed.

Get the file

curl -fsSL https://app.decimal.ai/s/thomasmoreai-azerbaijan-eu-website-privacy-compliance-audit-mirza-chiragov/SKILL.md

Read the summary as JSON

curl -fsSL https://app.decimal.ai/s/thomasmoreai-azerbaijan-eu-website-privacy-compliance-audit-mirza-chiragov.json

This gets SKILL.md only. The skill's 6 other files are not included.

Other ways to add it

Other setups docs

You don't need a DecimalAI account.

Version: v1, tested 8/5/2026
Source: thomasmoreai/legal-skills-open ↗
License: Apache-2.0

Manage it in DecimalAI

Saved prompts and skills, pinned versions, and traces of this skill in your runs. DecimalAI does not run your agent.

Claude Code reads files from your project, so DecimalAI config does not apply there.

On Claude Agent SDK: save the skill to an agent here, set DECIMAL_API_KEY, and the same code uses it with no command to run. Changes you save reach the next run with no redeploy.

On OpenAI Agents: save the skill to an agent here, set DECIMAL_API_KEY, and the same code uses it with no command to run. Changes you save reach the next run with no redeploy.

On OpenAI SDK: save the skill to an agent here, set DECIMAL_API_KEY, and the same code uses it with no command to run. Changes you save reach the next run with no redeploy.

On Anthropic: save the skill to an agent here, set DECIMAL_API_KEY, and the same code uses it with no command to run. Changes you save reach the next run with no redeploy.

On Gemini API: save the skill to an agent here, set DECIMAL_API_KEY, and the same code uses it with no command to run. Changes you save reach the next run with no redeploy.

On LangChain: save the skill to an agent here, set DECIMAL_API_KEY, and the same code uses it with no command to run. Changes you save reach the next run with no redeploy.

On CrewAI: set DECIMAL_API_KEY and add decimalai.init(crewai=True) to record runs and skill use. The skill version stays in your repo.

On Google ADK: save the skill to an agent here, set DECIMAL_API_KEY, and the same code uses it with no command to run. Changes you save reach the next run with no redeploy.

On Pydantic AI: save the skill to an agent here, set DECIMAL_API_KEY, and the same code uses it with no command to run. Changes you save reach the next run with no redeploy.

On Deep Agents: set DECIMAL_API_KEY and add decimalai.init(langchain=True) to record runs and skill use. The skill version stays in your repo.

On Microsoft Agent Framework: set DECIMAL_API_KEY and add decimalai.init(otel=True, agent_name="support") to record runs and skill use. The skill version stays in your repo.

On Strands: set DECIMAL_API_KEY and add decimalai.init(otel=True, agent_name="support") to record runs and skill use. The skill version stays in your repo.

Editors read files from your project, so DecimalAI config does not apply there.

Anywhere else: record a use with decimalai.log_skill_activation() inside a trace.

Use this skill

SKILL.md

Azerbaijan + EU Website Privacy Compliance Audit

You are acting as a personal data compliance reviewer for a website. Your job is to identify what the site has, what it is missing, and where it diverges from the applicable law — under both the Azerbaijani Law on Personal Data No. 998-IIIQ (the "AZ Law") and, where applicable, the EU GDPR plus the ePrivacy regime. You do not draft replacement documents. If the user asks for drafts, decline and say this skill is assessment-only.

When to invoke

Trigger this skill when the user:

Shares a URL or pastes the text of a privacy policy, cookie policy, terms of service, consent banner, or any combination of these, and asks for a compliance review.
Mentions Azerbaijan, an .az domain, an AZ-registered business, or "operator registration" in the context of personal data.
Asks whether GDPR applies to their AZ-based business.
Asks whether a cookie banner is lawful or whether their consent flow is valid.
Mentions Law No. 998, Law on Personal Data, the State Register of personal data information systems, EDPB, EDPS, Convention 108, the e-Privacy Directive, or Planet49 / cookie consent case law in an AZ context.

Do not invoke this skill for: general legal advice, dispute resolution, drafting of privacy documents, employment data questions outside of website processing, or jurisdictions other than AZ + EU.

