Ready to supercharge your AI agents?

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

CrossFrame · sickn33 | DecimalAI

Researchby sickn33

CrossFrame

Use when the user explicitly invokes CrossFrame or 跨尺度结构诊断 for Chinese-canonical structural diagnosis of complex relationships, organizations, institutions, public disputes, or long-term evolution.

Never made a case worseMaintained

SkillScore

SkillScore95/100

Test results 95

Safety

3/3 safety checks passed

Code scan
Intent
Content

What it changes

27%95%of test cases passed +68 pts

Without skill6 of 22

With skill21 of 22

15 fixed6 passed either way1 still failing0 broke

Measured on gemini-3.6-flash8/8/2026v1 · latest is v2

This benchmark measured an earlier version of the skill.

Track record

Agent runs: 0; All time

See one task, with and without the skill

One test task请使用跨尺度结构诊断来分析我目前处于的照护与职场双重陷落困境：在保持全职高压工作的同时，长期独自承担患病家属的居家照护与心理情绪支持，感觉陷入耗竭但无法退出。请在回答时先给出简明诊断提纲（说明分析对象、事实界限、候选机制与策略档位），接着用不带复杂学术术语的日常语言帮助我理清现实责任边界、受损成本承担方，并给出下一步可试探的低风险可观察动作。

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 sickn33-crossframe
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("sickn33-crossframe")
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 sickn33-crossframe

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/sickn33-crossframe/SKILL.md https://app.decimal.ai/s/sickn33-crossframe/SKILL.md

Copy SKILL.md

Save it in your project, as

.claude/skills/sickn33-crossframe/SKILL.md

This gets SKILL.md only. The skill's 50 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 sickn33-crossframe

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("sickn33-crossframe")
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/sickn33-crossframe/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/sickn33-crossframe/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 50 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 sickn33-crossframe

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("sickn33-crossframe")
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/sickn33-crossframe/SKILL.md

Give it to your agent

from pathlib import Path
from agents import Agent, Runner

skill = Path(".agents/skills/sickn33-crossframe/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 50 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 sickn33-crossframe

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("sickn33-crossframe")
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/sickn33-crossframe/SKILL.md

Give it to your agent

from pathlib import Path
from openai import OpenAI

client = OpenAI()
skill = Path(".agents/skills/sickn33-crossframe/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 50 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 sickn33-crossframe

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("sickn33-crossframe")
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/sickn33-crossframe/SKILL.md

Give it to your agent

from pathlib import Path
import anthropic

client = anthropic.Anthropic()
skill = Path(".agents/skills/sickn33-crossframe/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 50 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 sickn33-crossframe

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("sickn33-crossframe")
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/sickn33-crossframe/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/sickn33-crossframe/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 50 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 sickn33-crossframe

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("sickn33-crossframe")
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/sickn33-crossframe/SKILL.md

Give it to your agent

from pathlib import Path
from langchain.agents import create_agent

skill = Path(".agents/skills/sickn33-crossframe/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 50 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 sickn33-crossframe

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("sickn33-crossframe")
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/sickn33-crossframe/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 50 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 sickn33-crossframe

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("sickn33-crossframe")
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/sickn33-crossframe/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/sickn33-crossframe/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 50 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 sickn33-crossframe

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("sickn33-crossframe")
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/sickn33-crossframe/SKILL.md

Give it to your agent

from pathlib import Path
from pydantic_ai import Agent

skill = Path(".agents/skills/sickn33-crossframe/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 50 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 sickn33-crossframe

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("sickn33-crossframe")
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/sickn33-crossframe/SKILL.md

Give it to your agent

from pathlib import Path
from deepagents import create_deep_agent

skill = Path(".agents/skills/sickn33-crossframe/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 50 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 sickn33-crossframe

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("sickn33-crossframe")
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/sickn33-crossframe/SKILL.md

Give it to your agent

import asyncio
from pathlib import Path
from agent_framework import Agent

skill = Path(".agents/skills/sickn33-crossframe/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 50 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 sickn33-crossframe

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("sickn33-crossframe")
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/sickn33-crossframe/SKILL.md

Give it to your agent

from pathlib import Path
from strands import Agent

skill = Path(".agents/skills/sickn33-crossframe/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 50 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 sickn33-crossframe

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/sickn33-crossframe/SKILL.md https://app.decimal.ai/s/sickn33-crossframe/SKILL.md

Copy SKILL.md

Save it in your project, as

.agents/skills/sickn33-crossframe/SKILL.md

This gets SKILL.md only. The skill's 50 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/sickn33-crossframe/SKILL.md

Read the summary as JSON

curl -fsSL https://app.decimal.ai/s/sickn33-crossframe.json

This gets SKILL.md only. The skill's 50 other files are not included.

