agentleFS
aixisstudioaixisstudio/claude-skills/llms.txt

claude-skills

llms.txt1 starsChanged 6 days agoMITView on GitHub

Skills are folders with a SKILL.md file that teach an AI agent how to do a specific task — loadable context, not code. Anthropic's format: a YAML front matter (name, description) plus instructions, scripts, and resources the agent reads on demand. This repo is a curated collection of ready-to-use skills + a guide to writing your own.

Files
llms.txt
# claude-skills
> Agent Skills for Claude — SKILL.md files that teach AI agents real abilities
Maintained by aixisstudio. Related: Snitch. https://github.com/aixisstudio/claude-skills

## 🧩 What are Agent Skills?

**Skills are folders with a `SKILL.md` file** that teach an AI agent how to do a specific task — loadable context, not code. Anthropic's format: a YAML front matter (`name`, `description`) plus instructions, scripts, and resources the agent reads on demand.

This repo is a curated collection of ready-to-use skills + a guide to writing your own.

## 📚 Skill categories

### 📄 Document skills
| Skill | What it does |
|---|---|
| `docx` | Create/edit Word documents with tracked changes |
| `pdf` | Extract, split, merge, fill PDF forms |
| `pptx` | Build slide decks from outlines |
| `xlsx` | Spreadsheets with formulas, charts, pivots |

### 🛠️ Dev skills
| Skill | What it does |
|---|---|
| `webapp-testing` | Drive a browser, verify UI states |
| `mcp-builder` | Scaffold new MCP servers |
| `skill-creator` | Meta-skill: write new skills |
| `git-commit-helper` | Conventional commits, PR descriptions |

### 🎨 Creative skills
| Skill | What it does |
|---|---|
| `canvas-design` | Visual design specs → assets |
| `video-script` | Storyboard + script formatting |
| `brand-voice` | Enforce a style guide on drafts |

## 🧪 Anatomy of a SKILL.md

```markdown
---
name: pdf-form-filler
description: Fill PDF form fields. Use when the user provides a PDF with empty form fields.
---

# PDF Form Filler

## Instructions
1. Run `scripts/extract_fields.py form.pdf` to list fields
2. Ask the user for values of any ambiguous field
3. Fill with `scripts/fill_fields.py`

## Resources
- `scripts/` — helper scripts (deterministic, no LLM needed)
- `reference/field-types.m

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.