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 skills/cdeistopened/skill-stack/skill-extractornpx skills add cdeistopened/skill-stack --skill skill-extractorgit clone --depth 1 https://github.com/cdeistopened/skill-stackWhat 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 | $0.00067 | $0.01642 |
| Opus 5 | $0.00034 | $0.00821 |
| Sonnet 5 | $0.00013 | $0.00328 |
| Haiku 4.5 | $0.00007 | $0.00164 |
Grade A, and why
skill-extractor 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 2d 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 — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Extractor
Turn raw source material into a list of buildable Claude Code skills. Not a knowledge base — skills are workflows Claude can execute, not facts Claude should know.
The Core Distinction
Skill = a repeatable workflow with inputs, steps, and outputs that Claude executes inside a coding environment. Writing a YouTube script. Running an SEO audit. Drafting a newsletter. Creating ad copy.
Not a skill = static knowledge, reference material, domain expertise. How to raise meat birds. The history of fasting. Nutritional science. These become wiki articles, books, or reference docs — not skills.
The test: Can Claude do this thing, repeatedly, with different inputs, and produce a useful output? If yes → skill. If it's something Claude knows and references → not a skill.
Skill Taxonomy
Score each candidate against these six hallmarks. A strong skill exhibits 2+ of these.
1. Repeated SOP / Workflow
Something done regularly as part of a content or business process. The more often it's done, the higher the leverage.
Examples: Newsletter drafting, social post creation, podcast show notes, SEO content briefs, weekly reporting
2. Disposable One-Shot
Valuable but infrequent. Done once per project or client. Still worth codifying because it saves hours when needed — and becomes an agency offering if done for others.
Examples: Writing a LinkedIn bio, Amazon category research, brand identity creation, book launch checklist, landing page copy
3. Specific Knowledge Applied as Process
Domain expertise distilled into a repeatable method — not raw knowledge, but knowledge operationalized into steps Claude can follow.
Examples: Kallaway's "7 Lego Bricks" for short-form → YouTube scriptwriting skill. Dan Koe's "one-person business" model → content strategy skill. NOT "the history of short-form video" (that's reference).
4. Step-by-Step Process
A clear sequence where order matters. Often teachable, often already described as numbered steps in the source material.
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.
- 2d ago First seen · 178 lines · 67 tokens per session scan A fecec8a6ea9a
skill-extractor is a skill published in the GitHub repository cdeistopened/skill-stack (27 stars, last pushed 1mo ago), licensed MIT. It adds 67 tokens to every session and 1,642 once invoked, about $0.0003 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
article-writing
Write articles, guides, blog posts, tutorials, newsletter issues, and other long-form content in a distinctive voice derived from supplied examples or brand guidance. Use when the user wants polished written content longer than a paragraph, especially when voice consistency, structure, and credibility matter.
a-evolve
Apply A-Evolve's agentic evolution methodology to improve AI agent performance across runs. Use when the user wants to diagnose agent failures, generate targeted skills from error patterns, evolve system prompts, or accumulate episodic knowledge. Works standalone or inside AutoResearchClaw pipelines. Triggers on…
hive.chart-creation-foundations
Required reading whenever any chart tool is available. Teaches the one-tool embedding contract (call chartrender → live chart appears in chat AND a downloadable PNG lands in the queen session dir), the ECharts (data viz) vs Mermaid (structural diagrams) decision, the BI/financial-grade aesthetic baseline (no…
📝 任务完成后归档
重要提醒: 每次完成复杂调试或开发任务后，主动执行此流程！ 将学到的经验归档为 skill，供以后参考。不要等用户提醒。.
deck-course-module
暖纸背景 + Playfair, 左侧学习目标常驻, 含 MCQ 自测页.
code-documenter
Use when adding docstrings, creating API documentation, or building documentation sites. Invoke for OpenAPI/Swagger specs, JSDoc, doc portals, tutorials, user guides.