Ready to supercharge your AI agents?

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

gtrk-ref-reading · 参考片精读 · gitruck | DecimalAI

Design & Mediaby gitruck

gtrk-ref-reading · 参考片精读

参考片精读——把一条别人的视频读成「可复刻」的整片模型与时码细节：逐字时码转写 + 带台词标签的抽帧网格 + 关键动效逐帧看 + 按「系统」记录每个设计事件对着哪句话，落成 ANALYSIS.md / TIMELINE.md / PROGRESS.md，读完可交给 /gtrk-style-maker 产栏目 skill，或直接指导把这套包装迁移到用户自己的片子上。驱动 `gtrk transcript --json`（取字级时码）与纯本地零计费的 `gtrk media` 看片命令族。当用户想「拆解这条视频 / 精读参考片 / 学一下这个博主的包装 / 分析这条视频的风格 / 这条视频的动画是怎么做的 / 照着这条参考片的风格做 / 把 XX 的风格蒸馏出来 / 参考片逆向」时使用本 skill。凡要从一条参考视频里学包装与节奏，先用本 skill 读透再动手，别看几张截图就开始仿。

Never made a case worseMaintained

SkillScore

SkillScore96/100

Test results 96

Safety

3/3 safety checks passed

Code scan
Intent
Content

What it changes

16%96%of test cases passed +80 pts

Without skill4 of 25

With skill24 of 25

20 fixed4 passed either way1 still failing0 broke

Measured on gemini-3.8-flash11/2/2026v1

Track record

Agent runs: 0; All time

See one task, with and without the skill

One test task我们需要从视频第 12.5 秒和第 45.0 秒处提取标题文字的精准 RGB 色值和字体字重细节。为了避免网格缩放导致模糊失真，应该运行哪条命令？

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 gitruck-gtrk-ref-reading
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("gitruck-gtrk-ref-reading")
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 gitruck-gtrk-ref-reading

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/gitruck-gtrk-ref-reading/SKILL.md https://app.decimal.ai/s/gitruck-gtrk-ref-reading/SKILL.md

Copy SKILL.md

Save it in your project, as

.claude/skills/gitruck-gtrk-ref-reading/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 gitruck-gtrk-ref-reading

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("gitruck-gtrk-ref-reading")
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/gitruck-gtrk-ref-reading/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/gitruck-gtrk-ref-reading/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 gitruck-gtrk-ref-reading

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("gitruck-gtrk-ref-reading")
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/gitruck-gtrk-ref-reading/SKILL.md

Give it to your agent

from pathlib import Path
from agents import Agent, Runner

skill = Path(".agents/skills/gitruck-gtrk-ref-reading/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 gitruck-gtrk-ref-reading

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("gitruck-gtrk-ref-reading")
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/gitruck-gtrk-ref-reading/SKILL.md

Give it to your agent

from pathlib import Path
from openai import OpenAI

client = OpenAI()
skill = Path(".agents/skills/gitruck-gtrk-ref-reading/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 gitruck-gtrk-ref-reading

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("gitruck-gtrk-ref-reading")
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/gitruck-gtrk-ref-reading/SKILL.md

Give it to your agent

from pathlib import Path
import anthropic

client = anthropic.Anthropic()
skill = Path(".agents/skills/gitruck-gtrk-ref-reading/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 gitruck-gtrk-ref-reading

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("gitruck-gtrk-ref-reading")
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/gitruck-gtrk-ref-reading/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/gitruck-gtrk-ref-reading/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 gitruck-gtrk-ref-reading

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("gitruck-gtrk-ref-reading")
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/gitruck-gtrk-ref-reading/SKILL.md

Give it to your agent

from pathlib import Path
from langchain.agents import create_agent

skill = Path(".agents/skills/gitruck-gtrk-ref-reading/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 gitruck-gtrk-ref-reading

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("gitruck-gtrk-ref-reading")
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/gitruck-gtrk-ref-reading/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 gitruck-gtrk-ref-reading

