Curated agent skills for AI coding tools (Hermes, Claude Code, Codex, Cursor, Windsurf, Copilot) — a mix of community-vetted skills and personal workflow automations.
Browse the catalog | Install | CI notifications
Pick one skill:
npx skills add https://github.com/hongphuc5497/skills --skill <name>Pick several:
npx skills add https://github.com/hongphuc5497/skills --skill code-review --skill auto-pushOr grab everything:
npx skills add https://github.com/hongphuc5497/skillsgit clone https://github.com/hongphuc5497/skills.git
cd skills && bash install.shInteractive TUI:
curl -sSL https://raw.githubusercontent.com/hongphuc5497/skills/main/remote-install.sh | bashNon-interactive:
curl -sSL https://raw.githubusercontent.com/hongphuc5497/skills/main/remote-install.sh | bash -s -- \
--skills "code-review,auto-push" --tools "Claude Code" --scope globalStandalone, well-tested skills for common development workflows.
| Skill | What it does |
|---|---|
| auto-push | Generate a commit message, stage all changes, and push to remote after scanning for secrets, large files, and protect... |
| brand-name-checker | Check product and brand names for conflicts across trademarks, domains, social handles, and package registries. Retur... |
| cavecrew | Decision guide for delegating to caveman-style subagents. Tells the main thread WHEN to spawn cavecrew-investigator... |
| caveman | Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accu... |
| caveman-commit | Ultra-compressed commit message generator. Cuts noise from commit messages while preserving intent and reasoning. Con... |
| caveman-compress | Compress natural language memory files (CLAUDE.md, todos, preferences) into caveman format to save input tokens. Pres... |
| caveman-help | Quick-reference card for all caveman modes, skills, and commands. One-shot display, not a persistent mode. Trigger: /... |
| caveman-review | Ultra-compressed code review comments. Cuts noise from PR feedback while preserving the actionable signal. Each comme... |
| caveman-stats | Show real token usage and estimated savings for the current session. Reads directly from the Claude Code session log ... |
| code-optimizer | Analyze code for performance bottlenecks, memory leaks, and algorithmic inefficiencies. Use when asked to optimize, f... |
| code-review | Review code changes for bugs, security vulnerabilities, and code quality issues — producing prioritized findings with... |
| context-hub | Fetch current API/SDK docs before writing integration code. Use whenever writing code that integrates with an externa... |
| docs-generator | Generate and restructure project documentation into a clear, accessible hierarchy. Use when asked to organize docs, g... |
| idea-validator | Evaluate app ideas and startup concepts across market viability, technical feasibility, and competitive landscape. Us... |
| oss-ready | Transform a project into a professional open-source repository by adding LICENSE, README, CONTRIBUTING, CODE_OF_CONDU... |
| prd-generator | Generate Product Requirements Documents from idea.md and validate.md files. Use when asked to create or update a ... |
| quick-healthy-recipes | Generate exactly 3 simple, fast, healthy recipes from food photos, ingredient lists, or cravings. Use for what-to-coo... |
| release-manager | Manage software releases end-to-end: bump version, generate changelog, tag, push, GitHub release, publish to PyPI/npm... |
| security-setup | Install local-first security hardening: pre-commit secret detection, offline dependency scans, static analysis, repor... |
| seo-ai-optimizer | Audit and optimize websites for technical SEO, content SEO, and AI bot accessibility. Fixes meta tags, sitemaps, robo... |
| tasks-generator | Generate development tasks from a PRD file with sprint-based planning. Use when users ask to create tasks from PRD, b... |
| usability-review | Review UI for usability issues using Steve Krug's principles and produce a scannable report. Use when asked for a usa... |
Personal skills built for my specific stack and workflows.
| Skill | What it does |
|---|---|
| hermes-config | Configure Hermes Agent — providers, models, tools, skills, voice, gateway, plugins. Uses hermes CLI commands. Not for... |
| multi-agent-orchestrator | Orchestrate work across multiple AI coding agents (Hermes, Codex, Claude Code) — delegate tasks in parallel, merge re... |
| rtk | RTK (Rust Token Killer) — CLI proxy that compresses noisy shell output by 60-90%. Use when piping commands through rt... |
Supported Tool Paths
| Tool | Global path | Project path |
|---|---|---|
| Claude Code | ~/.claude/skills/<skill>/ |
.claude/skills/<skill>/ |
| Cursor | ~/.agents/skills/<skill>/ + .cursor/rules/<skill>.mdc |
same, relative |
| Windsurf | ~/.agents/skills/<skill>/ + .windsurf/rules/<skill>.md |
same, relative |
| GitHub Copilot | ~/.agents/skills/<skill>/ + .github/instructions/<skill>.instructions.md |
same, relative |
| OpenAI Codex | ~/.agents/skills/<skill>/ + ~/.codex/AGENTS.md |
same, relative |
| OpenCode | ~/.agents/skills/<skill>/ |
same, relative |
Project Structure
./
├── skills/ # Skill source files
│ ├── code-review/
│ │ ├── SKILL.md
│ │ ├── references/
│ │ └── scripts/
│ ├── auto-push/
│ └── prd-generator/
│ ├── SKILL.md
│ └── references/
├── assets/ # Logo, images
├── install.sh # Local installer (TUI)
├── remote-install.sh # Remote installer (curl-pipe)
├── CLAUDE.md # Agent context for this repo
├── AGENTS.md # Subagent definitions
├── CONTRIBUTING.md # How to contribute
├── CHANGELOG.md # Version history
└── LICENSE # MIT
Do I need all the skills? No. Each skill is independent. Install only what you need.
Can I create my own skills? Yes. Follow the Contributing Guide.
Why create your own? Tailored skills encode specific toolchains, API conventions, and failure modes battle-tested on actual hardware. General skills cover common development workflows.
View all skills | Contribute | MIT Licensed