Ready to supercharge your AI agents?

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

Manuscript Typeset · o0000-code | DecimalAI

Documentationby o0000-code

Manuscript Typeset

Typeset a finished academic Markdown manuscript into submission-ready and publication-preview outputs — WITHOUT altering any number, citation, or claim. Produces four artifacts: submission DOCX (pandoc + APA-7 reference-docx), submission PDF (LaTeX apa7 man: double-spaced, line-numbered, tables/figures end-placed), published-look preview PDF (apa7 jou two-column), and the clean Markdown. Fidelity is a hard script gate (exit 2, no --warn-only): every output is token-compared against its source an

SkillScore

SkillScore96/100

Test results 96

Safety

3/3 safety checks passed

Code scan
Intent
Content

What it changes

13%96%of test cases passed +83 pts

Without skill3 of 23

With skill22 of 23

19 fixed3 passed either way1 still failing0 broke

Measured on gemini-3.6-flash8/3/2026v121 comparable

Track record

Agent runs: 0; All time

See one task, with and without the skill

One test taskWhat exact extracted text stream is compared against the stripped source markdown during fidelity verification of a generated docx file?

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 o0000-code-manuscript-typeset
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("o0000-code-manuscript-typeset")
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 o0000-code-manuscript-typeset

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/o0000-code-manuscript-typeset/SKILL.md https://app.decimal.ai/s/o0000-code-manuscript-typeset/SKILL.md

Copy SKILL.md

Save it in your project, as

.claude/skills/o0000-code-manuscript-typeset/SKILL.md

This gets SKILL.md only. The skill's 15 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 o0000-code-manuscript-typeset

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("o0000-code-manuscript-typeset")
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/o0000-code-manuscript-typeset/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/o0000-code-manuscript-typeset/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 15 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 o0000-code-manuscript-typeset

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("o0000-code-manuscript-typeset")
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/o0000-code-manuscript-typeset/SKILL.md

Give it to your agent

from pathlib import Path
from agents import Agent, Runner

skill = Path(".agents/skills/o0000-code-manuscript-typeset/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 15 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 o0000-code-manuscript-typeset

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("o0000-code-manuscript-typeset")
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/o0000-code-manuscript-typeset/SKILL.md

Give it to your agent

from pathlib import Path
from openai import OpenAI

client = OpenAI()
skill = Path(".agents/skills/o0000-code-manuscript-typeset/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 15 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 o0000-code-manuscript-typeset

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("o0000-code-manuscript-typeset")
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/o0000-code-manuscript-typeset/SKILL.md

Give it to your agent

from pathlib import Path
import anthropic

client = anthropic.Anthropic()
skill = Path(".agents/skills/o0000-code-manuscript-typeset/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 15 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 o0000-code-manuscript-typeset

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("o0000-code-manuscript-typeset")
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/o0000-code-manuscript-typeset/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/o0000-code-manuscript-typeset/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 15 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 o0000-code-manuscript-typeset

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("o0000-code-manuscript-typeset")
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/o0000-code-manuscript-typeset/SKILL.md

Give it to your agent

from pathlib import Path
from langchain.agents import create_agent

skill = Path(".agents/skills/o0000-code-manuscript-typeset/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 15 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 o0000-code-manuscript-typeset

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("o0000-code-manuscript-typeset")
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/o0000-code-manuscript-typeset/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 15 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 o0000-code-manuscript-typeset

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("o0000-code-manuscript-typeset")
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/o0000-code-manuscript-typeset/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/o0000-code-manuscript-typeset/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 15 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 o0000-code-manuscript-typeset

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("o0000-code-manuscript-typeset")
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/o0000-code-manuscript-typeset/SKILL.md

Give it to your agent

from pathlib import Path
from pydantic_ai import Agent

skill = Path(".agents/skills/o0000-code-manuscript-typeset/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 15 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 o0000-code-manuscript-typeset

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("o0000-code-manuscript-typeset")
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/o0000-code-manuscript-typeset/SKILL.md

Give it to your agent

from pathlib import Path
from deepagents import create_deep_agent

skill = Path(".agents/skills/o0000-code-manuscript-typeset/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 15 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 o0000-code-manuscript-typeset

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("o0000-code-manuscript-typeset")
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/o0000-code-manuscript-typeset/SKILL.md

