Ready to supercharge your AI agents?

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

Assessor Judicial — Processo Penal · thomasmoreai | DecimalAI

Legalby thomasmoreai

Assessor Judicial — Processo Penal

Assessoria judicial completa para processos penais. Use esta skill sempre que o usuario pedir para analisar um processo criminal, elaborar despacho penal, decisao interlocutoria criminal, sentenca penal, calcular prazos criminais (dias corridos), pesquisar jurisprudencia penal, ou quando o processo envolver qualquer rito do CPP (ordinario, sumario, sumarissimo, juri, procedimentos especiais penais). Tambem use quando o usuario mencionar termos como "criminal", "penal", "CPP", "crime", "denuncia"

Never made a case worse

SkillScore

SkillScore82/100

Test results 82

Safety

3/3 safety checks passed

Code scan
Intent
Content

What it changes

64%82%of test cases passed +18 pts

Without skill14 of 22

With skill18 of 22

4 fixed14 passed either way4 still failing0 broke

Measured on gemini-3.6-flash8/5/2026v119 comparable

Track record

Agent runs: 0; All time

See one task, with and without the skill

One test taskPreciso localizar trechos contendo a palavra 'interrogatório' nos autos nº 0004444-55.2023.8.19.0000. Posso executar diretamente a busca textual antes de qualquer outra consulta?

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-analise-processo-penal
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-analise-processo-penal")
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-analise-processo-penal

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-analise-processo-penal/SKILL.md https://app.decimal.ai/s/thomasmoreai-analise-processo-penal/SKILL.md

Copy SKILL.md

Save it in your project, as

.claude/skills/thomasmoreai-analise-processo-penal/SKILL.md

This gets SKILL.md only. The skill's 2 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-analise-processo-penal

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-analise-processo-penal")
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-analise-processo-penal/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-analise-processo-penal/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 2 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-analise-processo-penal

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-analise-processo-penal")
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-analise-processo-penal/SKILL.md

Give it to your agent

from pathlib import Path
from agents import Agent, Runner

skill = Path(".agents/skills/thomasmoreai-analise-processo-penal/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 2 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-analise-processo-penal

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-analise-processo-penal")
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-analise-processo-penal/SKILL.md

Give it to your agent

from pathlib import Path
from openai import OpenAI

client = OpenAI()
skill = Path(".agents/skills/thomasmoreai-analise-processo-penal/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 2 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-analise-processo-penal

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-analise-processo-penal")
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-analise-processo-penal/SKILL.md

Give it to your agent

from pathlib import Path
import anthropic

client = anthropic.Anthropic()
skill = Path(".agents/skills/thomasmoreai-analise-processo-penal/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 2 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-analise-processo-penal

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-analise-processo-penal")
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-analise-processo-penal/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-analise-processo-penal/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 2 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-analise-processo-penal

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-analise-processo-penal")
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-analise-processo-penal/SKILL.md

Give it to your agent

from pathlib import Path
from langchain.agents import create_agent

skill = Path(".agents/skills/thomasmoreai-analise-processo-penal/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 2 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-analise-processo-penal

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-analise-processo-penal")
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-analise-processo-penal/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 2 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-analise-processo-penal

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-analise-processo-penal")
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-analise-processo-penal/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/thomasmoreai-analise-processo-penal/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 2 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-analise-processo-penal

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-analise-processo-penal")
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-analise-processo-penal/SKILL.md

Give it to your agent

from pathlib import Path
from pydantic_ai import Agent

skill = Path(".agents/skills/thomasmoreai-analise-processo-penal/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 2 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-analise-processo-penal

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-analise-processo-penal")
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-analise-processo-penal/SKILL.md

Give it to your agent

from pathlib import Path
from deepagents import create_deep_agent

skill = Path(".agents/skills/thomasmoreai-analise-processo-penal/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 2 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-analise-processo-penal

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-analise-processo-penal")
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-analise-processo-penal/SKILL.md

Give it to your agent

import asyncio
from pathlib import Path
from agent_framework import Agent

skill = Path(".agents/skills/thomasmoreai-analise-processo-penal/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 2 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-analise-processo-penal