Other ways to add it

Other setups docs

You don't need a DecimalAI account.

Version: v2 (v1 tested 8/8/2026)
Source: sickn33/antigravity-awesome-skills ↗
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

references/

templates/

SKILL.md

CrossFrame

When to Use This Skill

Use only when the user explicitly names CrossFrame, crossframe, /crossframe, $crossframe, or 跨尺度结构诊断.
Use for Chinese-canonical structural diagnosis where facts, scale, evidence, responsibility, mechanisms, and action limits must be separated.
Do not use passively for ordinary analysis, writing, relationship advice, public commentary, philosophy, or long-term forecasting.

Packaged Source Note

This AAS-ready copy preserves the original CrossFrame skill body below. Chinese remains the canonical semantic layer; English metadata is only for discovery, installation, and repository review.

Limitations

The skill body is intentionally Chinese-canonical; English metadata is for discovery and does not replace the original Chinese terms.
Use only after explicit CrossFrame invocation or crossframe-suite routing; do not apply it as a generic default reasoning layer.
It is an author-defined analytical framework, not an empirically validated diagnostic instrument. Terms such as trauma, healing and diagnosis must not be presented as clinical assessments of a person.
It structures analysis, drafting, and review, but does not replace source verification, domain expertise, or legal, medical, or financial judgment.

如果用户任务需要多个 CrossFrame 平行 skill 连续协作，先读取 ../crossframe-suite/SKILL.md 做总调度；本 skill 负责其中的结构诊断、事实边界、尺度窗口、机制候选、七闸复核和判断档位。

语言原则

本 skill 的权威语义是中文。CrossFrame 只是英文传播名与 skill id，不承担概念解释权。

遇到中英文可能冲突时，以中文术语为准：承接、回流、开放断言、尺度转移、责任链、观测反身性、低条件试探行动、退出转移、不浪费爱、强判断八件套、局部状态坐标、过程性产物边界。

