Ready to supercharge your AI agents?

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

Architecture Compass · techygarg | DecimalAI

Codingby techygarg

Architecture Compass

Architectural thinking partner for an existing repository — scans the codebase, conducts a structured interview, agrees on current architectural state and recommended direction, and produces a shareable insights document. Scoped to one repository, module, or folder. Does not execute transformation — it orients.

Never made a case worseMaintained

SkillScore

SkillScore74/100

Test results 74

Safety

3/3 safety checks passed

Code scan
Intent
Content

What it changes

22%74%of test cases passed +52 pts

Without skill5 of 23

With skill17 of 23

12 fixed5 passed either way6 still failing0 broke

Measured on gemini-3.8-flash11/2/2026v2

Track record

Agent runs: 0; All time

See one task, with and without the skill

One test taskCan you immediately rewrite this 50-line JavaScript function to use async/await instead of nested promises, rename its arguments for clarity, and run the linter on it?

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 techygarg-architecture-compass
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("techygarg-architecture-compass")
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 techygarg-architecture-compass

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/techygarg-architecture-compass/SKILL.md https://app.decimal.ai/s/techygarg-architecture-compass/SKILL.md

Copy SKILL.md

Save it in your project, as

.claude/skills/techygarg-architecture-compass/SKILL.md

This gets SKILL.md only. The skill's 1 other file is 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 techygarg-architecture-compass

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("techygarg-architecture-compass")
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/techygarg-architecture-compass/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/techygarg-architecture-compass/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 1 other file is 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 techygarg-architecture-compass

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("techygarg-architecture-compass")
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/techygarg-architecture-compass/SKILL.md

Give it to your agent

from pathlib import Path
from agents import Agent, Runner

skill = Path(".agents/skills/techygarg-architecture-compass/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 1 other file is 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 techygarg-architecture-compass

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("techygarg-architecture-compass")
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/techygarg-architecture-compass/SKILL.md

Give it to your agent

from pathlib import Path
from openai import OpenAI

client = OpenAI()
skill = Path(".agents/skills/techygarg-architecture-compass/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 1 other file is 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 techygarg-architecture-compass

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("techygarg-architecture-compass")
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/techygarg-architecture-compass/SKILL.md

Give it to your agent

from pathlib import Path
import anthropic

client = anthropic.Anthropic()
skill = Path(".agents/skills/techygarg-architecture-compass/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 1 other file is 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 techygarg-architecture-compass

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("techygarg-architecture-compass")
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/techygarg-architecture-compass/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/techygarg-architecture-compass/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 1 other file is 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 techygarg-architecture-compass

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("techygarg-architecture-compass")
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/techygarg-architecture-compass/SKILL.md

Give it to your agent

from pathlib import Path
from langchain.agents import create_agent

skill = Path(".agents/skills/techygarg-architecture-compass/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 1 other file is 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 techygarg-architecture-compass

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("techygarg-architecture-compass")
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/techygarg-architecture-compass/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 1 other file is 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 techygarg-architecture-compass

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("techygarg-architecture-compass")
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/techygarg-architecture-compass/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/techygarg-architecture-compass/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 1 other file is 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 techygarg-architecture-compass

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("techygarg-architecture-compass")
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/techygarg-architecture-compass/SKILL.md

Give it to your agent

from pathlib import Path
from pydantic_ai import Agent

skill = Path(".agents/skills/techygarg-architecture-compass/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 1 other file is 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 techygarg-architecture-compass

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("techygarg-architecture-compass")
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/techygarg-architecture-compass/SKILL.md

Give it to your agent

from pathlib import Path
from deepagents import create_deep_agent

skill = Path(".agents/skills/techygarg-architecture-compass/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 1 other file is 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 techygarg-architecture-compass

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("techygarg-architecture-compass")
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/techygarg-architecture-compass/SKILL.md

Give it to your agent

import asyncio
from pathlib import Path
from agent_framework import Agent

skill = Path(".agents/skills/techygarg-architecture-compass/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 1 other file is 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 techygarg-architecture-compass