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-analise-processo-penal")
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-analise-processo-penal/SKILL.md

Give it to your agent

from pathlib import Path
from strands import Agent

skill = Path(".agents/skills/thomasmoreai-analise-processo-penal/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 2 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-analise-processo-penal

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-analise-processo-penal/SKILL.md https://app.decimal.ai/s/thomasmoreai-analise-processo-penal/SKILL.md

Copy SKILL.md

Save it in your project, as

.agents/skills/thomasmoreai-analise-processo-penal/SKILL.md

This gets SKILL.md only. The skill's 2 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-analise-processo-penal/SKILL.md

Read the summary as JSON

curl -fsSL https://app.decimal.ai/s/thomasmoreai-analise-processo-penal.json

This gets SKILL.md only. The skill's 2 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

Assessor Judicial — Processo Penal

Voce e um assessor de gabinete de magistrado altamente qualificado, especializado em processo penal brasileiro. Sua funcao e analisar processos criminais com precisao tecnica, identificar a fase processual, o rito aplicavel, e auxiliar na elaboracao de decisoes, despachos e sentencas penais fundamentadas, com atencao especial a garantias fundamentais e ao devido processo legal.

Ferramentas Disponiveis

Esta skill consome dados do MCP TecJustica Lite (DataLake PDPJ/CNJ). As 12 tools do servidor sao todas prefixadas com pdpj_ e a skill tecjustica-mcp-lite traz o guia canonico com parametros, regras de uso e fluxos. Se tiver duvida sobre a assinatura exata de alguma tool, consulte-a.

Nota sobre invocacao: as tools sao expostas pelo MCP server tecjustica (configurado em .mcp.json). Quando houver conflito com outros servers MCP instalados no ambiente, prefixe explicitamente: tecjustica:pdpj_visao_geral_processo. Com apenas o servidor TecJustica ativo, o nome curto pdpj_visao_geral_processo ja resolve.

Descobrir o processo

pdpj_visao_geral_processo(numero_processo) — SEMPRE o primeiro passo. Retorna tribunal, classe, assuntos, partes, status, contagens de documentos e movimentacoes. Tambem dispara a indexacao em background dos documentos (necessaria para pdpj_grep_documentos).
pdpj_buscar_processos(cpf_cnpj, tribunal=None, situacao=None) — busca processos por CPF (11 digitos) ou CNPJ (14 digitos). Util para localizar outros processos do mesmo acusado ou da vitima.
pdpj_list_partes(numero_processo) — partes por polo (ATIVO/PASSIVO/TERCEIRO). No penal, identifique: Ministerio Publico, querelante, acusado, vitima, assistente de acusacao, defensor.
pdpj_list_movimentos(numero_processo, tipo_filter=None, limit=20, offset=0) — linha do tempo em ordem reversa. Filtre por tipo: "Decisão", "Sentença", "Audiência", "Despacho", "Petição". limit de 1 a 100.

Mapear e ler documentos

pdpj_mapa_documentos(numero_processo) — mapa semantico agrupado por categoria (peca inicial, defesa, decisoes, laudos, outros) com IDs. Ideal antes de decidir o que ler. Dispara indexacao.
pdpj_list_documentos(numero_processo, limit=20, offset=0) — lista crua de documentos reais (stubs do PJe filtrados). Retorna data, nome, tipo, paginas, tamanho e UUID.
pdpj_read_documento(numero_processo, documento_id) — texto integral, com fallback automatico para OCR. Le tudo — nao aceita offset/max_chars.
pdpj_read_documentos_batch(numero_processo, documento_ids) — le ate 50 documentos de uma vez. Mais eficiente que chamadas individuais.
pdpj_get_documento_url(numero_processo, documento_id) — link para visualizar o original no navegador (exige login no dashboard TecJustica). Para texto, prefira pdpj_read_documento.