Give it to your agent

import asyncio
from pathlib import Path
from agent_framework import Agent

skill = Path(".agents/skills/o0000-code-manuscript-typeset/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 15 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 o0000-code-manuscript-typeset

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("o0000-code-manuscript-typeset")
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/o0000-code-manuscript-typeset/SKILL.md

Give it to your agent

from pathlib import Path
from strands import Agent

skill = Path(".agents/skills/o0000-code-manuscript-typeset/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 15 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 o0000-code-manuscript-typeset

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/o0000-code-manuscript-typeset/SKILL.md https://app.decimal.ai/s/o0000-code-manuscript-typeset/SKILL.md

Copy SKILL.md

Save it in your project, as

.agents/skills/o0000-code-manuscript-typeset/SKILL.md

This gets SKILL.md only. The skill's 15 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/o0000-code-manuscript-typeset/SKILL.md

Read the summary as JSON

curl -fsSL https://app.decimal.ai/s/o0000-code-manuscript-typeset.json

This gets SKILL.md only. The skill's 15 other files are not included.

Other ways to add it

Other setups docs

You don't need a DecimalAI account.

Version: v1, tested 8/3/2026
Source: o0000-code/meta-analysis-skill ↗
License: NOASSERTION

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

Manuscript Typeset

把一篇已定稿的学术 Markdown 手稿排成投稿版 / 发表预览版的通用排版 Skill。它不做内容写作——内容属别的 Skill；它做的是版式变换:md → 投稿 docx / 投稿 PDF / 发表预览 PDF / 干净 md 四件,附忠实性声明、占位符清单、剥离报告。上游任意写作 Skill(元分析 L12、系统综述、empirical-imrad-writing 等)成稿后产一份 typeset_request.yaml 调用它;也有独立触发场景("把这篇稿子排成投稿版")。

第一可执行入口:§4 输入契约(typeset_request.yaml)+ §9 CLI。完整字段 schema 见 references/MANUSCRIPT-INPUT-CONTRACT.md,CLI 权威汇总见 README.md。

1. 忠实性纪律 = 本 Skill 的灵魂(先读这一段)

排版层不得改动任何数字、引用或 claim——一个都不行。 这不是一句承诺,是一条脚本断言:每件产物落盘前必过 fidelity_check——源(strip 后的 md)与产物(去 LaTeX 宏的 tex / 去 XML 的 docx 文本)逐 token 比对,两条硬门(退出码 2,该件不落、整体阻断,无 --warn-only):①任何在产物里出现、源里没有的数 → fail——忠实渲染从不凭空造数(实测 EXTRA=0),故任何注入或改动(含纯整数计数:研究数、PRISMA 记录数、千分位样本量、表格单元格计数)必现形;②任何载荷性数字或 DOI 缺失 → fail——载荷=数据形数值(效应量/CI/p 值/%/τ²/权重)+ 标签绑定关系(k= / N= / p< …,含关系符,比较符翻转 p<.001→p>.001 也拦)+ DOI。诚实边界(唯一未硬拦的方向):仅"纯删除"一个格式层合法重排的裸整数(参考文献页码 / DOI 内嵌年份 / 引擎另渲的标题计数,源里有产物合法省略)呈报供复核、不硬拦——改动永远拦,只有这类裸整数的静默删除落复核(详见 references/FIDELITY-DISCIPLINE.md §2/§4c)。

排版是版式变换,不是内容再加工。凡涉及改动数字 / 引用 / claim 的"优化"(顺手改个措辞、"修正"一个看着不对的数、自动翻译一句),一律不属于本 Skill 的职责边界——那是上游写作/核验 Skill 的事。实战范式一句话:"No verified number, citation, or claim was altered." 本 Skill 把它从"靠 agent 自觉 + 一句声明"升级为机器强制门,这是相对实战的核心增量。

名值绑定边界(诚实,不假装覆盖):fidelity_check 的逐字比对天然覆盖"排版层改了正文的数"——改了必被抓。但它对'输入件本身名值已错'无能为力:若上游表格里 "Costa 的 0.77" 被错标成 "Abbott et al.",两侧看到的是同一份(错的)绑定,判等放行。这类"名字配错了数据"是版式检查与数字比对之外的第三类检查,超出排版层职责。凡交付物含 study 名↔数值绑定(表格 / 图注),BUILD_NOTES 明写此边界,建议上游 / 署名人抽查(见 references/TYPESET-BUILD-NOTES-PATTERN.md)。

