Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add commands/samqin123/claude_skill_pool/extractgit clone --depth 1 https://github.com/samqin123/Claude_skill_poolWrote 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/commands/samqin123/claude_skill_pool/extract)<a href="https://agentmods.dev/commands/samqin123/claude_skill_pool/extract"><img src="https://agentmods.dev/badge/commands/samqin123/claude_skill_pool/extract.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00000 | $0.01669 |
| Opus 5 | $0.00000 | $0.00834 |
| Sonnet 5 | $0.00000 | $0.00334 |
| Haiku 4.5 | $0.00000 | $0.00167 |
Grade A, and why
extract 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 3d 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 — 215 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/extract - 研究方法论反向提取器
描述: 从已有的深度研究文档中抽象出可复用的研究框架模板，实现"研究思路模板化、未来场景复用化"
使用方法:
/extract [研究文档路径]
示例:
/extract 深度研究/Unifuncs.md
/extract 深度研究/MiroThinker.md
/extract 2026年核心资产投资研究报告.md
工作原理
当你执行 /extract 命令时，系统会：
-
读取并分析指定的研究文档
-
识别并提取六个核心维度的研究方法论框架：
- 宏观分析框架（历史对标、时代特征、关键时间点）
- 资产分类框架（分类逻辑、驱动因素、配置角色）
- 驱动逻辑验证框架（必要条件、转折信号）
- 三重验证体系（宏观+产业+财务）
- 风险预警框架（双向风险、动态调整）
- 专家观点整合框架（观点交叉验证）
-
生成并保存可复用的研究方法论模板到
research_frameworks/目录
输出结构
执行后会在项目根目录生成：
research_frameworks/
└── [提取时间]_[原研究主题]/
├── 00_研究方法论总览.md # 六维度框架概览
├── 01_宏观分析框架模板.md
├── 02_资产分类框架模板.md
├── 03_驱动逻辑验证框架模板.md
├── 04_三重验证体系模板.md
├── 05_风险预警框架模板.md
├── 06_专家观点整合框架模板.md
├── 07_研究工作流程.md
├── 08_Prompt模板库.md # Agent可直接使用的提示词
└── 09_使用指南.md
核心价值
不是提取结论，而是提取方法
❌ 错误理解：
- "提取2026年黄金的投资逻辑"
- "总结三硬资产的投资策略"
✅ 正确理解：
- "提取如何进行宏观对标的分析方法"
- "总结如何构建三重验证体系的研究框架"
实现跨场景复用
原场景: 2026年"三硬资产"投资策略研究
复用场景:
- 2027年"三硬资产"更新研究 → 直接套用框架，更新数据
- 2026年"软资产"研究 → 复用六维度结构，调整分类逻辑
- 其他宏观主题研究 → 复用分析范式，定制化内容
使用示例
示例1: 提取单个报告的方法论
/extract 深度研究/Unifuncs.md
系统会：
- 分析Unifuncs.md的研究逻辑
- 提取"三硬资产"分类方法论
- 提取"必要逻辑链"验证方法
- 生成8个框架模板文件
示例2: 对比提取多个报告
/extract 深度研究/Unifuncs.md,深度研究/MiroThinker.md
系统会：
- 分别分析两个报告
- 对比它们的研究方法论
- 提取共性框架和差异点
- 生成融合版方法论模板
示例3: 提取特定维度
/extract 深度研究/Unifuncs.md --dimensions=macro,verification
系统会：
- 只提取宏观分析框架（macro）
- 只提取三重验证体系（verification）
- 其他维度跳过
高级用法
生成Agent提示词模板
提取完成后，可以使用生成的 08_Prompt模板库.md 直接为Agent系统提供研究指令：
## 基于提取框架的Agent Prompt
你现在是一位深度研究分析师，请使用以下研究方法论框架：
### 宏观分析（参考01_宏观分析框架模板.md）
- 对标历史周期: [1970-80年代冷战]
- 时代特征判断: [全要素生产率停滞、逆全球化]
- 关键时间窗口: [每年1月初大宗再平衡]
### 资产分类（参考02_资产分类框架模板.md）
- 分类逻辑: [硬通货/硬科技/硬资源]
- 驱动因素: [每个类别的核心驱动力]
- 配置角色: [核心/卫星/对冲]
[... 其他维度]
请开始你的研究分析。
迭代现有框架
如果 research_frameworks/ 目录中已有框架，执行 /extract 时：
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.
- 3d ago First seen · 215 lines · 0 tokens per session scan A bf0dc6047fb9
extract is a command published in the GitHub repository samqin123/Claude_skill_pool (2 stars, last pushed 6mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,669 tokens. 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 2026-08-31.
Other commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.