Install expert workflows for AI coding agents

July 23, 2026 · View on GitHub

Agent Skills

License: MIT PRs Welcome Latest Release GitHub Stars

Install expert workflows for AI coding agents

One command drops a tested, versioned skill into your agent. No more ad-hoc prompts. The same rigorous steps run every time.

Skills are independent files. Works with Claude Code, Cursor, Windsurf, GitHub Copilot, OpenAI Codex, OpenCode.

Browse catalog | Install


Install

Validate this runbook: ./scripts/validate-install.sh --check

Pick one:

npx skills add https://github.com/luongnv89/skills --skill code-review

Pick several:

npx skills add https://github.com/luongnv89/skills --skill code-review --skill auto-push --skill test-coverage

All of them:

npx skills add https://github.com/luongnv89/skills

agent-skill-manager

Use agent-skill-manager (asm) for a single TUI/CLI across agents:

npm install -g agent-skill-manager
asm install github:luongnv89/skills
asm search   # find by name or description
asm list     # show installed skills
Other install methods

Remote (no clone)

curl -sSL https://raw.githubusercontent.com/luongnv89/skills/main/remote-install.sh | bash

Non-interactive:

curl -sSL https://raw.githubusercontent.com/luongnv89/skills/main/remote-install.sh | bash -s -- \
  --skills "code-review,auto-push" --tools "Claude Code" --scope global

Clone + local

git clone https://github.com/luongnv89/skills.git
cd skills && bash install.sh

How It Works

graph TD
    A[User request or trigger phrase] --> B[Agent matches skill name]
    B --> C[Loads SKILL.md + references/]
    C --> D[Follows exact steps + templates]
    D --> E[Quality gates + artifacts]
    E --> F[Report / plan / files / PR links]

A skill is a self-contained playbook: frontmatter metadata, instructions, optional scripts, and reference docs. The installer copies it to the right path for your agent.


Key Features

FeatureWhat you get
StandaloneAny mix installs cleanly; zero shared runtime
VersionedSemver + per-skill changelogs
StructuredSteps, templates, checklists, self-validation
Tool-agnosticSame skill works in Claude Code, Cursor, Windsurf, Codex, Copilot
ScannableTables, diagrams, short outputs
Suite supportMulti-phase products (e.g. website-cloner) with independent phases

Quick Start

npx skills add https://github.com/luongnv89/skills --skill landing-page-generator
npx skills add https://github.com/luongnv89/skills --skill code-review --skill auto-push

After install, call skills by name in your agent prompts (see catalog for each skill's trigger guidance).

See skills/ for full SKILL.md files.


Skill Catalog

Every skill is standalone. Install one or many.

Use:

npx skills add https://github.com/luongnv89/skills --skill <name>

Find by Category

CategoryWhat it covers
Code QualityReviews, cleanup, testing, optimization, usability
ShippingAuto push, pipelines, releases, security hardening
Product PlanningValidation, PRDs, architecture, tasks, naming
Frontend & DesignUIs, logos, diagrams, site clones
DocumentationDocs gen, READMEs, SEO, OSS prep, agent config
App StoreASO, review compliance
ToolingCLIs, installers, local models, agent comms

Code Quality

SkillVersionEffortWhat it does
code-review2.1.0highReview or improve code — 4 modes: bugs/security, performance, clean-code audit, slop cleanup
test-coverage1.3.0lowTarget untested branches and edge cases
dont-make-me-think1.3.2mediumUsability review using Krug's principles

code-review has four modes — pick by intent or pass mode:<name>:

I want to...ModeIt...
Find bugs, security, or quality issues in a diffreview (default)reads + reports prioritized findings
Make code faster / fix perf bottlenecksperfreads + reports performance fixes
Audit readability/standards vs the Clean Code cheat sheetcleanwrites an audit report (CLEAN_CODE_AUDIT.md)
Actually apply cleanup / refactor out AI slop & cruftcleanupwrites code (8-subagent refactor)

Adjacent skills: test-coverage (generate tests for untested branches) · dont-make-me-think (usability/UX review).

Shipping

SkillVersionEffortWhat it does
auto-push1.0.3lowCommit message + stage + push with secret and size checks
devops-pipeline2.0.3mediumPre-commit + GitHub Actions quality gates
security-setup1.4.0highLocal pre-commit secret scans, dep checks, static analysis, gated CI
fork-upstream-sync1.3.2mediumSync a fork with upstream while keeping feature branches and open PRs mergeable
release-manager2.6.0maxBump, changelog, tag, GitHub release, publish

Product Planning

SkillVersionEffortWhat it does
idea-validator1.5.0maxMarket, feasibility, competitor checks for ideas
viral-product-evaluator1.2.4highScore codebase + landing page vs 32 viral principles
brand-name-checker1.3.2maxTrademark, domain, social, registry conflicts
prd-generator1.3.2maxStructured PRD from idea or validate notes
tad-generator1.4.0maxTechnical architecture document from PRD
tasks-generator1.3.1maxSprint tasks and plan from PRD

Frontend & Design

SkillVersionEffortWhat it does
frontend-design1.2.4highProduction UIs with usability-first approach
logo-designer1.2.3medium7 SVG logo variants from project context
diagram-generator1.1.2highOne entry point for diagrams — routes to draw.io XML or Excalidraw JSON
website-cloner1.2.1high6-phase URL to improved Vite/React/Tailwind site