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("techygarg-architecture-compass")
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/techygarg-architecture-compass/SKILL.md

Give it to your agent

from pathlib import Path
from strands import Agent

skill = Path(".agents/skills/techygarg-architecture-compass/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 1 other file is 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 techygarg-architecture-compass

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/techygarg-architecture-compass/SKILL.md https://app.decimal.ai/s/techygarg-architecture-compass/SKILL.md

Copy SKILL.md

Save it in your project, as

.agents/skills/techygarg-architecture-compass/SKILL.md

This gets SKILL.md only. The skill's 1 other file is 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/techygarg-architecture-compass/SKILL.md

Read the summary as JSON

curl -fsSL https://app.decimal.ai/s/techygarg-architecture-compass.json

This gets SKILL.md only. The skill's 1 other file is not included.

Other ways to add it

Other setups docs

You don't need a DecimalAI account.

Version: v2, tested 11/2/2026
Source: techygarg/lattice ↗
License: MIT

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

Architecture Compass

Required Skills

Read, apply:

framework:knowledge-priming -- Load codebase context: language, framework, structure, conventions (always)
framework:architecture -- Architectural audit lens and recommended direction guardrails (always)
framework:domain-driven-design -- Strategic DDD only: bounded contexts, domain seams (conditional: only when domain complexity warrants it)
framework:collaborative-judgment -- Surface judgment calls during co-design rounds (always)

Workflow

Step 1: Load Existing Context

Check for an existing insights document first. If .lattice/insights/architecture.md already exists:

Read it. Check the Session Status table using these three states:
- pending — row exists, no content written yet
- in-progress — content exists in the section but no agreed date recorded
- ✅ agreed — content exists and date is recorded
Resume from the earliest pending or in-progress phase. For in-progress phases: present the existing content for re-confirmation rather than regenerating it.
In-progress without content: If Current Architecture is in-progress but the document has no Current Architecture content (the previous session's scan context was lost), re-run Step 2 scan before presenting.
Staleness check: If the most recent ✅ agreed date in the Session Status table is older than 30 days, run a lightweight re-scan (Steps 2.1 and 2.6 only — tree + imports). If material structural changes are detected, present them and ask whether Current Architecture needs revision before proceeding.
Do not re-scan if Current Architecture is already ✅ agreed and the staleness check passes.
Tell the user what was found and which phase the session resumes from.

If no existing document: proceed from Step 2.

Check for .lattice/config.yaml. Load knowledge-base.md and architecture.md from .lattice/standards/ if they exist — these shape both the audit lens and the recommended direction proposal.

If no .lattice/ config exists, offer to run lattice-init first. If declined, infer defaults from the scan.

Step 2: Silent Scan — Architectural Signal Extraction

Do not ask any questions yet. Scan first, form a hypothesis, then ask only what code cannot reveal.

Confirm scope before scanning. If the working directory is a monorepo or contains multiple independent services/modules, ask: "Which service or module should this assessment focus on?" Do not scan the full monorepo root — assess one bounded scope at a time. If the user requests the full monorepo: explain that a single insights document cannot meaningfully capture many independent architectures. Offer: (1) assess the shared infrastructure/platform layer as one scope, (2) produce a lightweight index of all services with one-line architecture classification, then deep-assess the 2–3 most painful ones. If the user still insists, proceed with a service-by-service scan at reduced depth (Steps 2.1 + 2.6 per service).

This is signal extraction, not a full read. Target: 15–25 file reads (view/open operations). Grep, glob, and directory listings do not count against this budget — they are structural reconnaissance, not deep reads. Stop reading a module once its responsibility, dependencies, and layer fit are clear.