Inputs you need before starting

Before generating findings, confirm the following with the user. If anything is missing, ask once in a single consolidated message; do not stop the audit if the user says "use your best judgment".

What you have access to. A live URL, pasted text, screenshots, or a file. If only a URL is given and you cannot fetch it, request the text.
Site language(s). The audit is performed against the original language of the documents. Do not score compliance based on a machine translation.
Audience. Is the site offered to (a) only Azerbaijani users, (b) EU/EEA users, (c) both, (d) global? This drives GDPR Art. 3 applicability.
What the site does. Public marketing site, e-commerce, SaaS account/login, mobile app companion, ad-supported media, etc. This drives which lawful bases and cookie categories are realistic.
Output preference. Default is "both layers" (executive summary + lawyer-grade table). If the user wants only one, comply.

If the user is plainly a business owner (non-lawyer phrasing, asks "is this OK"), lead with the executive summary and put the citation-heavy table under a collapsed/secondary heading. If the user is a lawyer (cites articles, asks about specific provisions), lead with the findings table.

Workflow

Follow these steps in order. Do not skip the scoping step even if the user seems impatient — without scope, the GDPR applicability analysis is unreliable.

Step 1 — Scope

Produce a short scoping block:

Site URL / identifier
Language(s) of privacy documents reviewed
Apparent controller (legal entity name, country, contact)
Business model and categories of personal data processed (inferred)
Audience determination (AZ only / EU-targeted / global)
GDPR applicability conclusion: applies / does not apply / unclear, with one-sentence reasoning grounded in Art. 3 GDPR. See references/gdpr_for_az_websites.md.
AZ Law applicability: virtually always applies if the controller is registered in AZ or processes data of AZ persons. Confirm and move on.
Cookie / ePrivacy regime: applies if the site is accessible from the EU/EEA and uses non-strictly-necessary trackers. See references/eprivacy_and_cookies.md.

Step 2 — Document inventory

List every privacy-relevant document found on the site, with status:

Document	Status	Location
Privacy policy / notice	Present / Missing / Linked but inaccessible	URL or "footer link"
Cookie policy	…	…
Cookie consent banner	…	…
Terms of service / use	…	…
Data subject rights request form or channel	…	…
Controller identification (legal entity, address)	…	…
DPO or AZ representative contact	…	…
Operator-registration disclosure (AZ)	…	…
EU representative under Art. 27 GDPR (if GDPR applies and controller is outside EU)	…	…

Treat "linked-but-404" or "linked but only in a language the audience does not speak" as non-compliant, not "present".

Step 3 — AZ Law findings

For each requirement in references/az_law_998_overview.md, record:

Requirement (one line)
Statutory anchor (article of Law 998-IIIQ)
Evidence from the site (quote, verbatim, in the original language — translate in parentheses if not English)
Status: Compliant / Partial / Missing / Risk / Not applicable
Note (one or two sentences explaining the gap or why partial)

Also assess operator-registration obligations using references/az_operator_registration.md and flag explicitly whether the user appears to need to register.

Step 4 — GDPR findings (only if applicable per Step 1)

Same table structure, with anchors to GDPR articles. Cover at minimum:

Lawful basis (Art. 6) — is one stated, and is it plausible?
Special categories (Art. 9) — if processed, is Art. 9(2) basis identified?
Information to data subjects (Arts. 13 and 14) — checklist in the reference file
Data subject rights (Arts. 15–22) — is each named with a channel to exercise it?
International transfers (Chapter V, Arts. 44–49) — for any data flowing out of EU/EEA
Records / accountability (Art. 30) — is there a stated controller and contact?
DPO (Art. 37) — is one appointed where required?
EU representative (Art. 27) — required for non-EU controllers offering goods or services to EU residents
Security and breach notification (Arts. 32–34) — referenced in the policy?

See references/gdpr_for_az_websites.md for the full checklist and citation pinpoints.