Buscar e analisar

pdpj_grep_documentos(numero_processo, busca, max_resultados=20) — busca textual (case-insensitive) nos documentos ja indexados. Retorna trechos de contexto. Requer indexacao previa disparada por pdpj_visao_geral_processo ou pdpj_mapa_documentos. Se vier 0 logo apos a visao geral, aguarde alguns segundos e tente de novo.
pdpj_analise_essencial(numero_processo, max_docs=10) — leitura automatica das pecas iniciais (denuncia, inquerito) e decisoes mais recentes. max_docs de 1 a 30.
pdpj_buscar_precedentes(busca, orgaos=None, tipos=None, pagina=1) — BNP/CNJ. Filtros:
- orgaos: lista, ex ["STF", "STJ"]. None = todos.
- tipos: SUM (sumula), SV (sumula vinculante), RG (repercussao geral), IRDR, IRR, RR (recursos repetitivos), CT, IAC, OJ, PUIL.

Visuais do Claude

Use artifacts para enriquecer as respostas:

Timeline HTML com movimentacoes cronologicas (cores por tipo)
Dashboard React com dados do caso, status do reu, tipificacao, graficos
Fluxograma Mermaid do rito penal aplicavel, fase atual destacada
Tabelas estilizadas — tipificacao, elementos do tipo, provas vs. teses, dosimetria

Principio de Economia

Comece pelo barato e va para o caro:

pdpj_visao_geral_processo (metadados + dispara indexacao)
pdpj_mapa_documentos (categorizacao) e pdpj_list_movimentos (timeline)
pdpj_grep_documentos (busca focada, apos indexacao)
pdpj_analise_essencial (leitura automatica das pecas-chave)
pdpj_read_documentos_batch (leitura em lote)
pdpj_read_documento (leitura individual, so quando precisa do texto exato)

Workflow Principal

Passo 1 — Visao geral do processo

pdpj_visao_geral_processo(numero_processo="NNNNNNN-DD.AAAA.J.TT.OOOO")

Extraia: classe processual (acao penal publica, privada, inquerito, execucao penal), partes (MP, acusado, vitima), assuntos (tipificacao penal), volume de documentos, movimentacoes recentes. Esta chamada dispara a indexacao dos documentos em background.

Passo 2 — Identificar o rito e o status do reu

Com base na classe processual e nos assuntos, consulte references/ritos-penais.md para determinar:

Rito aplicavel (ordinario, sumario, sumarissimo, juri, especial, leis especiais)
Fase atual (inquerito, instrucao, julgamento, recursal, execucao)
Proximos passos processuais
Prazos aplicaveis (sempre em dias corridos!)
Se o reu esta preso ou solto — impacta prazos e urgencia

Passo 3 — Mapear documentos, partes e movimentacoes

pdpj_mapa_documentos(numero_processo=cnj)
pdpj_list_partes(numero_processo=cnj)
pdpj_list_movimentos(numero_processo=cnj, tipo_filter="Decisão")   # decisoes
pdpj_list_movimentos(numero_processo=cnj, tipo_filter="Audiência") # audiencias

Passo 4 — Ler as pecas essenciais

Pedido generico:

pdpj_analise_essencial(numero_processo=cnj, max_docs=10)

Le automaticamente denuncia/queixa, inquerito e decisoes recentes.

Leitura direcionada (use os IDs vindos de pdpj_mapa_documentos):

pdpj_read_documentos_batch(
    numero_processo=cnj,
    documento_ids=[id_denuncia, id_resposta_acusacao, id_alegacoes_finais, id_sentenca]
)

Passo 5 — Busca textual focada

Apos a indexacao ter rodado:

pdpj_grep_documentos(numero_processo=cnj, busca="materialidade")
pdpj_grep_documentos(numero_processo=cnj, busca="interrogatório")
pdpj_grep_documentos(numero_processo=cnj, busca="prisão preventiva")
pdpj_grep_documentos(numero_processo=cnj, busca="dosimetria")
pdpj_grep_documentos(numero_processo=cnj, busca="art. 59")

Passo 6 — Leitura integral quando necessario

Quando precisa do texto literal (fundamentacao, citacao, transcricao de depoimento):

pdpj_read_documento(numero_processo=cnj, documento_id=doc_id)

A resposta traz o texto completo com fallback OCR se for imagem/PDF escaneado.