2. 触发与适用场景

2.1 触发短语

英文:typeset manuscript、submission-ready manuscript、publication-ready、submission docx / PDF、APA 7 manuscript formatting、reference-docx、apa7 man/jou、camera-ready、strip internal traces。中文:把 md 学术稿排成投稿版 / 发表版、出投稿 docx / PDF、投稿排版、发表预览、学术排版、内部痕迹剥离、生成投稿 Word。

2.2 反向触发(不适用 / 切到其他 Skill)

用户场景	切到
写 / 改内容本身(Intro/Method/Results/Discussion 措辞)	对应写作 Skill(empirical-imrad-writing / meta-analysis L11 / systematic-review)
参考文献核验 / 修 DOI / APA 格式化	`academic-ref-check`(本 Skill 消费其核验产物,不代做核验)
forest / funnel / PRISMA / RoB 图渲染	`meta-analysis` 内置 ma-plots 渲染器 / `ssci-plots`
编号制期刊(Vancouver / AMA / NEJM 数字上标引用)	须 CSL 档——v2 延期,见 §5 边界
md 通用转 Word(非学术投稿规范)	`academic-paper-converter` 等通用转换 Skill

2.3 定位:成稿出口 + 独立入口

成稿出口(主用法):写作 Skill 完成 md 定稿(含 SP7 核验过的参考列表)后,产 typeset_request.yaml 调本 Skill。假设前提 = md 已定稿、引用已核验——本 Skill 不回头改内容。
独立入口:用户手上有一篇定稿 md("把这篇排成投稿版"),自行填 typeset_request.yaml(或让本 Skill 据 md YAML 头兜底元数据)即可跑。

3. 双引擎(各干各的,不强求单引擎)

产物	引擎	说明
投稿 docx	pandoc + reference-apa7.docx	APA 7 样式一次调校成 committed 资产;行号走 OOXML 后处理(stdlib,不依赖 python-docx)
投稿 PDF(apa7 man)	XeLaTeX + apa7 类	双倍行距 + 行号(`lineno`)+ 图表末置 + CJK 0 缺字
发表预览 PDF(apa7 jou)	XeLaTeX + apa7 类	双栏单倍行距 + `\leftheader` 适配 + 悬挂缩进 0.18in + 宽内容 `\onecolumn` 末置
generic PDF(兜底)	XeLaTeX + 通用 article	无 apa7 类依赖时的单栏投稿兜底

为什么不追求 pandoc 单引擎出 PDF:apa7 的 man/jou 细节——自动 title page、running head、行号、de-float 末置结构、CJK unicode-map 逐字符映射、jou 双栏适配(leftheader/hang/onecolumn/de-float GRADE 表)——pandoc 的默认模板做不到。实战已把 LaTeX 这条路验证到 0 error / 0 缺字 / 双 PDF 均成功编译,故双引擎各司其职:docx 只走 pandoc + reference-docx,PDF 只走 LaTeX。docx 的 CJK 与复杂表格能力弱于 LaTeX,BUILD_NOTES 诚实标注每件质量状态。

4. 输入契约(权威 = `typeset_request.yaml`;G9 据此接线)

上游产 typeset_request.yaml,声明:manuscript(正文 md)/ outputs(请求的输出子集)/ template_family(apa7 | generic)/ metadata(题录,md YAML 头兜底)/ references(默认档 = 保真渲染)/ tables(md: pandoc 或 raw_tex: 直通双形态)/ figures(末置,顺序即呈现序)/ strip_rules(可选)/ docx_line_numbers(可选)。

逐字段 schema、manuscript.md YAML 头约定、IMRaD 标题层级、metadata 覆盖规则,全文见 references/MANUSCRIPT-INPUT-CONTRACT.md(这是 G9 接线的权威)。最小可跑样例 = scripts/typeset_request.example.yaml(指向 scripts/tests/fixtures/smoke/ 的合成非元分析 IMRaD 稿,证通用性)。

4.1 四件输出 + 附件

请求的 outputs 子集,每件如 §3;此外每次必产三份附件:

BUILD_NOTES.md — 忠实性声明 + recompile 指令 + 每件质量状态(页数 / 缺字数 / overfull)+ 名值绑定边界诚实声明。模板见 references/TYPESET-BUILD-NOTES-PATTERN.md。
PLACEHOLDERS.md — 占位符清单(author / affiliation / funding / corresponding,PDF/docx 内清楚标记,待用户填)。
STRIP_REPORT.md — 剥离报告(剥了什么 / 留了什么 / 为什么——判断留痕)。

5. 引用:v1 只做默认档 + author-date 锁定边界

默认档(v1 唯一支持) = 上游 SP7 核验过的 md 参考列表 → 保真渲染:解析 md(## 组标题 分组,如 Cited / Included / Excluded,每条一段)→ hanging-indent tex(man 0.5in / jou 0.18in)。不引入 citeproc、不走 .bib。
理由(R5-A10,比蓝图更强):风险不在 citeproc 格式化本身(它不改数据),而在"SP7 核验过的 APA 文本 → .bib 结构化"这步无核验的再转换——避开它 = 保住 0 幻觉链。上游引用真值已在核验产物里,排版层无权再加工。
author-date 锁定边界(诚实):默认档只服务 author-date 制期刊(APA 系)。投编号制期刊(Vancouver / AMA)必须走 CSL 档,且此时引用文本要重新过一遍核验——CSL / .bib 通用引用档 = v2 账本 V6,显式延期(首个编号制投稿需求时启用)。
治本接口愿望(additive,不阻塞 v1):handoff 给 academic-ref-check 一条愿望——核验时同步产出 verified CSL-JSON 侧车(核验器本就查 CrossRef/OpenAlex,结构化数据在手,顺手落盘零成本)。此后 CSL 档 = 同一核验真值的第二渲染,双档从"保真 vs 灵活"两难变成"同一真值两渲染"。

6. 内部痕迹剥离(strip)

排版前对全部输入件(正文 + 参考 + 表格)按 strip_rules.yaml 剥离内部过程痕迹,产剥离报告。这是实战发现的新问题类别:

剥离:gate codes(SP7 §3c / SP7 open item)、内部 corpus ID(papersearchpro-1628,直接致 overfull hbox)、过程顶注(L11 integrated final draft)。
保留:方法学披露(Method 里的 SP1–SP7 sign-off gates 是有意的监督流程披露)——strip 规则精确到能区分,判断入剥离报告留痕。
安全断言:strip 只能删配置的痕迹模式,被删 span 不得含任何数字 / 引用 token(strip_traces 自查,违规 exit 2)。
注:样本痕迹常在参考文献与表格而非正文(SP7 §3c 在 References、papersearchpro-1628 在 Table 1 ID 列)——strip 范围 = 全部排版输入件,别只 grep 正文。

strip_rules 缺失 → 恒等复制 + 报告声明"未配置"(不阻塞)。规则 schema 见 references/STRIP-RULES-SPEC.md(Lane C)。

7. 退出码契约(全脚本统一)

码	含义
`0`	成功(请求输出全建 + fidelity 全绿)
`1`	输入 / 契约错(request 缺字段 / 文件缺失 / 硬依赖缺失且无降级)——硬 fail
`2`	fidelity 断言失败或 strip 安全违规(数字 / 引用 / claim 变动)——铁律,不设 `--warn-only`,必阻断,不落该件
`3`	空(无正文可排)

依赖降级(honest):缺 xelatex → 降级为 docx + md 两件(请求的 PDF 件标记 skipped,stderr WARN + BUILD_NOTES 声明,整体 exit 0);缺 pandoc → 连 docx 不能出 → exit 1。fidelity 失败永不降级(码 2 硬阻断)。详见 §8 + README。

8. 依赖诚实(与 G10 doctor 对齐)

用户 runtime 硬依赖:pandoc(docx 必需)、xelatex(TinyTeX,PDF 必需)、python3 + pyyaml。
不依赖 python-docx / lxml:reference-apa7.docx 是 committed 二进制资产;docx 行号注入用 stdlib zipfile+xml。make_reference_docx.py 用 python-docx 仅 dev-time(重生成资产时),用户不需要。
字体:Times New Roman(main)/ Songti SC 宋体(CJK)/ Heiti SC(CJK sans)——macOS 自带;缺字体探测 + 降级说明见 README + BUILD_NOTES。
探测:typeset.py 启动查 shutil.which('pandoc'/'xelatex'),据此决定是否降级(见 §7)。降级路径权威汇总见 README.md。