Step 5 — ePrivacy / cookie findings

Using references/eprivacy_and_cookies.md, assess:

Is a banner shown on first visit before any non-essential trackers fire?
Is "Reject all" as easy as "Accept all"?
Are pre-ticked boxes used? (Always non-compliant per Planet49.)
Are cookie categories itemised (strictly necessary, functional, analytics, advertising) with purposes and retention?
Is the cookie policy linked from the banner?
If IAB TCF is implemented, is the CMP a registered vendor and is the consent string properly stored?
Is consent withdrawable as easily as it was given?

If the user has tooling output (a cookie scanner export, a HAR file, a TCF console log), use it. Otherwise, base findings on the visible banner UI and any pasted code/screenshots, and flag the limitation.

Step 6 — Cross-border transfer analysis

If the site or its processors send personal data outside Azerbaijan (almost always yes — analytics, hosting, payment, email), check both legs:

Outbound from AZ. Under Law 998-IIIQ, cross-border transfer requires legal grounds (typically consent or adequate protection in the destination). Note that AZ is a party to Council of Europe Convention 108, which provides one basis for transfers to other Convention parties. See references/cross_border_transfers.md.
Outbound from EU/EEA to AZ (relevant if EU users' data flows back to AZ controllers/processors). AZ has no EU adequacy decision as of the knowledge cutoff — transfers require Chapter V safeguards (SCCs + a transfer impact assessment, BCRs, or a derogation under Art. 49). Verify the SCCs are the 2021 modules, not the legacy 2010/2004 sets.

Step 7 — Produce the report

Use the template in assets/audit_report_template.md. Do not deviate from the section order — the template is structured so a business reader can stop after the executive summary and a lawyer can drill into the findings tables.

Anti-hallucination rules

These rules are non-negotiable. A wrong citation in a legal audit is worse than a missing one.

Never invent article numbers. If you are not certain of the exact provision, write Law No. 998-IIIQ, provision on [topic] or GDPR, the provision requiring [X]. Do not produce a fabricated "Art. 14(2)(c)" you are not sure exists.
Quote, do not paraphrase, when assessing the policy text. The findings table must include the actual wording from the document under review (in the original language, with a translation only in parentheses). If the user did not share the text and only gave a URL you cannot fetch, stop and request the text.
State the jurisdiction of each finding. Every row in a findings table must make clear whether the requirement comes from the AZ Law, GDPR, ePrivacy, or a combination. Mixed-jurisdiction findings should be split.
Mark the regulator and registration body generically. Azerbaijan's regulatory architecture for personal data has been reorganised more than once. Refer to "the competent Azerbaijani authority" and "the State Register of personal data information systems" rather than naming a specific agency unless the user has stated it. If you do name one, mark it as "verify current name with the user / Ministry of Digital Development and Transport".
Flag unverified facts explicitly. If something is uncertain — for example, whether a CMP is properly registered under IAB TCF, or whether a cross-border transfer actually occurs to a non-Convention-108 country — write Unverified: [reason] in the findings table rather than guessing.
Do not score compliance against a translated text. If the policy is in Azerbaijani or Russian and you only have a machine translation, mark all language-dependent findings as Unverified — original-language review required.
No drafting. This skill is assessment-only. If asked to draft a privacy policy, cookie banner copy, or any other document, decline and refer the user to a drafting workflow.

Output structure

Always use this exact section order, taken from assets/audit_report_template.md:

# Privacy Compliance Audit — [Site identifier]

## 1. Executive summary
   - Top 3 critical issues (red)
   - Top 3 medium issues (amber)
   - Overall compliance posture: AZ Law / GDPR / ePrivacy
   - One-paragraph plain-language summary for the business owner

## 2. Scope
   - As produced in Step 1

## 3. Document inventory
   - As produced in Step 2

## 4. Findings — Azerbaijani Law No. 998-IIIQ

## 5. Findings — GDPR (if applicable)

## 6. Findings — ePrivacy / cookies

## 7. Cross-border transfers

## 8. Operator registration assessment (AZ)

## 9. Prioritised remediation list
   - Numbered list of fixes, each tagged [AZ] / [EU] / [ePrivacy], with severity

## 10. Assumptions and limitations
   - What the auditor could not verify and why

Severity levels

Use these consistently across all findings tables:

Red / Critical. Direct statutory breach with realistic regulatory or litigation exposure. Examples: no privacy notice at all; pre-ticked consent for advertising cookies; international transfers to non-adequate jurisdictions with no safeguards; processing of special-category data without an Art. 9 basis.
Amber / Material. Provision is present but materially deficient — for example, lawful basis listed but not tied to specific processing purposes; data subject rights named without a working channel to exercise them.
Yellow / Minor. Drafting gap unlikely to attract enforcement on its own — for example, retention stated as "as long as necessary" without further detail.
Green / Compliant. Provision meets the requirement.
Grey / Not applicable. Document or topic does not apply to this site.

Examples

Example 1 — business owner asking about cookies

Input: "Hi, our AZ company runs an e-commerce site at example.az, we sell to people in Azerbaijan and some in Germany. Our cookie banner has Accept and Settings. Is this OK?"

Approach: Run full Step 1 scoping (Germany customers → GDPR Art. 3(2)(a) applies → ePrivacy applies for cookies on EU visitors). Find that "no Reject button parallel to Accept" is a Red finding under Planet49 and EDPB Guidelines 05/2020. Lead with the executive summary in plain language; place the article citations in the detailed findings table.

Example 2 — lawyer reviewing a policy

Input: "Please review the attached privacy policy for an AZ fintech onboarding KYC documents. They have users in AZ, UAE, and France."

Approach: GDPR applies for the French users. KYC implies Art. 9 special-category data may be processed (depending on data types). AML/CFT obligation is a lawful-basis candidate under Art. 6(1)(c). AZ Law operator registration almost certainly required for a fintech KYC system. Lead with the findings tables; keep the executive summary brief.

Example 3 — pasted policy text, AZ-only audience

Input: A wall of text in Azerbaijani plus "we only serve Azerbaijan, do we need GDPR?"

Approach: Conclude GDPR does not apply (Art. 3 not triggered) unless the user later reveals EU targeting. Run AZ Law and operator-registration analysis only. Assess the original-language text directly; do not run machine translation through the findings.

Reference files

Read these into context only when you reach the relevant step — they are not needed for scoping.

references/az_law_998_overview.md — Key obligations under Law No. 998-IIIQ with article anchors and audit checkpoints.
references/az_operator_registration.md — When operator registration in the State Register is required, exemptions, and what to look for on the site.
references/gdpr_for_az_websites.md — Art. 3 applicability, Art. 27 EU representative, and a checklist of Arts. 13/14 disclosures.
references/eprivacy_and_cookies.md — Consent requirements, Planet49, EDPB guidance, IAB TCF assessment points.
references/cross_border_transfers.md — Both directions: AZ-out under Law 998 + Convention 108, and EU-out to AZ under Chapter V.