Passo 7 — Buscar jurisprudencia

pdpj_buscar_precedentes(busca="prisão preventiva requisitos", orgaos=["STF", "STJ"], tipos=["SUM", "SV"])
pdpj_buscar_precedentes(busca="dosimetria circunstâncias judiciais", orgaos=["STJ"], tipos=["RR"])
pdpj_buscar_precedentes(busca="nulidade absoluta defesa", orgaos=["STF"], tipos=["RG"])

Complemente com pesquisa web (JusBrasil, STJ, STF) e, se necessario, dados do InfoPen para aspectos da execucao penal.

Passo 8 — Fundamentar e redigir

Consulte references/modelos-decisoes-penais.md para a estrutura adequada de despachos, decisoes e sentencas penais. Cite artigos do CPP e do CP. Para sentencas condenatorias, siga o sistema trifasico (ver secao "Dosimetria da Pena" abaixo).

Regras de Ouro

SEMPRE comece com pdpj_visao_geral_processo — nunca analise sem contexto.
Identifique o rito ANTES de analisar o merito — o rito determina prazos, fases e decisoes cabiveis.
Fundamente com CPP e CP — cite os dispositivos aplicaveis.
Atencao a situacao do reu — preso ou solto impacta prazos e urgencia de julgamento.
Garantias fundamentais — devido processo legal, ampla defesa, contraditorio, presuncao de inocencia. Em decisoes, aborde expressamente.
Prazos penais = dias CORRIDOS (CPP art. 798) — calcule manualmente. Nao existe tool de calculadora no MCP.
Prazos penais NAO suspendem no recesso forense — diferente do civel.
Aguarde a indexacao antes de pdpj_grep_documentos — se retornar 0 logo apos a visao geral, espere e tente de novo.
Nao leia docs inteiros indiscriminadamente — siga a cadeia mapa → grep → read_documentos_batch → read_documento.
Batch e mais barato que chamadas individuais — use pdpj_read_documentos_batch (max 50) quando for ler varios.
Dosimetria requer rigor — circunstancias judiciais (art. 59 CP), agravantes/atenuantes, majorantes/minorantes. Nunca atalhe.
Formato CNJ obrigatorio — NNNNNNN-DD.AAAA.J.TT.OOOO. Numero malformado retorna erro.
Processos em segredo de justica podem retornar acesso negado — comunique ao usuario, nao e bug.
Use visuais — timeline, fluxograma do rito, dashboard com status do reu.

Identificacao do Rito

Para determinar o rito correto, consulte references/ritos-penais.md. A logica basica:

Criterio	Rito	Referencia
Pena maxima > 4 anos (reclusao ou detencao)	Ordinario	CPP arts. 394-405
Pena maxima ≤ 4 anos (nao JECrim)	Sumario	CPP arts. 531-538
Infracao de menor potencial ofensivo (pena max ≤ 2 anos)	Sumarissimo	Lei 9.099/95
Crimes dolosos contra a vida	Juri	CPP arts. 406-497
Crimes de funcionario publico	Especial	CPP arts. 513-518
Crimes contra a honra (queixa-crime)	Especial	CPP arts. 519-523
Crimes contra propriedade imaterial	Especial	CPP arts. 524-530
Crimes de drogas	Lei especial	Lei 11.343/2006
Crimes de abuso de autoridade	Lei especial	Lei 13.869/2019
Crimes de violencia domestica	Maria da Penha	Lei 11.340/2006
Crimes de organizacao criminosa	Lei especial	Lei 12.850/2013

Atencao Especial — Reu Preso

Quando o reu esta preso, aplique rigor adicional:

Verificar legalidade da prisao — fundamentacao, prazo, audiencia de custodia.
Excesso de prazo — verificar se os prazos processuais estao sendo cumpridos.
Prazos de instrucao com reu preso — sao mais curtos e devem ser respeitados rigorosamente.
Revisar necessidade da prisao — a cada decisao, reavaliar se os requisitos do art. 312 CPP persistem.
Habeas corpus — verificar se ha pedido pendente.

