Self-Improving Agent: curate auto-memory, promote learnings to CLAUDE.md and rules, extract proven patterns into reusable skills. Provides /si:review, /si:promote, /si:extract, /si:status, and /si:remember slash commands.
Read-only analyst for `~/.claude/projects/<project>/memory/`. Identifies promotion candidates (entries proven enough for CLAUDE.md), stale references, consolidation opportunities, conflicts with existing CLAUDE.md rules, and reports health metrics (capacity, freshness, organization). Spawned by `/si:review`.
Transforms a proven pattern or debugging solution into a standalone, portable skill package. Generates `SKILL.md` with proper frontmatter, reference docs, and examples that work in any project (no hardcoded paths or project-specific values). Spawned by `/si:extract` when a recurring solution should become reusable.
Turn a proven pattern or debugging solution into a standalone reusable skill with SKILL.md, reference docs, and examples. Use when the user runs /si:extract or asks to package a recurring solution from memory into a skill.
Graduate a proven pattern from auto-memory (MEMORY.md) to CLAUDE.md or .claude/rules/ for permanent enforcement. Use when the user runs /si:promote or asks to make a learned behavior permanent.
Explicitly save important knowledge to auto-memory with timestamp and context. Use when a discovery is too important to rely on auto-capture.
Analyze auto-memory for promotion candidates, stale entries, consolidation opportunities, and health metrics. Use when the user runs /si:review or asks what has been learned and what should be promoted or pruned.
Curate Claude Code's auto-memory into durable project knowledge. Analyze MEMORY.md for patterns, promote proven learnings to CLAUDE.md and .claude/rules/, extract recurring solutions into reusable skills. Use when: (1) reviewing what Claude has learned about your project, (2) graduating a pattern from notes to enforced rules, (3) turning a debugging solution into a skill, (4) checking memory health and capacity.
Executes bash commands
Hook triggers when Bash tool is used
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
355 production-ready Claude Code skills, plugins, and agent skills for 13 AI coding tools.
The most comprehensive open-source library of Claude Code skills and agent plugins — also works with OpenAI Codex, Gemini CLI, Cursor, and 9 more coding agents. Reusable expertise packages covering engineering, DevOps, marketing (incl. AEO — Answer Engine Optimization for LLM citation), security (PreToolUse hooks), compliance, C-level advisory (incl. founder-mode CFO/CMO/CRO/CPO/COO/CHRO/CISO/GC/CDO/CAIO/CCO/VPE personas + 21 /cs:* slash commands), productivity (capture/email/reflect), an academic research stack (litreview/grants/dossier/patent/syllabus/pulse/notebooklm/deep-research + hybrid router), and enterprise Research Operations (clinical-research/research-finance/market-research/product-research, v2.9.0).
Works with: Claude Code · OpenAI Codex · Gemini CLI · OpenClaw · Hermes Agent1 · Mistral Vibe2 · Cursor · Aider · Windsurf · Kilo Code · OpenCode · Augment · Antigravity
5,200+ GitHub stars — the most comprehensive open-source Claude Code skills & agent plugins library.
Claude Code skills (also called agent skills or coding agent plugins) are modular instruction packages that give AI coding agents domain expertise they don't have out of the box. Each skill includes:
One repo, thirteen platforms. Works natively as Claude Code plugins, Codex agent skills, Gemini CLI skills, Hermes Agent skills, Mistral Vibe skills, and converts to more tools via scripts/convert.sh. All 602 Python tools run anywhere Python runs.
| Skills | Agents | Personas | |
|---|---|---|---|
| Purpose | How to execute a task | What task to do | Who is thinking |
| Scope | Single domain | Single domain | Cross-domain |
| Voice | Neutral | Professional | Personality-driven |
| Example | "Follow these steps for SEO" | "Run a security audit" | "Think like a startup CTO" |
All three work together. See Orchestration for how to combine them.