Website cloner phases (install individually or as suite):

PhaseVersionWhat it does
website-analyzer1.3.06-dimension analysis → JSON
website-clone-report1.2.2Stakeholder report from analysis
website-improvement-prd1.3.0Improvement PRD
website-implementation-plan1.3.2tasks.md from PRD
website-builder1.3.1Build improved site
website-clone-final-report1.3.0Before/after summary

Diagram generator engines (install the umbrella or a single engine):

EngineVersionWhat it does
drawio-generator1.2.3draw.io XML — precise, editable, C4, swimlanes
excalidraw-generator1.3.3Excalidraw JSON — hand-drawn, sketch, wireframes

Documentation

SkillVersionEffortWhat it does
doc-manager2.0.2mediumGenerate/update docs to match code, cited to path:line, never invented
landing-page-generator1.2.1highLanding pages: marketing copy from a brief, or a README-to-landing rewrite
seo-ai-optimizer1.2.3highTechnical SEO + AI-bot directives
oss-ready1.2.1lowAdd OSS files and templates
agent-config1.3.1mediumCLAUDE.md + AGENTS.md per best practices
subagent-creator1.1.2highCreate, evaluate, improve Claude Code subagent files (.claude/agents/*.md)

App Store

SkillVersionEffortWhat it does
aso-marketing1.2.1maxApp Store + Google Play keyword and metadata optimization
appstore-review-checker1.2.1highPre-submission audit vs Apple guidelines

Tooling

SkillVersionEffortWhat it does
cli-builder1.0.5high5-step CLI tool builder with approval gates
ollama-optimizer1.1.1mediumHardware-aware Ollama tuning
install-script-generator2.2.1highCross-platform install.sh with env detection
opencode-runner1.4.1mediumDelegate work to opencode free cloud models
herdr-agent-comms1.22.2mediumManage Herdr agent fleets: tile panes, message/wait/read, steer
issue-work-loop1.3.1maxResolve one GitHub issue via a Herdr implementer→reviewer loop until CLEAN
tmux-agent-comms2.1.0mediumSpawn, message, read CLI agents in tmux

Suite Folders

Most skills are skills/<name>/. Multi-phase products live under a suite folder: umbrella at skills/<umbrella>/ + phases at skills/<umbrella>/<phase>/.

Current suites: website-cloner (6 sequential phases) and diagram-generator (draw.io + Excalidraw engines behind one router). Install an umbrella or any child. Installers discover both levels.

Mirror the layout for your own multi-skill products.


Project docs

DocPurpose
CONTRIBUTING.mdContribute skills; structure and versioning
docs/guide-building-agent-skills.mdAuthoring guide (plan → write → validate → distribute)
docs/brand_kit.mdLogo files, colors, typography
docs/DECISIONS.mdDoc ambiguity resolutions
docs/troubleshooting.mdInstall/setup validation fixes
docs/archive/Historical work notes (not current product docs)
CHANGELOG.mdRelease history
SECURITY.mdVulnerability reporting

FAQ

Do I need every skill?
No. Pick only what you need. All are independent.

Which agents work?
Any that load external skill files. Installer tools (install.sh:23): Claude Code, Cursor, Windsurf, GitHub Copilot, OpenAI Codex, OpenCode, Google Antigravity.

How do I make my own?
Follow CONTRIBUTING.md, docs/guide-building-agent-skills.md, or patterns from existing skills.

Do skills change my runtime code?
No. They only guide the agent during development.


Get Started

npx skills add https://github.com/luongnv89/skills --skill code-review

All skills · Contribute · MIT


Supported Tool Paths
ToolGlobalProject
Claude Code~/.claude/skills/<skill>/.claude/skills/<skill>/
Cursor~/.agents/skills/<skill>/ + .cursor/rules/<skill>.mdcsame
Windsurf~/.agents/skills/<skill>/ + .windsurf/rules/<skill>.mdsame
GitHub Copilot~/.agents/skills/<skill>/ + .github/instructions/<skill>.instructions.mdsame
OpenAI Codex~/.agents/skills/<skill>/ + ~/.codex/AGENTS.mdsame
OpenCode~/.agents/skills/<skill>/same
Google Antigravity~/.agents/skills/<skill>/same
Project Structure
.
├── skills/
│   └── <name>/
│       ├── SKILL.md
│       ├── scripts/
│       ├── references/
│       └── docs/
└── install.sh / remote-install.sh

# Suite umbrellas also hold child skills:
# skills/<umbrella>/<child>/SKILL.md  (install.sh:44-46)
Creating Skills

See CONTRIBUTING.md.

Minimal:

---
name: my-skill
description: "When to use and what it produces. Don't use for X."
license: MIT
effort: medium
metadata:
  version: 1.0.0
  author: "Your Name"
---
# Agent instructions here. Keep SKILL.md under 500 lines.
Contributing

Read CONTRIBUTING.md and CODE_OF_CONDUCT.md.

Security

See SECURITY.md.

Acknowledgements
  • frontend-design draws from Anthropic's patterns.
  • Many skills follow the conventions established in the skill-creator lineage.

Website · Claude How-To · Blog