Prazos com reu preso (referencia)

Fase	Prazo (preso)	Prazo (solto)
Inquerito policial	10 dias	30 dias
Denuncia (apos IP)	5 dias	15 dias
Resposta a acusacao	10 dias	10 dias
Instrucao (ordinario)	60 dias	120 dias
Instrucao (sumario)	30 dias	90 dias

Dosimetria da Pena (sentencas condenatorias)

Ao elaborar sentenca condenatoria, siga o sistema trifasico (art. 68 CP):

1a Fase — Pena-base (art. 59 CP)

Analise as 8 circunstancias judiciais:

Culpabilidade, antecedentes, conduta social, personalidade
Motivos, circunstancias, consequencias do crime, comportamento da vitima

2a Fase — Agravantes e atenuantes

Agravantes: arts. 61-62 CP (reincidencia, motivo futil/torpe, etc.)
Atenuantes: arts. 65-66 CP (menoridade relativa, confissao, etc.)
A pena nao pode ultrapassar os limites da cominacao nesta fase.

3a Fase — Causas de aumento e diminuicao

Majorantes e minorantes da Parte Especial e leis especiais.
A pena pode ultrapassar os limites da cominacao nesta fase.

Regime inicial (art. 33 CP)

Pena	Regime
> 8 anos	Fechado
> 4 e ≤ 8 anos	Semiaberto (se nao reincidente)
≤ 4 anos	Aberto (se nao reincidente)

Substituicao (art. 44 CP)

Pena ≤ 4 anos + crime sem violencia/grave ameaca + nao reincidente especifico → pode substituir por restritiva de direitos.

Sursis (art. 77 CP)

Pena ≤ 2 anos + nao reincidente em crime doloso + circunstancias favoraveis → pode suspender.

Analise Visual

Timeline de Movimentacoes

Crie um artifact HTML interativo com as movimentacoes em ordem cronologica, usando cores por tipo:

Vermelho: prisoes, mandados, restricoes de liberdade
Laranja: denuncias, aditamentos, acusacoes
Verde: concessoes de liberdade, absolvicoes, extincoes de punibilidade
Azul: audiencias, despachos, pericias
Amarelo: intimacoes, citacoes, prazos

Dashboard do Processo Criminal

Crie um artifact React com Recharts contendo:

Card com dados principais (acusado, tipificacao, vara, situacao — preso/solto)
Timeline resumida das fases processuais
Indicadores de status (fase atual, prazos proximos, alertas de excesso)
Tabela de tipificacao com pena cominada

Fluxograma do Rito

Use Mermaid para mostrar o fluxo do rito penal aplicavel, destacando a fase atual.

Referencias

Para detalhes completos sobre ritos, prazos e modelos de decisao, consulte:

references/ritos-penais.md — Todos os ritos do CPP com fases, prazos e pontos de decisao
references/modelos-decisoes-penais.md — Templates de despachos, decisoes e sentencas penais

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 v5 — 10/7/2026

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

br/criminal/skills/analise-processo-penal/SKILL.md

View on GitHub ↗

License MITImported 10/7/2026Version v1Bundled 2 files

Illustrative Want to see what thomasmoreai/analise-processo-penal 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

Assessor Judicial — Processo Penal

Ferramentas Disponiveis

Descobrir o processo

Mapear e ler documentos

Buscar e analisar

Visuais do Claude

Principio de Economia

Workflow Principal

Passo 1 — Visao geral do processo

Passo 2 — Identificar o rito e o status do reu

Passo 3 — Mapear documentos, partes e movimentacoes

Passo 4 — Ler as pecas essenciais

Passo 5 — Busca textual focada

Passo 6 — Leitura integral quando necessario

Passo 7 — Buscar jurisprudencia

Passo 8 — Fundamentar e redigir

Regras de Ouro

Identificacao do Rito

Atencao Especial — Reu Preso

Prazos com reu preso (referencia)

Dosimetria da Pena (sentencas condenatorias)

1a Fase — Pena-base (art. 59 CP)

2a Fase — Agravantes e atenuantes

3a Fase — Causas de aumento e diminuicao

Regime inicial (art. 33 CP)

Substituicao (art. 44 CP)

Sursis (art. 77 CP)

Analise Visual

Timeline de Movimentacoes

Dashboard do Processo Criminal

Fluxograma do Rito

Referencias

SkillSafety

Source

Related skills

More in the registry