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 skills add gmh5225/awesome-skills --skill claude-codegit clone --depth 1 https://github.com/gmh5225/awesome-skillsWrote 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/gmh5225/awesome-skills/claude-code)<a href="https://agentmods.dev/skills/gmh5225/awesome-skills/claude-code"><img src="https://agentmods.dev/badge/skills/gmh5225/awesome-skills/claude-code/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/gmh5225/awesome-skills/claude-code"><img src="https://agentmods.dev/badge/skills/gmh5225/awesome-skills/claude-code.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00032 | $0.00531 |
| Opus 5.5 | $0.00013 | $0.00212 |
| Sonnet 5.5 | $0.00006 | $0.00106 |
| Haiku 4.5 | $0.00003 | $0.00053 |
Grade B, and why
claude-code-skills scanned grade B with 1 finding 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 1mo 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.
Enumerates other installed skillsmediumAgent snooping
Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.
ls ~/.claude/skills/ How it starts
The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Code Skills
Scope
Use this skill when:
- Installing skills for Claude Code
- Developing Claude Code specific skills
- Understanding Claude Code skill discovery
Installation Paths
- Project scope:
.claude/skills/in project root - User scope:
~/.claude/skills/
Claude Code auto-discovers skills from these directories.
Installing Skills
From GitHub Repository
# Clone to project
git clone https://github.com/user/skill-repo .claude/skills/skill-name
# Or clone to user directory
git clone https://github.com/user/skill-repo ~/.claude/skills/skill-name
Manual Installation
- Create skill folder in
.claude/skills/ - Add
SKILL.mdwith frontmatter - Restart Claude Code to pick up new skills
Verifying Installation
# List installed skills
ls ~/.claude/skills/
# Check skill metadata
head ~/.claude/skills/skill-name/SKILL.md
Using Skills
Skills activate automatically based on your request context. You can also:
- Mention skill name explicitly in your prompt
- Use
/initto bootstrap context for a repository
Official Skills Repository
Key Official Skills
| Skill | Purpose |
|---|---|
| docx | Word document manipulation |
| xlsx | Excel spreadsheet operations |
| pptx | PowerPoint presentations |
| PDF extraction and creation | |
| webapp-testing | Playwright-based web testing |
| mcp-builder | Create MCP servers |
| skill-creator | Interactive skill creation |
Claude Code Commands
/init- Initialize project context- Skills auto-load when relevant to your task
Best Practices
- Keep skills focused on specific tasks
- Use progressive disclosure for large reference files
- Include scripts for automation
- Test skills in isolated environments first
Full Resource List
For more detailed Claude Code skill resources, complete link lists, or the latest information, use WebFetch to retrieve the full README.md:
https://raw.githubusercontent.com/gmh5225/awesome-skills/refs/heads/main/README.md
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.
- 1mo ago First seen · 95 lines · 32 tokens per session scan B 91c91e74f8da
claude-code-skills is a skill published in the GitHub repository gmh5225/awesome-skills (97 stars, last pushed 4d ago), licensed MIT. It adds 32 tokens to every session and 531 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it B with 1 finding (enumerates other installed skills). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
api-to-example
Turns REST API documentation into a runnable curl, fetch, or code example with required headers, request body, and placeholders for secrets. Use when the user wants to generate a request from API docs, an endpoint, or a Swagger/OpenAPI spec — "give me a curl for this", "show a fetch example", "how do I call this API".
code-translator
Converts a code snippet from one programming language to another while preserving behavior and flagging library, runtime, and type-system differences. Use when the user asks to translate, port, rewrite, or convert code between languages — "port this to Python", "rewrite in Rust", "convert Java to Go".
libretranslate-markdown-i18n
Machine-translate Markdown / Obsidian / Quartz content into other languages using a self-hosted LibreTranslate instance, preserving frontmatter, headings, emojis, bold/italic, wikilinks (![[...]]/[[...]]) and internal links. Use whenever a user wants to auto-translate a Markdown vault, Obsidian notes, or a…
animated-portfolio-sites
Build a one-page animated personal or portfolio site (canvas starfield, rotating galaxies with mouse parallax, hidden accordion/card content, anchor nav) and publish it free on GitHub Pages. Covers the canvas technique and the Pages permission wall, not just one task.
deal-checker
Judges whether a product's price is worth it by checking typical prices, alternatives, total cost, and timing, then giving a clear buy / wait / skip call. Use when the user asks "is this a good deal", "should I buy this", "is this worth the price", "too expensive", or wants a price check or comparison before…
job-fit-review
Reviews a job posting or pasted job description for fit, gaps, legitimacy signals, compensation context, resume customization, and interview prep. Use when the user shares a job posting, job listing, job ad, or job description and wants help deciding whether to apply, evaluating the role, or checking if a job is legit.