A curated, open-source skill library for agentic developer tools.

Give your coding agent reusable playbooks for planning, debugging, QA, security, docs, data work, browser automation, and shipping.

Open Skill Marketplace — search 258 skills, preview SKILL.md inline, explore the bundle graph, copy install commands.

---

Why This Exists

Most agents start every task from a blank prompt. Skills give them reusable operating procedures: when to ask for clarification, how to run a review, how to triage tests, how to handle PDFs, how to build a quick analysis, how to use browser QA, and how to ship safely.

awesome-agent-skill packages those workflows as portable SKILL.md files for modern coding agents.

Skill Marketplace

Live demo: charlieviettq.github.io/awesome-agent-skill

Feature	What you get
Task advisor	Describe your task, get skills + bundle + install command
Browse & filter	Domain, tier, risk, quality, bundle filters
Bundle graph	Interactive force graph of bundle → domain → skill
Skill preview	Read SKILL.md on the page without opening GitHub

Regenerate locally: python3 scripts/generate-catalog.py then serve catalog/.

What You Get

Area	Includes
Agent workflow	Specs, planning, TDD, incremental implementation, code review, verification
Agent systems	MCP, RAG, tool contracts, context-window management, agent evaluation
Browser QA	gstack-style browsing, QA, canary checks, benchmarks, screenshots
Reliability and security	CI gates, launch checklists, observability, API security, skill supply-chain audit
Data and content	Analysis, visualization, documents, spreadsheets, PDFs, presentations
Role playbooks	Engineering, research, product, operations, orchestration, language experts

Works With

Portable SKILL.md folders for agentic coding tools:

Tool	Install path	Notes
Cursor	.cursor/skills/	Source of truth in this repo
Claude Code	.claude/skills/	Generated from Cursor skills
Codex CLI	.claude/skills/ or project skills dir	Copy compatible skill folders
OpenCode	.opencode/skills/ or .cursor/skills/	Follow your client’s skill discovery path
Gemini CLI / other agents	Project skills directory	Same SKILL.md format; verify client docs

Copy only the domains you need. Reload the agent session after installing skills.

Compatibility Matrix

Tool	Install path	Reload required	Commands support
Cursor	.cursor/skills/	Reload window / new chat	Project rules optional
Claude Code	.claude/skills/	Restart session	Optional .claude/commands/
Codex CLI	project skills dir	Restart session	Follow client docs
OpenCode	.opencode/skills/ or .cursor/skills/	Restart session	Follow client docs
Gemini CLI	.gemini/commands/ + skills dir	Restart session	Optional .gemini/commands/

Skills remain the source of truth. Commands in .claude/commands/ and .gemini/commands/ are optional wrappers for validate/sync/install workflows.

Quickstart (3 steps)

1. Choose a bundle — browse the Skill Marketplace or ask the advisor:

git clone https://github.com/charlieviettq/awesome-agent-skill.git
cd awesome-agent-skill
python3 scripts/skillhub.py recommend "ship safely with tests and CI"

2. Install into your project (preview first with --dry-run):

python3 scripts/skillhub.py install-bundle ship-ready /path/to/project --format cursor --dry-run
python3 scripts/skillhub.py install-bundle ship-ready /path/to/project --format cursor

Or install the CLI package: pip install -e . then skillhub install-bundle starter . --format cursor.

3. Reload your agent (Cursor: reload window / new chat; Claude Code: restart session).

More install options

# Curated bundles (see registry/bundles.json)
bash scripts/install/install-bundle.sh starter /path/to/project --format both
bash scripts/install/install-bundle.sh agent-builder /path/to/project --format cursor

# Single domain or skill
bash scripts/install/install-domain.sh core-workflow /path/to/project --format cursor
bash scripts/install/install-skill.sh core-workflow/verify-before-done /path/to/project --format cursor

See docs/skillhub-cli.md and docs/comparison.md (how this differs from a plain awesome list).

Marketplace: python3 scripts/generate-catalog.py — deployed via GitHub Pages from catalog/.

Manual install (Cursor):

mkdir -p /path/to/project/.cursor/skills
rsync -a .cursor/skills/core-workflow/ /path/to/project/.cursor/skills/core-workflow/
rsync -a .cursor/skills/security-appsec/ /path/to/project/.cursor/skills/security-appsec/
rsync -a .cursor/skills/writing-docs/ /path/to/project/.cursor/skills/writing-docs/

Install Claude Code skills:

mkdir -p /path/to/project/.claude/skills
rsync -a .claude/skills/ /path/to/project/.claude/skills/

Reload your agent session after copying skills.