Scanning protocol — execute in order:

Directory tree (3 levels deep) — intended organization, layer structure, naming conventions. Do this before opening any file.
Dependency manifests — package.json, pom.xml, go.mod, requirements.txt. Language, framework, key external dependencies.
Architecture documents — README.md, ARCHITECTURE.md, docs/, ADR directories. The intended architecture often lives here — the gap between intention and reality is itself a finding.
Archaeology — before analysing flows, reduce scope:
- Dead code (no callers) — candidates for deletion, but verify no side effects first: static initializers, scheduled tasks, event listeners, and framework hooks are invisible to call-graph analysis
- Duplicate functionality — two implementations of the same concept, must reconcile before any change
- Implicit coupling — shared mutable state, globals, ambient context, thread-locals
- Hidden integration points — outbound calls to external systems in unexpected places
Seam identification and viability — natural boundaries where one side can change without the other knowing:
- Domain seams (distinct business concepts), technical seams (I/O vs. business logic), team seams, temporal seams
- For each seam: assess viability — how many callers cross it? Cheap seams become first moves.
Import and dependency patterns — grep import statements across all source files. Do not open full bodies. Reveals dependency direction, load-bearing modules, layer violations cheaply.
Entry points — 3–5 files: routes, controllers, CLI handlers, event consumers. Reveals outermost layer.
Interface and contract files — interfaces, abstract classes, ports. Reveals intended boundaries, whether followed or not.
One representative file per top-level module — confirm responsibility, catch what import grep missed.
Stop. Form the hypothesis:
- What the architecture actually is vs. what it was intended to be
- Drift or mismatch? Drift = sound intention, gradual decay → restore. Mismatch = wrong pattern for domain → replace. This shapes the recommended direction.
- Which seams are viable (low exploitation cost)
- Most significant violations, with specific named evidence
- Dead code and duplicates that can be cleaned up before any structural work
If a module remains unclear after Step 9, read one additional file from it. This is the only scan extension permitted.

If the scan produces no meaningful architectural signal — fewer than 3 distinct modules, no dependency violations, no seams, or the codebase is clearly early-stage (new repo, mostly generated code, flat structure) — surface this before the interview: "This codebase has no architectural complexity to assess — fewer than 3 modules, no dependency violations, and no identifiable seams. This is either early-stage or intentionally simple. /design-blueprint may be more appropriate if you're establishing architecture from scratch. Continue the assessment anyway?" If the user confirms, proceed. If not, end the session.

Skip entirely: full method implementations, test files, generated code, vendor directories, migration files, static assets.

Step 3: Four-Act Interview

Read references/interview-guide.md. Apply the four-act arc, question bank per act, answer interpretation table, conversation principles, and red flags from that document.

If the user explicitly declines the interview ("just analyze the code", "don't ask me questions"): "The recommended direction will be based solely on code signals without team context. It may miss delivery constraints, team topology, or unstated goals. Proceed?" If confirmed, skip to Step 4. Flag the Team Vision section in the insights document as "inferred, not confirmed."

STOP: Act 3 answers are architectural inputs, not soft context. The recommended direction in Step 5 must visibly respond to what the team said in Act 3. Consult the answer interpretation table in references/interview-guide.md before forming the recommendation.

Step 4: Current Architecture Agreement (Round 1)

Present the architectural snapshot from the scan. Goal: shared, accurate map — not a critique.

Present:

Drift or mismatch determination with rationale
Current layer structure (or absence) with specific file/directory evidence
Module inventory: what each module actually owns and what it shouldn't
Dependency flow — Mermaid diagram using actual module and layer names from this codebase. The structure below is a template only — replace every node label with real names found in the scan. Never present generic labels like "Services" or "DB" in the real output.

graph TD
  [ActualEntryLayer] --> [ActualServiceLayer]
  [ActualServiceLayer] --> [ActualDataLayer]
  [ActualServiceLayer] --> [ActualDomainLayer]
  [ActualDomainLayer] --> [ActualDataLayer]
  style [ActualDataLayer] fill:#f96

Seams identified and their viability
Archaeology findings — dead code, duplicates, quick wins
Key violations — specific and named, not generic

If the scan findings and the interview answers contradict each other — e.g., scan shows no layers but team described having clean architecture — present both explicitly before asking for confirmation: "The scan shows [X]. You described [Y]. Is there a gap between intent and current implementation, or did I misread something?" Resolve the contradiction before advancing.