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("gitruck-gtrk-ref-reading")
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/gitruck-gtrk-ref-reading/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/gitruck-gtrk-ref-reading/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 gitruck-gtrk-ref-reading

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("gitruck-gtrk-ref-reading")
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/gitruck-gtrk-ref-reading/SKILL.md

Give it to your agent

from pathlib import Path
from pydantic_ai import Agent

skill = Path(".agents/skills/gitruck-gtrk-ref-reading/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 gitruck-gtrk-ref-reading

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("gitruck-gtrk-ref-reading")
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/gitruck-gtrk-ref-reading/SKILL.md

Give it to your agent

from pathlib import Path
from deepagents import create_deep_agent

skill = Path(".agents/skills/gitruck-gtrk-ref-reading/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 gitruck-gtrk-ref-reading

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("gitruck-gtrk-ref-reading")
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/gitruck-gtrk-ref-reading/SKILL.md

Give it to your agent

import asyncio
from pathlib import Path
from agent_framework import Agent

skill = Path(".agents/skills/gitruck-gtrk-ref-reading/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 gitruck-gtrk-ref-reading

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("gitruck-gtrk-ref-reading")
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/gitruck-gtrk-ref-reading/SKILL.md

Give it to your agent

from pathlib import Path
from strands import Agent

skill = Path(".agents/skills/gitruck-gtrk-ref-reading/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 gitruck-gtrk-ref-reading

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/gitruck-gtrk-ref-reading/SKILL.md https://app.decimal.ai/s/gitruck-gtrk-ref-reading/SKILL.md

Copy SKILL.md

Save it in your project, as

.agents/skills/gitruck-gtrk-ref-reading/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/gitruck-gtrk-ref-reading/SKILL.md

Read the summary as JSON

curl -fsSL https://app.decimal.ai/s/gitruck-gtrk-ref-reading.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 11/2/2026
Source: gitruck/cli ↗
License: MIT

Manage it in DecimalAI

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

Use this skill

SKILL.md

gtrk-ref-reading · 参考片精读

你是读片的人。目标不是「描述这条片子」，而是产出一份能指导复刻的理解：这片想让观众得到什么、靠哪些视觉 / 声音系统做到、每个系统在哪句话上做了什么、换成用户的人 / 产品 / 画幅 / 语言时，哪些作用要保留、哪些形式要重做。

这个 skill 不做什么 → 找谁

不产栏目 skill、不写栏目配置 → 读完交 /gtrk-style-maker（精读结论作为「作品逆向」的证据，见文末）。
不剪片、不铺轨、不出 MG 颗粒 → 成片管线（/gtrk-talking-head、/gtrk-splitter、/gtrk-mg 与栏目 MG skill）。
不下载链接：只读用户本地的视频文件。给的是链接 / 平台 ID 时，请用户先自行合法取得、放到本地。

硬边界

产物落点纪律（MUST · 全文见随包 AGENT.md 同名一节）：精读产物（ANALYSIS / TIMELINE / PROGRESS / 转写稿 / evidence 下的网格与片段）只落精读目录（缺省 <参考片同目录>/<参考片名>-精读/，用户指定优先）。交付物 MUST NOT 先写 agent 自有目录再拷进工程；中转本身即违规，体积不是豁免理由。引用参考片用原路径，不复制原片；gtrk media 的中间物由命令自己放系统 temp、用完即删。

计费只有转写一处：gtrk transcript --json 走云端字级 ASR，按官网实时价格计费——跑之前告诉用户这一步要花钱、大约多少（以 CLI 打出的实时提示为准）。gtrk media 全部纯本地、零计费、不联网。
用户须有权使用这条参考片做学习分析。证据图只在精读目录里供判读，原片的帧与片段 MUST NOT 进栏目 skill 的 assets、MUST NOT 混进成片。
转写稿 MUST 是这条参考片自己的：标签和 --around 都假设转写稿与视频同一条时钟。gtrk media 发现时长 / 文件名对不上会告警——见到告警先查，别带着错时钟读下去。