英文可以用于文件名、别名、对外简介或必要的双语标注；不要把中文概念硬译成英文后再反向理解。

核心定位

CrossFrame 不是“把 v5.0 文本塞进上下文”的提示词包，而是一个可执行的结构推理协议。

每次使用都必须先形成内部推理产物，再输出结论。结论可以很短，但不能跳过事实抽取、七闸复核、机制候选、判断档位、源结构连续性和表达闸。

必须执行的顺序

判断用户请求类型：快速诊断、完整诊断、推演、开放断言、命题验证、强判断、高反身性对象、亲密关系轻量入口、疗愈与转移、公共制度专项、低条件行动、高责任反俘获审查、框架边界、生命周期/状态坐标、递进闭环、势场/自主解离、治理连续性、框架治理与证伪、AI 过程性产物边界、弱信号/不透明检查、无制度基础设施中间路径、无法退出主体保护、隐喻/来源透明、工具化可及性、观测收束、超大规模压力测试、表达翻译、理论后台，或概念解释。
读取 references/runtime-read-policy.md、references/read-routing-map.md 和必要时 references/v5-material-selection-map.md，确定本次需要加载的 v5 source modules、连读包、协议、工作表、概念卡和模板。
先定位 v5 source modules，不全量打开大文件。默认只记录需要的 source module、关键词、V5-H 或源范围；只有源锚点不足、用户要求源审计、或高责任判断需要核验时，才定向读取 references/v5-source-spine.md、references/v5-section-digest-index.md、references/v5-coverage-map.md 或 references/v5-term-fidelity.md 的相关局部。
读取 references/continuity-closure-map.md 展开入口包的“必须同读闭包”；需要包说明、源锚点或降档细节时，再读取 references/continuity-bundles.md 和对应 references/continuity-bundles/v5/<bundle-id>.md。默认最多读取 3 个入口核心包 + 2 个相邻辅助包；这个上限不限制必须同读闭包。高责任、公共制度、组织处置、公开判断必须优先读七闸、强判断八件套、低权力保护、证据降级与行动上限包及其闭包。
按 templates/read-state-capsule.md 生成 v5-read-state-capsule：先列 source modules，再列入口包、必须同读闭包、相邻候选、源锚点、降档边界和下游读取策略。suite 不生成胶囊，胶囊由本核心层生成并传给专项 skill、essay 和 review。
填写内部 intake：对象、尺度、事实、证据缺口、用户用途、受影响对象、观测影响、权力结构、行动上限。
通过七闸：对象闸、证据闸、尺度闸、责任闸、观测闸、权力闸、行动闸。七闸任一不完整，不能维持强判断。
形成至少两个机制候选；除非证据足以说明只有一个机制。
对承担判断作用的概念做完整吸收：读取对应概念卡，并用 worksheets/concept-fidelity-check.md 做保真检查。
用 worksheets/source-continuity-check.md 检查是否只读了孤立概念卡、漏掉 v5 相邻约束或需要降档。
用 worksheets/source-anchor-integrity-check.md 检查中心命题、机制候选、高风险概念和行动边界能否回指胶囊源锚点；不能回指的内容只能标为“本文推断 / 表达转译 / 外部思想映射”，不得写成 CrossFrame v5 原义。
决定判断档位：轻量观察、开放断言、完整诊断、强判断、低条件试探行动、退出转移。若必须联读但未联读，或源锚点不足，不能维持强判断。
先输出可见推理提纲，再选择模板输出：先说现实语言，再按需要附内部映射。