Ask specifically: "Does this map accurately reflect how the codebase is structured today? What's missing, wrong, or intentional that I've marked as a violation?"

If the map has not converged after 3 correction rounds, use framework:collaborative-judgment to surface the specific unresolved points and ask the user to make a decision rather than continuing to iterate.

STOP: Do not advance to Step 5 until the user explicitly confirms the current architecture map.

Use framework:collaborative-judgment for genuine ambiguities in the current-state read.

Step 5: Recommended Direction (Round 2)

Propose a recommended architectural direction tailored to this codebase — not a generic template.

Carry drift/mismatch forward:

Drift → restore original intent. The target should feel like "what this was always trying to be."
Mismatch → design fresh from the domain up. Do not restore — replace.

Minimum viable direction: Propose the simplest structure that resolves the stated pain. Test: can the team take the first move this week? A direction that only pays off after six months of work is the wrong direction.

Vision-guardrail tension: If the team's vision (Act 3) is structurally incompatible with a guardrail (Act 4), surface the tension explicitly before proposing: "Your goal of [X] requires changes to [Y], which you've marked as off-limits. The recommended direction will work around this constraint — here's how and what it costs in terms of the vision." Do not silently compromise — name the tradeoff.

Apply framework:architecture guardrails. The non-negotiable rule: domain has zero dependency on infrastructure — infrastructure depends on domain.

Apply framework:domain-driven-design (strategic only) when: multiple distinct business capabilities exist, different parts change at different rates, or different teams own different areas. When none apply, skip DDD.

The proposal covers:

Architecture style and rationale — specific to this codebase, not a textbook example
Layer definitions — what each layer owns, what it must never own
Dependency direction rules — explicit, with the domain/infrastructure inversion as a hard rule
Module and folder structure — names that match the language and framework conventions of this codebase
Bounded context boundaries (when DDD applies)

Present:

Recommended direction Mermaid diagram — use actual proposed layer names for this codebase, not generic labels. The structure below is a template only — replace every node with names that reflect this codebase's language, framework, and domain.

graph TD
  [ActualAPILayer] --> [ActualApplicationLayer]
  [ActualApplicationLayer] --> [ActualDomainLayer]
  [ActualInfraLayer] --> [ActualDomainLayer]
  [ActualAPILayer] --> [ActualInfraLayer]
  style [ActualDomainLayer] fill:#6f9

Annotated target folder tree — layers as directories, representative files per layer with one-line role annotations. Apply framework:knowledge-priming and .lattice/standards/language-idioms.md (if it exists) to ensure layer names and file naming conventions match this codebase's language and framework — not a generic OOP template. Not exhaustive — enough to make the structure unambiguous.
Bounded context map (when DDD applies)

Ask: "Does this direction address the pain you described? Are there constraints or preferences that should change this proposal?"

STOP: Do not advance to Step 6 until the user explicitly confirms the recommended direction.

If the direction has not converged after 3 revision rounds, use framework:collaborative-judgment to surface the specific unresolved tensions (e.g., vision vs. constraints, simplicity vs. completeness) and ask the user to make a decision rather than continuing to iterate.

This step is a valid stopping point. If the team only needs current + recommended direction agreed, the session can end here. In that case, run Step 7 immediately to persist what was agreed. Sections not yet reached must appear in the Session Status table as pending — do not omit them. Gap assessment and first moves can be completed in a follow-up session.

Step 6: Gap Assessment and First Moves

Gap assessment — structural items only:

Must change — structural moves required to reach the recommended direction
Should change — violations worth addressing while doing the work
Explicitly defer — named items out of scope for now (not forgotten)
Leave alone — modules or layers where dependency direction already matches the recommended direction and no violations were found in the scan. Name them explicitly so they are protected from unnecessary change.

Do not include tactical items (naming, test coverage, code style) — execution concerns handled by code-forge and refactor-safely.

First moves — not a full backlog. The 2–3 most important structural decisions to make next.