铁律（读片方法，贯穿全程）

整片与细节来回修正。 先通读形成暂定解释，再逐系统精读；细节推翻整片理解时，回去改 ANALYSIS。只做其中一头都读不准。
让时间可见，不靠代表帧。 口播类参考片先取字级时码；网格一律带 --transcript；关键动效逐帧看。几张截图说不清一个东西何时进、怎么变、驻多久、何时走。
按「系统」记，不按镜头记。 跨镜头存在的物件（一块板、一个圆窗、一套字幕）在 ANALYSIS 里记一次，再在 TIMELINE 里按时间记它的状态变化（出现 / 高亮 / 灰化 / 合并 / 换形态 / 退场）。镜头边界只用来导航。
每个设计事件都写「对着哪句话」。 原句引文 + 源片秒，再写它为观众做了什么（落一个数、答一个问题、给判断盖章、让位给下一个论点）。迁移时按这句话的作用重绑到目标稿，MUST NOT 照抄秒数。
迁移时保留作用、重做形式。 换人 / 换产品 / 换画幅 / 换语言时，问「这个系统在这里干什么」，再为目标设计能干同一件事的形式。目标上不成立的作用（没有真实数据却要画数据图）就明确不做，MUST NOT 编内容去填形式。
文件是记忆。 发现一条写一条：整片模型进 ANALYSIS，时码细节进 TIMELINE，当前问题 / 未看的段落 / 下一步进 PROGRESS。换会话的人只读这三份文件就能接着读。
事实与解读分开写。 「看到的」是画面 / 网格 / 转写稿上能指出的东西；「它在做什么」是你的解读。没看清的标「待查」并记下时码，回到源片换个尺度再看，MUST NOT 凭印象补写。
采样之间有空隙。 概览网格会漏掉短事件，相邻两格看着没变不等于中间没发生事。追一个系统时把密度加到能看清它的进 / 变 / 驻 / 出为止。
动效的名字只是起点。 「弹出」「推近」不够复刻：要看路径、缩放 / 透明度变化、几帧到位、有没有过冲和回落、到位后是静止还是慢漂、和邻近事件谁先谁后。一个物件的「淡出副本」可能就是它自己在退场——逐帧看清再下结论。
边读边说。 每读完一段，用一两句话 + 一张代表网格告诉用户你发现了什么、它对迁移意味着什么；细节留在文件里。用户的口味与背景信息能改变读法，别闷头读完才开口。

工序

0 · 立案

确认四件事并写进 PROGRESS.md 第一版：参考片路径（可多条，定一条主读、其余交叉印证）；用户要学什么（整体包装 / 某个系统 / 节奏）；目标是什么（套到谁的什么片上：换人？换产品？换画幅？换语言？）；精读目录在哪。

1 · 取证底座

gtrk media probe "<参考片>"                                     # 时长 / 尺寸 / 帧率 / 有无音轨
gtrk transcript "<参考片>" --json --out "<精读目录>/transcript.md" # 计费：先告知用户
gtrk media lines "<精读目录>/transcript.json"                     # 逐句：u<id> 起–止 文本
gtrk media boundaries "<参考片>" --rate 4 --threshold 0.12 \
  --transcript "<精读目录>/transcript.json" -o "<精读目录>/evidence/boundaries.json"

--out 指到精读目录里的 transcript.md，字级时码稿就落在同目录的 transcript.json（gtrk media --transcript 吃它）。Markdown 里待补的「总结」可以不补——ANALYSIS 就是这条片子的总结。
无口播的参考片（纯音乐 / 纯画面）跳过转写，用画面变化与动作定位。
boundaries 给的是视觉变化候选（机械证据，不是镜头判定）；它的平均间隔就是「多久一变」，候选附的句号告诉你换板发生在哪句话上。

2 · 通读整片

读完整的转写全文，再看整片概览网格：

gtrk media tiles "<参考片>" --frames 48 --cols 6 --rows 4 --cell 320 \
  --transcript "<精读目录>/transcript.json" -o "<精读目录>/evidence/overview"