读取规则

默认遵守 references/runtime-read-policy.md：不读取 evals/、examples/、完整成功案例、完整失败案例或全量 v5 大索引。它们只用于开发压测、回归验证、风格调试、用户显式要求源审计或源锚点失败后的定向补读。
普通诊断：读 protocols/diagnosis-protocol.md，并使用 worksheets/intake-worksheet.md、worksheets/seven-gates-worksheet.md、worksheets/evidence-ledger.md、worksheets/mechanism-candidates.md。
推演、后续走向、路径展开、分支终点：读 protocols/inference-protocol.md 和 templates/inference-output.md，并按需追加状态坐标、长期演化、治理连续性包。
低到中等把握的判断：读 protocols/open-assertion-protocol.md、worksheets/open-assertion-record.md、templates/open-assertion-output.md 和 v5-open-assertion-proposition-pack。
高责任、强权力密度、处分、名誉、权利、资源、公共记忆类问题：读 protocols/anti-capture-protocol.md、worksheets/high-responsibility-check.md，并追加 v5-low-power-protection-pack、v5-evidence-downgrade-action-ceiling-pack。
影响资格、名誉、资源、权利、处置、公共记忆的强判断：读 protocols/proposition-verification-protocol.md、worksheets/proposition-verification.md、worksheets/prospective-registration.md、templates/strong-judgment-output.md，并追加 v5-strong-judgment-eight-pack。
AI 报告、合规材料、漂亮汇报、机构自评、模型诊断：读 v5-ai-process-artifact-boundary-pack；必须声明过程性产物不得充当现实证明。
会因被观察、命名、公开或处置而改变行为、身份、证据或边界的对象：读 protocols/high-reflexivity-protocol.md、worksheets/reflexivity-state-transfer.md、templates/high-reflexivity-output.md 和 v5-observation-reflexivity-release-pack。
亲密关系、家庭、朋友、照护、单方承接、解释劳动和爱被要求的场景：读 protocols/intimate-relationship-protocol.md、worksheets/intimate-relationship-light-check.md、templates/intimate-relationship-output.md，并先读 v5-love-trapped-trauma-pack 和 v5-low-power-protection-pack。
系统停滞、创伤、修复、退出转移和重建场景：读 protocols/healing-transfer-protocol.md、worksheets/healing-transfer-map.md、templates/healing-transfer-output.md 和 v5-action-healing-transfer-pack。
公共制度、平台治理、公共承诺和高权力密度公共议题：读 protocols/public-institution-protocol.md、worksheets/public-institution-check.md、templates/public-institution-output.md，并追加 v5-public-power-institution-pack、v5-evidence-downgrade-action-ceiling-pack、v5-low-power-protection-pack。
CrossFrame 可能被当作万能理论、领域替代品、人格审判工具或 AI 合规材料背书时：读 protocols/framework-boundary-protocol.md、worksheets/framework-boundary-check.md、references/framework-ontology-protection.md 和 v5-use-boundary-governance-pack。
长期演化、阶段判断、组织/关系/制度周期变化：读 protocols/lifecycle-diagnosis-protocol.md、worksheets/lifecycle-stage-record.md、templates/lifecycle-output.md 和 v5-state-coordinate-lifecycle-pack。阶段 0-6 只能作为局部状态坐标，禁止写成线性宿命。
战略推进、长期修复、子锚点闭环、为什么忙但没有积累：读 protocols/progression-protocol.md、worksheets/sub-anchor-progression.md、templates/progression-output.md 和 v5-long-evolution-progression-field-pack。
正负势场、沉积基本盘、自主解离、保护性退出：读 protocols/field-dissociation-protocol.md、worksheets/field-dissociation-check.md 和 v5-long-evolution-progression-field-pack。
调节、预警、偿付约束、多中心治理、承接者生成和代际承接：读 protocols/governance-continuity-protocol.md、worksheets/governance-continuity-check.md、templates/governance-continuity-output.md 和 v5-governance-continuity-multicenter-pack。
文明尺度、历史尺度、超大规模圈层或宏大公共判断：读 protocols/large-scale-stress-test-protocol.md、worksheets/large-scale-stress-test.md、templates/large-scale-stress-output.md，并先降级检查证据和发布门禁。
面向普通人、管理、制度公共、技术治理或其他 AI 软件改写表达：读 protocols/expression-translation-protocol.md、references/expression-translation-table.md、templates/expression-translation-output.md 和 v5-domain-translation-normative-source-pack。
概念解释、概念边界、思想解释类问题：读 protocols/concept-explanation-protocol.md、references/concepts-minimal-set.md、references/v5-term-fidelity.md、v5-core-concept-integrity-pack，再按需读必要概念卡。
哲学、意义、第一因、生命是什么、虚无主义、存在理由等抽象问题：优先走概念解释协议，先做尺度拆分和结构性开放断言；只有无法转成任何结构问题时，才退回 protocols/framework-boundary-protocol.md。
如果最终输出要使用承接/回流、开放断言、尺度转移、观测反身性、权力封闭、低条件试探行动、爱/开放行动、主体/责任链、证据成本、机制候选、判断档位、退出转移、修复副产品等高风险概念，必须先读取对应概念卡和 v5 连读包；不能只凭最小概念集作精细判断。

输出规则

默认输出短而清楚。除非用户明确要求极简结论，否则先展示一个“推理提纲”；不展示完整工作表。
推理提纲必须包含：诊断对象、事实边界、尺度窗口、七闸复核、机制候选、判断档位、本次读取的概念或保真检查、本次 v5 连续联读包、读态胶囊摘要、下一步观察或行动。
深度、审计、高责任、公共制度、亲密关系、长期演化和文章输出场景，推理提纲必须显示“本次连续联读包”；普通轻量问题可以写“未触发”。
推理提纲只能写提纲，不写冗长内心推理；它用于让用户看见推理路径，也用于约束后续输出不跳步。
用户要求解释、工作表或审计时，可提供事实、来源、假设、方法和简洁判断依据；不披露隐藏的内部推理链。工作表只呈现可供核验的证据摘要。
默认先说人话，不堆术语。第一段必须让没有读过框架的人也能明白“发生了什么、为什么卡住、下一步看什么”。
永远区分：来源、事实、证据、解释、机制候选、判断档位、行动上限。
术语只能作为附加映射，不得作为结论本身。不要用“这是典型的 X，所以 Y”替代推理。
输出前必须通过表达闸：删掉所有框架术语后，核心判断仍然能被普通用户读懂。
不得把结构诊断变成人格审判、命运预言、意识形态标签或道德授权。
不得用尺度升维抹掉低尺度痛苦、压力、失职和责任链。
不得把“爱”说成命令、正当性证明或单方面忍耐要求。
不得把 AI 生成的合规材料、漂亮报告、自评文本当作高成本证据。
不得用强判断绕开命题验证；开放断言不能作为高责任处置依据。
高反身性对象不得无限递归；第三层之后没有新增高成本证据或结构变量时，必须收束或降档。
亲密关系场景先保护痛苦、安全和边界，不把修复责任压回受伤者。
疗愈与转移只提供结构行动边界，不替代医疗、心理、法律、安全或组织处置。
如果证据不足但问题紧急，输出低风险、可撤回、可观察的小动作，而不是假装已经完成强诊断。