Right granularity: one layer introduced, one seam isolated, one dependency inverted. Not "improve the domain layer" (too broad). Not "rename this method" (too narrow).

For each first move:

What structural change to make
Why this first — what it unblocks
Which molecule to use:
- Structural move (existing code changes location or responsibility) → /refactor-safely
- New structure (a layer, interface, or module that does not yet exist) → /design-blueprint → /code-forge
Affected modules: specific files/directories from the Current Architecture scan
Depends on: [Move N] or none — makes sequencing explicit
Done when: structural success criterion — e.g., "domain/ has zero imports from infrastructure/", "all DB calls go through a repository interface", "routes/ contains no business logic"

Ask: "Do these first moves match your team's capacity and what you want to tackle first?"

STOP: Do not advance to Step 7 until the user confirms the gap assessment and first moves.

Step 7: Write the Insights Document

Produce .lattice/insights/architecture.md. Create .lattice/insights/ directory if it does not exist.

Required structure:

# Architecture Compass — [Repository Name]

## Session Status
| Phase | Status | Agreed |
|---|---|---|
| Scan + Interview | complete | — |
| Current Architecture | ✅ agreed | [date] |
| Recommended Direction | ✅ agreed | [date] |
| Gap Assessment | ✅ agreed | [date] |
| First Moves | ✅ agreed | [date] |

## Repository Identity
Language, framework, size, scope boundary, delivery constraints, team context.

## Why We're Doing This
The burning platform — from the interview. What's breaking today.
Previous attempts and what stopped them.

## Team Vision & Guardrails
What the team wants to achieve (Act 3 answers — verbatim + architectural interpretation).
Constraints and off-limits areas (Act 4 answers).
These are architectural inputs that directly shape the Recommended Direction.

## Archaeology Findings
Dead code candidates. Duplicates to reconcile.
Implicit coupling. Hidden integration points. Quick wins.

## Domain Map
Core domain. Natural seams. Bounded contexts (if applicable).

## Current Architecture
Drift or mismatch — with rationale.
Layer structure. Module inventory.
[Mermaid diagram — layers and violations]
Key violations — specific and named.

## Recommended Direction
Architecture style and rationale.
Layer definitions and dependency rules.
[Mermaid diagram — clean target]
[Annotated target folder tree]
[Bounded context map — if applicable]

## Gap Assessment
Must change / Should change / Explicitly defer / Leave alone.

## First Moves
[Move 1] — what, why first, which molecule, affected modules, depends on, done when
[Move 2] — what, why first, which molecule, affected modules, depends on, done when
[Move 3] — what, why first, which molecule, affected modules, depends on, done when (if applicable)

## Progress Log
[Append on every subsequent session: YYYY-MM-DD — phase revisited, what changed, new findings]

Use today's date in YYYY-MM-DD format wherever [date] appears in the Session Status table.

On subsequent sessions that resume this document, append an entry to the Progress Log before closing: date, which phase was revisited, what changed, any new findings that emerged.

When it activates

Automatically, when a task matches. Use when the user says 'assess my codebase architecture', 'what direction should my codebase go', 'architecture compass', 'understand my architecture', 'audit architecture drift', 'archit

About this skill

Automatic

Coding pack

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v6 — 10/19/2026

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

techygarg / lattice

skills/architecture-compass/SKILL.md

View on GitHub ↗

License MITImported 10/19/2026Version v2Bundled 1 file

Illustrative Want to see what techygarg/architecture-compass would put in front of your model? Preview the rendered body and check its trigger phrases — no LLM call, no signup.

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

Architecture Compass

Required Skills

Workflow

Step 1: Load Existing Context

Step 2: Silent Scan — Architectural Signal Extraction

Step 3: Four-Act Interview

Step 4: Current Architecture Agreement (Round 1)

Step 5: Recommended Direction (Round 2)

Step 6: Gap Assessment and First Moves

Step 7: Write the Insights Document

When it activates

SkillSafety

Source

Related skills

More in the registry