写 ANALYSIS 的「这片想让观众得到什么」「整片结构与节奏」（分段表：段 / 时码 / 看到的 / 它在做什么）。长片分段读，但始终保持对整片走向的把握。

3 · 认出系统

从概览与变化点里找反复出现、跨镜头存在的东西：讲者机位、画中画、实体图标 / 徽章、数字、标题牌、字幕、章节标识、B-roll、梗图、转场、声音标点…… 每个系统在 ANALYSIS 记一次：看到的（形态、位置、配色、字体气质）/ 它在做什么 / 状态集合 / 首次出现时码。用参考片自己的样子命名（S1 书柜机位、S4 逐字落板……），别套别人的分类表。

4 · 逐系统精读

对每个系统挑 2–3 处最典型的出现，按尺度切换：

要回答的问题	命令
这段话和画面怎么一一对上	`gtrk media tiles "<参考片>" --around "<台词>" --padding 1 --every 0.5 --cols 4 --rows 3 --transcript <稿> -o evidence/<名>`
一个元素几帧到位、之后怎么动	`gtrk media tiles "<参考片>" --around "<台词>" --padding 0.3 --every-frame --cols 6 --rows 4 --cell 360 --transcript <稿> -o evidence/motion/<名>`
字体、配色、间距、层级	`gtrk media frames "<参考片>" --at <秒,秒> -o evidence/<名>`（缺省源分辨率，看清再写色值与字重）
一次看好几段	`gtrk media tiles "<参考片>" --ranges <ranges.json> --transcript <稿> -o evidence/<名>`（`[{id, around}` 或 `{id, start, end}]`）
台词出现在哪 / 重复几次	`gtrk media lines <稿> --find "<台词>"`，再用 `--occurrence <n>` 选
留一段动态证据	`gtrk media cut "<参考片>" --around "<台词>" --occurrence <n> -o evidence/<名>.mp4`

每读清一处，就在 TIMELINE 写一节（格式见 references/landing-templates.md）。逐帧看动效时照 references/close-reading-checklist.md 过一遍。

读网格：每格画面下方三行——①源片秒 · 时码（逐帧模式加帧号）· 句号；②此刻正在读的字与字级起止；③所在整句（当前字高亮）。「此刻无字在读」「句间空隙」只说明这一刻没有字级时码覆盖，不等于静音。网格是证据，结论由你写，并在 TIMELINE 里写上证据路径。

5 · 回头修正整片模型

细节改变了理解（发现两个「不同物件」其实是同一物件的两个状态、某个转场其实是章节标点），就回去改 ANALYSIS。补齐「色彩与字体」（从大图取近似色值，写清用途）与「动效性格」（快进慢驻？状态变化多于出场？切走不清板？）。

6 · 给每个系统判归属：叠层还是版式

逐个系统问一句：「它改不改变讲者在画面里的位置、大小或可见区域？」

不改变 → 叠层：叠在既有画面上、讲者原样不动（字卡、角标、大数字、印章、标签……）。迁移时归 MG 生产 skill（produces: "MG"）。
改变 → 版式：讲者被缩放、裁切、挪位或让位（人像圆窗、图版与讲者同屏、对照并排、整幅标题版式、逐句换画面……）。迁移时归合成风格 skill（produces: "composite"，由 /gtrk-composite 消费）。

判据看讲者，不看元素大小：整幅替换掉讲者的标题版属版式（讲者的可见区域变成零）；一枚很小的人像圆窗也属版式（讲者被缩放、裁切）；压在讲者画面上的大号字卡仍属叠层（讲者原样在场）。在 ANALYSIS 每个系统下加一行「归属：叠层 / 版式」并写一句理由（看了哪张网格判的）。拿不准的系统去逐帧网格里看讲者那一格的变化，别凭印象定。两类不能混进同一个栏目 skill——把「图版 + 讲者圆窗」做成 MG 的结果，是整幅底板挖洞露脸，讲者其实没被缩放，形式对不上作用。怎么登记进栏目配置以 /gtrk-style-maker 第⑥招「家族切分」为准，本 skill 只负责判归属、给证据。

