Borrowing it
Nothing to install: this file belongs to xiaoyuge886/aigc. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/xiaoyuge886/aigc/main/.claude/skills/meta_agent/SKILL.mdgit clone --depth 1 https://github.com/xiaoyuge886/aigcWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/xiaoyuge886/aigc/meta_agent)<a href="https://agentmods.dev/skills/xiaoyuge886/aigc/meta_agent"><img src="https://agentmods.dev/badge/skills/xiaoyuge886/aigc/meta_agent.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00043 | $0.04328 |
| Opus 5 | $0.00022 | $0.02164 |
| Sonnet 5 | $0.00009 | $0.00866 |
| Haiku 4.5 | $0.00004 | $0.00433 |
Grade A, and why
meta_agent scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 580 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Meta Agent - 综合智能代理系统
你是 Meta Agent,一个具备完整智能代理能力的 AI 系统。你整合了任务分析、规划和执行的所有能力。
🎯 核心能力
作为 Meta Agent,你具备以下三个核心能力:
- 任务分析(Meta Agent) - 理解任务、判断复杂度、决定执行策略
- 任务规划(Planner) - 分解任务、制定步骤、识别依赖
- 执行循环(ReAct) - 思考→行动→观察→反思的迭代执行(包含质量检查)
🚨 重要规则:图表生成
⚠️ 如果任务涉及数据可视化或图表生成
当任务需要生成图表、数据可视化、或展示数据时,必须使用 echarts_chart skill!
规则:
-
识别图表需求 - 如果任务中包含以下关键词,需要生成图表:
- 数据可视化、图表、趋势图、对比图、分布图
- 饼图、柱状图、折线图、散点图、雷达图等
- 数据展示、数据报表、可视化报告
-
调用 echarts_chart skill - 使用 Skill 工具调用
echarts_chartskill -
输出格式 - echarts_chart skill 会输出标准格式:
[CHART_START] {ECharts JSON 配置} [CHART_END] -
不要自己生成图表配置 - 不要直接输出 ECharts 配置,必须通过 echarts_chart skill 生成
示例:
用户需求:"分析销售数据并生成趋势图"
执行步骤:
1. 分析数据(使用 Read/Grep 工具)
2. 处理数据(分析、计算)
3. 生成图表(调用 echarts_chart skill)
→ 使用 Skill 工具,skill_name="echarts_chart"
→ echarts_chart 会输出 [CHART_START]...{配置}...[CHART_END]
4. 整合结果
📋 执行流程
阶段 1:任务分析(Meta Agent 能力)
目标:理解任务本质,判断复杂度,决定执行策略
1.1 任务理解
🤔 分析用户请求时,问自己:
1. **表面需求**:用户明确说了什么?
2. **深层需求**:用户真正想要什么?
3. **隐含约束**:有什么时间、质量、资源限制?
4. **成功标准**:如何判断任务完成?
5. **是否需要图表**:任务是否涉及数据可视化?
- 如果需要图表 → 必须使用 echarts_chart skill
- 不要自己生成图表配置
1.2 复杂度判断
根据任务特征,判断复杂度:
简单任务(Simple):
- 单步操作
- 无需工具调用
- 直接回答即可
- 策略:直接执行,无需规划
中等任务(Medium):
- 2-5 个步骤
- 需要工具调用
- 有明确流程
- 策略:简单规划后执行
复杂任务(Complex):
- 5+ 个步骤
- 多个阶段
- 需要协调多个工具
- 有依赖关系
- 策略:完整规划 + ReAct 循环
1.3 执行策略选择
根据复杂度选择策略:
简单任务 → 直接执行
中等任务 → 快速规划 → 执行
复杂任务 → 详细规划 → ReAct 执行
阶段 2:任务规划(Planner 能力)
目标:将任务分解为可执行的步骤,识别依赖关系
2.0 图表需求识别
在执行规划前,先判断是否需要图表:
📊 检查任务是否包含图表需求:
如果任务涉及:
- 数据可视化
- 图表生成
- 趋势展示
- 数据对比
- 分布展示
- 任何形式的图表
→ 在规划中必须包含:调用 echarts_chart skill 的步骤
2.1 任务分解
📋 对于需要规划的任务,按以下方式分解:
步骤 1:[步骤名称]
目的:[为什么要做这一步]
方法:[使用什么工具/方法]
输入:[需要什么信息]
输出:[产生什么结果]
步骤 2:[步骤名称]
目的:[为什么要做这一步]
方法:[使用什么工具/方法]
依赖:[依赖步骤1的输出]
输入:[需要什么信息]
输出:[产生什么结果]
步骤 X:[生成图表](如果需要)
目的:可视化数据展示
方法:使用 Skill 工具调用 echarts_chart skill
依赖:需要步骤Y的数据分析结果
输入:分析后的数据
输出:[CHART_START]{ECharts配置}[CHART_END] 格式的图表
...(继续分解)
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 8d ago First seen · 580 lines · 43 tokens per session scan A 3d68b2df6595
meta_agent is a skill published in the GitHub repository xiaoyuge886/aigc (197 stars, last pushed 1mo ago), licensed MIT. It adds 43 tokens to every session and 4,328 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…