# Clone the repository
git clone https://github.com/alirezarezvani/claude-skills.git
cd claude-skills
# Run the setup script
./scripts/gemini-install.sh
# Start using skills
> activate_skill(name="senior-architect")
# Add the marketplace
/plugin marketplace add alirezarezvani/claude-skills
Hermes Agent is BYO-sync tier: the repo ships a pre-generated .hermes/skills/claude-skills/ tree, but you run python scripts/sync-hermes-skills.py once locally to install into ~/.hermes/skills/. Uses the same agentskills.io SKILL.md standard — no format conversion. ↩
Mistral Vibe is also BYO-sync tier: the repo ships a pre-generated .vibe/skills/claude-skills/ tree, run ./scripts/vibe-install.sh once locally to install into ~/.vibe/skills/. Same agentskills.io SKILL.md standard — no format conversion. Docs: https://docs.mistral.ai/mistral-vibe/agents-skills. ↩
npx claudepluginhub motivatedc-creator/saafy --plugin self-improving-agentVP of Engineering advisory: delivery throughput analyzer (DORA 4 metrics + cycle-time bottleneck identification), eng hiring funnel calculator (7-stage conversion + pipeline gap + weakest-stage fixes), eng team structure designer (squad/tribe model + manager-trigger + director-trigger + span-of-control). 4 in-depth references: DORA framework, eng hiring funnel, eng team structure (Conway's Law), production discipline (on-call, incidents, deployment, SLOs). Stdlib-only. Standalone-installable; also bundled in c-level-skills. NOT a CTO skill — VPE owns how the team ships, CTO owns what to build.
Hypothesis testing, A/B experiment analysis, sample size calculation, and confidence intervals. 3 stdlib-only Python tools with Z-test, t-test, chi-square, effect sizes, power analysis, and Wilson score intervals.
Premium single-file HTML landing page generator with GSAP 3D animations, scroll-triggered effects, and mouse-parallax depth. Forcing 3-4 question grill-me intake (product+pitch, audience register, brand overrides, tone) locks down positioning before any copy or markup is written. Outputs a single self-contained HTML file (Claude Code) or HTML artifact (Claude.ai) with all CSS/JS inline — only externals are Google Fonts + GSAP via CDN. Configurable brand colors via CSS custom property overrides. Source spec: megaprompts/04-landing-megaprompt.md (PR #657). Distinct from product-team/skills/landing-page-generator (which outputs Next.js TSX for conversion-optimized lead-gen) — this skill is for premium visual one-pagers with motion design.
Arquiteto de Empresa (PT-BR): constrói um negócio do zero como um bundle OKF (Open Knowledge Format) — uma árvore de arquivos .md versionáveis com frontmatter type, links formando grafo, e index.md/log.md reservados, legível por humanos e por agentes. Conduz o fundador por uma entrevista de 12 fases (fundação, estratégia, mercado, financeiro, comercial, marketing, produto, operações, tech, pessoas, jurídico, governança), uma fase por vez, e gera os conceitos markdown conformantes. 3 ferramentas stdlib: scaffold_bundle (andaime do bundle), okf_linter (valida type/arquivos reservados/links), index_generator (regenera os index.md). Standalone-installable; também empacotado em c-level-skills.
A disciplined coding pipeline that grounds code in verified structure before a line is written: Discuss -> Map -> Decompose -> Execute -> Verify, with a lazy-senior-dev YAGNI ladder that deletes unnecessary code first. No invented APIs, no assumed imports, no placeholder code. Opt-in for high-stakes, complex, or multi-file work; not for trivial edits. Synthesizes four MIT/open-source projects (Ralph, GSD Core, Graphify, Ponytail).
Ultra-compressed communication mode. Cuts 65% of output tokens (measured) while keeping full technical accuracy by speaking like a caveman.
Multi-model consensus engine integrating OpenAI Codex CLI, Gemini CLI, and Claude CLI for collaborative code review and problem-solving.
Memory compression system for Claude Code - persist context across sessions
Comprehensive UI/UX design plugin for mobile (iOS, Android, React Native) and web applications with design systems, accessibility, and modern patterns
Comps, precedents, LBO to a branded pitch deck, end to end