7 · 迁移表

ANALYSIS 末节按系统写一张表：归属（叠层 / 版式）/ 保留什么作用 / 在目标上形式怎么重做 / 不做什么及理由。目标的变化逐项过：换人（这个角色在所有出现处都要换，不只是脸）、换产品（产品的真实卖点、道具、界面、证据、CTA）、换语言（字幕分组与节奏跟着新语言走）、换画幅（横转竖时哪些系统要重新构图、哪些要拆）、增删系统（删掉的系统原来干的活交给谁）、多参考片（每个作用来自哪条，冲突怎么取舍）。

8 · 交付与交棒

跟用户讲清：整片模型一句话、最关键的 3–5 个系统（各附一张证据网格路径）、迁移要点、仍待查的问题。然后按用户的去向交棒：

要沉淀成自己栏目的风格体系 / 栏目 skill → /gtrk-style-maker（见下节）。
栏目 skill 已就绪、要直接做片 → 回成片管线，按 TIMELINE 里「对着哪句话」的关系在目标稿上重新落点。
只是学习 / 评估 → 精读目录本身就是交付物。

交给 /gtrk-style-maker 时

精读结论是证据，不是用户的维度。/gtrk-style-maker 的「作品逆向」会拿 ANALYSIS 里的系统逐个出示证据网格问用户：「这个像你吗？哪里不像？你会怎么叫它？」——用户认领的才进栏目 skill，命名用用户的话；用户否掉的记成禁令候选。所以交棒时给它：精读目录路径、系统清单（每条附一张最能说明问题的网格和归属：叠层 / 版式）、迁移表。不要替用户把系统清单直接写成栏目 skill。 归属决定用户认领的系统最后进 MG 生产 skill 还是合成风格 skill；两类分开登记的做法见 /gtrk-style-maker 第⑥招。

TIMELINE 里的典型段落可以成为栏目 skill 的判例（「这句话该落一个大数字，因为……」），但判例里放的是我们按其作用重做的成品，不是原片截图。

交付前自检

口播参考片有字级转写；所有引用的网格都带了 --transcript？
ANALYSIS 每个系统都写了「看到的 / 它在做什么 / 状态集合」，且是一次记录、不按镜头重复？
每个系统都按「改不改变讲者的位置、大小或可见区域」判了归属（叠层 / 版式）并写了依据；没有把版式类系统归成叠层？
TIMELINE 每节都有：源片秒区间 + 段落意义、原句引文、发生了什么、为观众做了什么、证据路径（文件真实存在）？
至少一个关键动效做过逐帧（写得出几帧到位、之后怎么动）？
事实与解读分开；没看清的标了「待查」与时码？
迁移表逐系统写了保留作用 / 重做形式 / 不做及理由；没有为填形式编造内容？
PROGRESS 写清当前问题、未看的段落 / 系统、下一步？
产物全在精读目录；没复制原片；原片帧没有流进栏目 skill 或成片？

About this skill

Automatic

Marketing & Content pack

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v8 — 10/26/2026

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

gitruck / cli

skills/gtrk-ref-reading/SKILL.md

View on GitHub ↗

License MITImported 10/26/2026Version v1Bundled 2 files

Illustrative Want to see what gitruck/gtrk-ref-reading 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

gtrk-ref-reading · 参考片精读

这个 skill 不做什么 → 找谁

硬边界

铁律（读片方法，贯穿全程）

工序

0 · 立案

1 · 取证底座

2 · 通读整片

3 · 认出系统

4 · 逐系统精读

5 · 回头修正整片模型

6 · 给每个系统判归属：叠层还是版式

7 · 迁移表

8 · 交付与交棒

交给 /gtrk-style-maker 时

交付前自检

SkillSafety

Source

Related skills

More in the registry