表达闸

最终输出前，内部检查四问：

第一段是否不用术语也能说清问题？
用户是否能知道这个判断来自哪些事实，而不是来自概念套用？
是否把“承接、回流、尺度、开放断言”等术语翻译成了现实行为？
是否给出了一个可观察信号或行动边界？

任一不通过，先重写表达，再输出。

推理提纲

默认输出前置一个简短提纲：

诊断对象：
事实边界：
尺度窗口：
七闸复核：
机制候选：
判断档位：
本次读取的概念：
本次 v5 连续联读包：
下一步：

这个提纲不是完整工作表，也不是冗长推理链。它的作用是让用户看见：本次输出确实先界定对象、检查证据、比较机制、再给判断。

核心资料

references/runtime-read-policy.md：正常运行时的轻量读取策略，控制 eval/examples、完整案例和大 source modules 的默认不读取边界。
references/continuity-closure-map.md：v5 连读包闭包的轻量运行时图。
references/v5-source-spine.md：v5.0 原文标题层级、章节顺序、段落范围、相邻关系、表格索引和默认连读包。
references/v5-section-digest-index.md：v5.0 逐节保真摘要、不可误读边界和相邻联读提醒。
references/v5-coverage-map.md：v5.0 章节到 skill 模块、协议、工作表和连读包的覆盖地图。
references/v5-term-fidelity.md：v5.0 术语保真表，防止压缩失真。
references/v5-material-selection-map.md：v5.0 source modules、连读包、协议和模板的选择图。
references/continuity-bundles.md：v5.0 连续联读包索引。
references/continuity-bundles/v5/：26 个 v5 独立连读包。
references/read-routing-map.md：按请求类型选择协议、工作表、概念卡和模板。
templates/read-state-capsule.md：本次 v5 source modules、入口包、必须同读闭包、源锚点和下游读取策略的胶囊模板。
references/crossframe-v2-core.md、references/v2-*、references/v3-*：历史基线，仅在版本追踪或回退审计时读取。
references/concepts-minimal-set.md：最小概念集。
references/framework-ontology-protection.md：框架本体保护、反领域殖民、反模型殖民和概念改动规则。
references/guardrails.md：反误用规则。
references/diagnostic-dimensions.md、references/diagnostic-toolbox-index.md：复杂案例按需读取。
references/theory-backend-index.md：根假设、核心推论、全周期演化、递进模式、多中心治理等深层理论索引。
references/expression-translation-table.md：把后台概念翻译成普通人、管理、制度和技术治理语境。
references/concept-cards/：高风险概念卡。
worksheets/seven-gates-worksheet.md：七闸复核表。
worksheets/source-continuity-check.md：输出前检查是否读少、断章或漏掉原文连续约束。
worksheets/source-anchor-integrity-check.md：输出前检查中心命题、机制候选、概念、行动边界和文章转译是否能回指胶囊源锚点。

