skills
AGENTS.md0 starsChanged 36 days agoMITView on GitHub
This repository is a curated registry of agent skills — reusable expertise modules that can be loaded by AI agents (e.g., via SWAL, Codex, Claude Code, or any agent framework that supports skill injection). Each skill lives in skills/<category>/<skill-name>/ and is defined by a SKILL.md file with YAML frontmatter. Reference a skill by its id (declared in frontmatter). Example: You can also load all skills within a category: Each skill exposes a raw_url pointing to its SKILL.md on GitHub (raw).…
Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.
Of the AGENTS.md files we read, the 31,700 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
In this repository225 other files it gives its agents.
- agent-issue-delegationSkill
- jules-recovery-protocolSkill
- cavemanSkill
- bug-triageSkill
- issue-triageSkill
- brand-guardianSkill
- claude-design-principlesSkill
- swal-theme-creatorSkill
- ui-designerSkill
- ux-researcherSkill
- visual-storytellerSkill
- whimsy-injectorSkill
- background-transfer-monitorSkill
- cpanel-node-opsSkill
- cron-fleet-maintenanceSkill
- hermes-gateway-troubleshootingSkill
- kanban-orchestratorSkill
- kanban-workerSkill
- linux-performance-profilesSkill
- rclone-cloud-backupSkill
- rclone-drive-backupSkill
- shared-hosting-node-opsSkill
- subagent-output-truncationSkill
- swal-grep-alias-rgSkill
- swal-network-launchSkill
- ai-engineerSkill
- backend-architectSkill
- devops-automatorSkill
- frontend-developerSkill
- gestalt-orchestrationSkill
- gitcore-swal-workflowSkill
- mobile-app-builderSkill
- prototypeSkill
- rapid-prototyperSkill
- tddSkill
- test-writer-fixerSkill
- astroSkill
- NextJSSkill
- Tailwind CSSSkill
- frontend-agentSkill
- Frontend DoctorSkill
- agentic-e2eSkill
- agents-sdkSkill
- agy-customizationsSkill
- antigravity_guideSkill
- bateria-de-testingSkill
- browser-automationSkill
- camera-photo-backupSkill
- cargo-wizardSkill
- cloudflare-billing-guardSkill
- cloudflare-one-migrationsSkill
- cloudflare-oneSkill
- codificacion-ciclosSkill
- cole-medin-workflowSkill
- hexagonal-architecture-layers-javaSkill
- critical-change-evaluatorSkill
- cron-automation-managerSkill
- design-md-creatorSkill
- desktop-computer-useSkill
- discord-server-ctrlSkill
- The first 60 shown.
The file
We split this AGENTS.md into the rules it gives an agent
3 rules. About 0 are common, 0 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 125
Create a folder: skills/<category>/<skill-name>/
- Very specific: line 126
Add SKILL.md with valid YAML frontmatter and markdown body.
- Very specific: line 128
Run python3 scripts/manifest-generator.py to regenerate the manifest.
≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
AGENTS.md — Agent Briefing for iberi22/skills
Overview
This repository is a curated registry of agent skills — reusable expertise modules that can be loaded by AI agents (e.g., via SWAL, Codex, Claude Code, or any agent framework that supports skill injection).
Each skill lives in skills/<category>/<skill-name>/ and is defined by a SKILL.md file with YAML frontmatter.
How to Use These Skills
1. Load by ID
Reference a skill by its id (declared in frontmatter). Example:
skills:
- id: nextjs
- id: python
- id: content-creator2. Load by Category
You can also load all skills within a category:
skills:
- category: marketing3. Raw URL Access
Each skill exposes a raw_url pointing to its SKILL.md on GitHub (raw). This is useful for dynamic loading at runtime:
https://raw.githubusercontent.com/iberi22/skills/main/skills/<category>/<skill-name>/SKILL.md4. Manifest
The canonical registry is at _registry/manifest.yaml. It contains metadata for all skills: id, name, description, category, tags, path, raw_url, authors, etc. Parse this to discover available skills programmatically.
Format Conventions (v2)
All SKILL.md files follow the v2 format:
---
id: unique-skill-id
name: Display Name
category: category-name
tags:
- tag1
- tag2
goals:
- "One-line description of what this skill enables."
- "Another goal or context."
authors:
- Author Name
---
# Content
Markdown body with system prompt, instructions, examples, and constraints.Required Frontmatter Fields
| Field | Type | Description |
id | string | Unique kebab-case identifier |
name | string | Human-readable name |
category | string | Top-level category folder name |
tags | string[] | Searchable tags |
goals | string[] | What the skill enables (1–3 items ideal) |
Optional Frontmatter Fields
| Field | Type | Description |
version | string | Semantic version |
description | string | Short description (auto-extracted if missing) |
authors | string[] | Attribution |
license | string | License identifier |
original_source | string | Upstream URL if ported |
context | string | When/where to apply this skill |
Category Taxonomy
| Category | Description | Count |
ai | AI/ML tooling, fine-tuning, inference | — |
communication | Writing, messaging, tone, translation | — |
debugging | Bug triage, root-cause analysis, diagnostics | — |
design | UI/UX, visual storytelling, brand, whimsy | — |
devops | Deployment, infrastructure, CI/CD | — |
education | Learning content, exam generation, validation | — |
engineering-principles | Architecture, code quality, principles | — |
engineering-workflow | TDD, prototyping, rapid iteration, testing | — |
framework | Next.js, Astro, Vite, Tailwind CSS, etc. | — |
frontend | Frontend-specific agents and patterns | — |
language | Language-specific guidelines (Python, Rust, etc.) | — |
marketing | Content, growth, social media, ASO | — |
operations | Analytics, finance, legal, support | — |
product | Research, feedback, prioritization | — |
project-management | Sprints, shipping, studio coordination | — |
testing | QA, benchmarking, workflow optimization | — |
tools | CLI tools, agent wrappers, MCP integrations | — |
web | Web design guidelines, accessibility, performance | — |
Note: Category counts are auto-generated in
_registry/manifest.yaml.
Contributing
Adding a New Skill
- Create a folder:
skills/<category>/<skill-name>/ - Add
SKILL.mdwith valid YAML frontmatter and markdown body. - Optionally add companion files (e.g.,
setup.md,examples/). - Run
python3 scripts/manifest-generator.pyto regenerate the manifest. - Open a Pull Request.
PR Checklist
SKILL.mdfrontmatter is valid YAML (run a YAML linter).idis unique across the entire registry.categorymatches an existing folder or is added to taxonomy.goalsare concise and actionable.- No sensitive data (API keys, passwords, internal URLs) in content.
CI / Lint
Pull requests are validated by GitHub Actions:
- YAML lint — all
SKILL.mdfrontmatters must parse cleanly. - ID uniqueness — no duplicate skill IDs.
- Manifest freshness —
manifest.yamlmust be up to date (or themanifestworkflow will auto-commit it after merge).
Automation
| Workflow | Trigger | Purpose |
manifest.yml | Push to skills/** | Regenerates _registry/manifest.yaml and commits it. |
skill-watchdog.yml | Weekly (cron) + manual dispatch | Monitors upstream repos for new skills and opens issues. |
Questions?
Open an issue or reach out via the repo discussions.
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
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.