9. CLI 概览(权威签名见 README)

编排器 typeset.py 读 request → strip_traces(所有输入件)→ 对每个请求引擎跑 build_pdf / build_docx → 对每件产物跑 fidelity_check(source=stripped 输入,rendered=该产物) → 全绿才落该件;任一 fidelity fail(码 2)→ 该件不落 + 整体 exit 2 + 报告。产 BUILD_NOTES / PLACEHOLDERS / STRIP_REPORT。

四个底层脚本(build_pdf.py / build_docx.py / strip_traces.py / fidelity_check.py)+ 编排器 typeset.py 的完整 CLI 签名、参数、机读摘要 JSON、退出码,权威汇总见 README.md。

10. 边界与模板族(不过度工程)

模板族 v1 = apa7(man + jou)+ generic。APA 7 覆盖心理学 / 社科主战场,够第一版。
scripts/templates/<family>/ 只留空槽位(Elsevier / 双栏会刊等)——按真实需求再加 = v2,不预填。
不自动翻译:表本地化(如中文 GRADE 表 → 英文)= 上游提供已本地化版本,走 raw_tex: 直通,本 Skill 绝不自译(违忠实性)。
CSL / .bib 通用引用档、编号制期刊、非 APA 期刊族 = v2 延期(§5 / §10 V6)。

11. 文件组织

manuscript-typeset/
├── SKILL.md                              本文件:触发 / 忠实性纪律 / 输入契约 / 双引擎 / 边界
├── README.md                             CLI 签名权威 + 依赖探测 + 降级路径 + 目录导览
├── LICENSE                               dual: PolyForm-NC 1.0.0 (code) + CC BY-NC-SA 4.0 (docs)
├── references/
│   ├── MANUSCRIPT-INPUT-CONTRACT.md      输入契约全文(G9 接线权威)
│   ├── TYPESET-BUILD-NOTES-PATTERN.md    BUILD_NOTES / 占位符 / 忠实性声明 / 名值边界 模板
│   ├── FIDELITY-DISCIPLINE.md            铁律 + 断言覆盖边界(Lane C)
│   └── STRIP-RULES-SPEC.md               strip_rules schema + 剥离报告格式(Lane C)
└── scripts/
    ├── typeset.py                        编排器(读 request → strip → 引擎 → fidelity gate → 四件+附件)
    ├── build_pdf.py / build_docx.py      PDF / docx 引擎
    ├── strip_traces.py / fidelity_check.py   剥离 + 忠实性门
    ├── typeset_request.example.yaml      最小可跑样例(指向合成非 MA 稿)
    ├── assets/tex/                        preamble-common / unicode-map / apa7-man/jou/generic 模板
    ├── assets/docx/reference-apa7.docx    APA7 样式 reference-docx(committed 资产)
    ├── templates/<family>/                v2 期刊族槽位(空)
    └── tests/                             各引擎回归 + fixtures/smoke 非 MA 冒烟稿

About this skill

Automatic

Doc Ops pack

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/1/2026

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

o0000-code / meta-analysis-skill

skills/manuscript-typeset/SKILL.md

View on GitHub ↗

License PolyForm-Noncommercial-1.0.0 AND CC-BY-NC-SA-4.0Imported 8/1/2026Version v1Bundled 15 files · scripts

Illustrative Want to see what o0000-code/manuscript-typeset 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

Manuscript Typeset

1. 忠实性纪律 = 本 Skill 的灵魂(先读这一段)

2. 触发与适用场景

2.1 触发短语

2.2 反向触发(不适用 / 切到其他 Skill)

2.3 定位:成稿出口 + 独立入口

3. 双引擎(各干各的,不强求单引擎)

4. 输入契约(权威 = typeset_request.yaml;G9 据此接线)

4.1 四件输出 + 附件

5. 引用:v1 只做默认档 + author-date 锁定边界

6. 内部痕迹剥离(strip)

7. 退出码契约(全脚本统一)

8. 依赖诚实(与 G10 doctor 对齐)

9. CLI 概览(权威签名见 README)

10. 边界与模板族(不过度工程)

11. 文件组织

SkillSafety

Source

Related skills

More in the registry

4. 输入契约(权威 = `typeset_request.yaml`;G9 据此接线)