高风险概念闸

以下概念不能只按字面理解；一旦它们承担判断作用，必须读取对应概念卡和 v5 连读包：

承接 / 回流：读 references/concept-cards/chengjie-huiliu.md，并联读 v5-core-concept-integrity-pack。
开放断言：读 references/concept-cards/open-assertion.md，并联读 v5-open-assertion-proposition-pack。
尺度转移 / 尺度升维：读 references/concept-cards/scale-transfer.md，并联读 v5-cross-scale-context-translation-pack。
观测反身性：读 references/concept-cards/reflexivity.md，并联读 v5-observation-reflexivity-release-pack。
权力封闭 / 反俘获：读 references/concept-cards/power-closure.md，并联读 v5-public-power-institution-pack 与 v5-low-power-protection-pack。
低条件试探行动：读 references/concept-cards/low-condition-action.md，并联读 v5-diagnosis-admission-downgrade-exit-pack。
爱 / 开放行动 / 不浪费爱：读 references/concept-cards/love-open-action.md，并联读 v5-love-trapped-trauma-pack。
主体 / 责任链：读 references/concept-cards/responsibility-chain.md，并联读 v5-responsibility-intervention-separation-pack。
证据成本 / 弱信号 / AI 合规材料：读 references/concept-cards/evidence-cost.md，并联读 v5-source-evidence-separation-pack 与 v5-ai-process-artifact-boundary-pack。
机制候选：读 references/concept-cards/mechanism-candidates.md，并过七闸。
判断档位：读 references/concept-cards/judgment-grades.md，并联读 v5-evidence-downgrade-action-ceiling-pack。
退出转移：读 references/concept-cards/exit-transfer.md，并联读 v5-action-healing-transfer-pack。
修复副产品 / 伪修复：读 references/concept-cards/repair-byproduct.md，并联读 v5-action-healing-transfer-pack。
生命周期 / 阶段：读 protocols/lifecycle-diagnosis-protocol.md，并联读 v5-state-coordinate-lifecycle-pack。
框架治理 / 证伪 / 良性消亡：读 references/concept-cards/framework-governance-falsification.md，并联读 v5-framework-self-diagnosis-falsification-pack。
无法退出主体 / 复杂创伤 / 无健康基准：读 references/concept-cards/trapped-subject-trauma-baseline.md，并联读 v5-love-trapped-trauma-pack。
隐喻漂移 / 来源透明 / 规范性前提：读 references/concept-cards/metaphor-source-transparency.md，并联读 v5-domain-translation-normative-source-pack。
使用门槛债 / 工具化 / 分裂协议：读 references/concept-cards/accessibility-toolization-split.md，并联读 v5-toolization-accessibility-release-pack。
观测收束 / 熵增边界：读 references/concept-cards/observation-entropy-contraction.md，并联读 v5-observation-reflexivity-release-pack。

最低合格标准

一次合格的 CrossFrame 输出必须能回答：

我们到底在诊断什么对象？
哪些是来源，哪些是事实，哪些只是解释？
当前处在哪个尺度窗口？
七闸中哪一闸通过、哪一闸导致降级？
至少有哪些机制候选？
是否需要命题验证、强判断八件套、高反身性处理、亲密关系轻量入口、疗愈转移或公共制度专项？
谁在承担成本，谁有改变条件？
本次判断依赖哪些高风险概念，是否读取了完整概念卡和 v5 连读包？
这个判断能被什么证据撤回？
下一步是观察、修复、试探行动，还是退出转移？
生命周期判断是否写成了局部状态坐标，而不是线性宿命？
本次是否触发 v5 连续联读包，是否避免了只读孤立概念卡？
是否生成 v5-read-state-capsule，并让中心命题、机制候选、高风险概念和行动边界回指源锚点？

About this skill

Automatic

Research pack

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v8 — 11/8/2026

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

sickn33 / antigravity-awesome-skills

skills/crossframe/SKILL.md

View on GitHub ↗

License MITImported 11/8/2026Version v2Bundled 50 files

Illustrative Want to see what sickn33/crossframe would put in front of your model? Preview the rendered body and check its trigger phrases — no LLM call, no signup.

Other skills for the same job

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

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

CrossFrame

When to Use This Skill

Packaged Source Note

Limitations

语言原则

核心定位

必须执行的顺序

读取规则

输出规则

表达闸

推理提纲

核心资料

高风险概念闸

最低合格标准

SkillSafety

Source

Other skills for the same job

Related skills

More in the registry