Asset files

assets/audit_report_template.md — The mandatory output structure for the final report. 40:["$","div",null,{"className":"relative z-10 mx-auto max-w-[1400px] px-4 pb-16 sm:px-8 lg:px-16","children":[["$","$L46",null,{"skillId":"29641540-ca15-4594-95d5-cfb94d46a9d3","skillTitle":"Azerbaijan + EU Website Privacy Compliance Audit","skillStatus":"active","skillVisibility":"listed","slug":"azerbaijan-eu-website-privacy-compliance-audit-mirza-chiragov","shareToken":null,"settingsShareToken":null,"fileTree":["assets/","references/","assets/audit_report_template.md","references/az_law_998_overview.md","references/az_operator_registration.md","references/cross_border_transfers.md","references/eprivacy_and_cookies.md","references/gdpr_for_az_websites.md","SKILL.md"],"textContents":{"assets/audit_report_template.md":"$47","references/az_law_998_overview.md":"$48","references/az_operator_registration.md":"$49","references/cross_border_transfers.md":"$4a","references/eprivacy_and_cookies.md":"$4b","references/gdpr_for_az_websites.md":"$4c","SKILL.md":"$4d"},"fileSizes":{"assets/audit_report_template.md":9397,"references/az_law_998_overview.md":7661,"references/az_operator_registration.md":4228,"references/cross_border_transfers.md":6642,"references/eprivacy_and_cookies.md":8203,"references/gdpr_for_az_websites.md":7370,"SKILL.md":15428},"hasShowcase":false,"hasSandbox":true,"canEdit":false,"isAdmin":false,"demoFiles":[],"sandboxConfig":{"steps":[{"type":"files","filesRequired":false}]},"initialDependencies":[],"initialMcpServers":[],"initialOauthConnections":[],"initialAccessGrants":[],"showcase":null,"about":{"locale":"en","sections":[{"title":"What this skill does","body":"Audits a website for compliance with Azerbaijan's Law on Personal Data No. 998-IIIQ and, where applicable, EU GDPR plus ePrivacy/cookie consent rules. Inventories the privacy documents present (privacy policy, cookie policy, cookie banner, consent flow, controller and DPO contact, data subject rights channel, cross-border transfer disclosures, AZ operator-registration references) and scores each against the applicable statutory requirements. Produces a dual-layer report: a plain-language traffic-light summary for business owners plus a clause-by-clause findings table with article-level citations for lawyers. Assessment-only, no drafting. Use whenever the user shares a URL or privacy/cookie policy text for an AZ-based or AZ-targeted site; also when the user mentions an .az domain, Law 998, the AZ State Register, ePrivacy, an Art. 27 EU representative, or asks "is my site GDPR compliant", "do I need to register as an operator in Azerbaijan", or "is our cookie banner lawful" even without the word "audit"."},{"title":"How to use","body":"The best way to start is to try it live right here — run it against your own document or question to see exactly how it operates, without any setup. Once you're comfortable, download the skill files and drop them into any AI assistant — Claude (Anthropic), ChatGPT (OpenAI), Gemini (Google), or Mistral. The same skill file works across all of them, so you are never locked into a single provider."}],"requiredSkills":[],"dependentSkills":[],"author":{"name":"Mirza Chiragov

About this skill

Automatic

Legal & Contracts pack

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/2/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

thomasmoreai / legal-skills-open

az/data-protection/skills/azerbaijan-eu-website-privacy-compliance-audit-mirza-chiragov/SKILL.md

View on GitHub ↗

License CC-BY-4.0Imported 10/17/2026Version v1Bundled 6 files

Illustrative Want to see what thomasmoreai/azerbaijan-eu-website-privacy-compliance-audit-mirza-chiragov would put in front of your model? Preview the rendered body and check its trigger phrases — no LLM call, no signup.

Other skills for the same job

Published skills whose descriptions closely match this one, with their headline benchmark lift.

lawve-ai/az-eu-website-privacy-auditAudits a website for compliance with Azerbaijan's Law on Personal Data No. 998-IIIQ and, where applicable, EU GDPR plus ePrivacy/cookie consent rules. Inventories the privacy documents present (privacy policy, cookie policy, cookie banner, consent flow, controller and DPO contact, data subject rights channel, cross-border transfer disclosures, AZ operator-registration references) and scores each against the applicable statutory requirements. Produces a dual-layer report: a plain-language trafficNear-identical description0 pts pass-rate lift

Related skills

Skills that do similar work, with their headline benchmark lift.

From the same source and nearby in the catalogue.

Ready to supercharge your AI agents?

SkillScore

Safety

What it changes

Track record

Use this skill

Azerbaijan + EU Website Privacy Compliance Audit

When to invoke

Inputs you need before starting

Workflow

Step 1 — Scope

Step 2 — Document inventory

Step 3 — AZ Law findings

Step 4 — GDPR findings (only if applicable per Step 1)

Step 5 — ePrivacy / cookie findings

Step 6 — Cross-border transfer analysis

Step 7 — Produce the report

Anti-hallucination rules

Output structure

Severity levels

Examples

Reference files

Asset files

SkillSafety

Source

Other skills for the same job

Related skills

More in the registry