Optional Commands

Optional slash-command wrappers (skills remain source of truth):

Command	Claude Code	Gemini CLI
Validate skills	/validate-skills	validate-skills
Sync Claude output	/sync-skills	sync-skills
Install domain	/install-domain	copy from scripts/install/
Install bundle	/install-bundle	copy from scripts/install/

Copy .claude/commands/ or .gemini/commands/ into your project to enable.

Formats

Agent surface	Path	Status
Cursor	.cursor/skills/**/SKILL.md	Source of truth (nested paths, e.g. knowledge-work/data/analyze)
Claude Code	.claude/skills/<flat-name>/SKILL.md	Generated flat names via scripts/claude-skill-map.json

Claude uses flat directory names (analyze, va-data-scientist) mapped from nested Cursor paths. Cursor does not need flat copies at .cursor/skills/analyze/ — the full path is the skill id for install and agent discovery.

Cursor → Claude (normal workflow after editing .cursor/skills/):

python3 scripts/convert-to-claude.py --in-repo --force --write-map --prune-orphans

Claude → Cursor (recovery when you edited .claude/skills/ only):

python3 scripts/convert-to-cursor.py --in-repo --only-newer
python3 scripts/convert-to-claude.py --in-repo --force --write-map --prune-orphans

Check parity:

python3 scripts/audit-skill-parity.py
python3 scripts/validate-skills.py --parity

Skill Map

Full index: SKILL_INVENTORY.md

Repository Layout

.
├── .cursor/skills/      # Cursor skill format, source of truth
├── .claude/skills/      # Claude Code skill format, generated from Cursor skills
├── .claude/commands/    # Optional Claude slash commands
├── .gemini/commands/    # Optional Gemini command wrappers
├── scripts/             # Conversion, validation, install, metrics
├── docs/                # Contributor guides, distribution, release cadence
├── .github/workflows/   # Skill validation CI
└── SKILL_INVENTORY.md   # Human-readable skill index

Highlights

Folder	Good For
core-workflow/	Spec-first implementation, planning, TDD, verification, reviews
ai-agent-systems/	MCP servers, RAG systems, agent evals, tool schemas
gstack/	Browser QA, ship workflows, design review, scrape flows
voltagent/	Role-based subagent playbooks
security-appsec/	API security, secure design, skill supply-chain checks
reliability-ops/	CI gates, SLOs, launch readiness, postmortems
writing-docs/	PDF, DOCX, XLSX, PPTX, prose polish
visualization/	Charts, figures, infographics, data storytelling

Design Principles

• Portable: skills are plain folders with SKILL.md.
• Composable: copy one domain or the full pack.
• Public-safe: no secrets, customer data, or private org assumptions.
• Agent-first: written as workflows an agent can follow, not as static articles.
• Reviewable: skills stay small; long references belong in reference.md or examples.

Updating Skills

Edit the Cursor source:

$EDITOR .cursor/skills/core-workflow/spec-driven-development/SKILL.md

Regenerate Claude output (and prune stale nested copies under .claude/skills/):

python3 scripts/convert-to-claude.py --in-repo --force --write-map --prune-orphans

Run validation:

python3 scripts/validate-skills.py --parity

Generate metrics snapshot:

python3 scripts/repo-metrics.py

Private Skills

Keep team-specific or sensitive skills in your own repository under paths such as .cursor/skills/private/ and .claude/skills/private/. This public pack is intentionally generic.

Contributing

Contributions welcome. See .github/CONTRIBUTING.md, docs/skill-writing-guide.md, and docs/review-rubric.md.

• Propose a skill: New skill issue
• Report outdated content: Outdated skill issue
• Track awesome-list submission: Distribution issue
• Good first issues: docs/good-first-issues.md

Recent changes: CHANGELOG.md | Release cadence: docs/RELEASE_CADENCE.md

Submit to Awesome Lists

If you maintain an awesome-list or agent-tools roundup, consider linking this repo under categories such as AI agents, Cursor, Claude Code, MCP, or developer tools. Suggested blurb:

awesome-agent-skill — 170+ portable agent skills (planning, QA, security, MCP, browser automation, data/docs) for Cursor and Claude Code.

External catalogs we track: EXTERNAL_SKILLS.md | Submission tracker: docs/distribution.md

License

MIT. See LICENSE. Use it, fork it, and adapt it for your own agents.