alirezarezvani/claude-skills

Claude Code Skills & Plugins

411 production-ready skills for Claude Code and 12 other coding agents, covering engineering, product, marketing, compliance, finance and the C-suite. We test whether each skill loads when you ask in plain words, and publish the results.

Works with: Claude Code · OpenAI Codex · Gemini CLI · OpenClaw · Hermes Agent[^hermes] · Mistral Vibe[^vibe] · Cursor · Aider · Windsurf · Kilo Code · OpenCode · Augment · Antigravity

Install in one minute

Claude Code

/plugin marketplace add alirezarezvani/claude-skills
/plugin install engineering-skills@claude-code-skills

Codex, Cursor, Gemini CLI, Copilot and other agents (the open-source skills installer)

npx skills add alirezarezvani/claude-skills

More options for each tool are under Quick Install.

Pick your role

| You are | Install | You get | |---|---|---| | Software engineer | engineering-skills | Architecture, code review, TDD, frontend, backend, DevOps, security, QA | | Platform or AI engineer | engineering-advanced-skills | Agent design, RAG, MCP servers, CI/CD, observability, SLOs, evals | | Product manager | product-skills | Discovery, RICE, PRDs, user stories, roadmaps, UX research | | Delivery lead or scrum master | pm-skills | Sprint health, Jira and Confluence, flow metrics, forecasts | | Marketer | marketing-skills | SEO, answer-engine optimization, copywriting, CRO, email, paid ads | | Founder or executive | c-level-skills | CEO, CTO, CFO, CMO, CRO and other advisors, board prep, hard calls | | Regulated industry | ra-qm-skills | ISO 13485, EU MDR, FDA, ISO 27001, SOC 2, GDPR, CAPA, risk files | | Finance | finance-skills | DCF, budgets, SaaS metrics, month-end close |

Install with /plugin install @claude-code-skills.

Start with these

Each of these loaded on every plain-language test prompt. See all verified skills.

| Skill | What it does | Install | |---|---|---| | agent-run-forensics | Checks what your agent actually did against what it said it did, from the session transcript | agent-run-forensics | | human-gate | Refuses to ship a plan, spec or migration until a named person has reviewed it and no blocker is open | human-gate | | skill-retro | Grades your skills from your own past sessions and proposes only the edits the evidence supports | skill-retro | | i18n-localization | Finds missing keys, broken placeholders and wrong plural forms before a language ships | i18n-localization | | month-end-close | Runs the close calendar, proves reconciliations and refuses boilerplate variance explanations | month-end-close | | cmmc-readiness | Scores CMMC 2.0 Level 2 readiness, SPRS and POA&M close-out | cmmc-readiness |

[^hermes]: 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. [^vibe]: 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: .

---

What Are Claude Code Skills & Agent Plugins?

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:

• SKILL.md — structured instructions, workflows, and decision frameworks
• Python tools — 807 CLI scripts (all stdlib-only, zero pip installs)
• Reference docs — 917 templates, checklists, and domain-specific knowledge files

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 807 Python tools run anywhere Python runs.

Skills vs Agents vs Personas

| | 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.

---

Quick Install

Windows users: clone with git clone -c core.symlinks=true (Developer Mode enabled) — otherwise the .gemini//.codex//.vibe//.hermes/ mirror trees check out as 1-line pointer text files instead of skills — and set PYTHONUTF8=1 so tools that print Unicode don't crash on legacy-codepage consoles. Details: INSTALLATION.md → Windows Notes.

Claude Code (Recommended)

# Add the marketplace
/plugin marketplace add alirezarezvani/claude-skills
Install by domain
/plugin install engineering-skills@claude-code-skills          # core engineering
/plugin install engineering-advanced-skills@claude-code-skills  # POWERFUL-tier
/plugin install product-skills@claude-code-skills               # product
/plugin install marketing-skills@claude-code-skills             # marketing
/plugin install ra-qm-skills@claude-code-skills                 # regulatory/quality
/plugin install pm-skills@claude-code-skills                    # project management
/plugin install c-level-skills@claude-code-skills               # C-level advisory (full C-suite)
/plugin install business-growth-skills@claude-code-skills       # business & growth
/plugin install finance-skills@claude-code-skills               # finance
Or install a standalone plugin
/plugin install pw@claude-code-skills                           # Playwright testing toolkit
/plugin install self-improving-agent@claude-code-skills         # Auto-memory curation
/plugin install karpathy-coder@claude-code-skills               # Coding-discipline reviewer
/plugin install grill-me@claude-code-skills                     # Plan interrogator

Only names listed in .claude-plugin/marketplace.json can be installed. Most skills (for example skill-security-auditor or content-creator) ship inside a domain bundle, so install the bundle that contains them. Run /plugin and open the marketplace to browse every installable name.

Claude Code (Recommended)

# Add the marketplace
/plugin marketplace add alirezarezvani/claude-skills
Install by domain
/plugin install engineering-skills@claude-code-skills          # core engineering
/plugin install engineering-advanced-skills@claude-code-skills  # POWERFUL-tier
/plugin install product-skills@claude-code-skills               # product
/plugin install marketing-skills@claude-code-skills             # marketing
/plugin install ra-qm-skills@claude-code-skills                 # regulatory/quality
/plugin install pm-skills@claude-code-skills                    # project management
/plugin install c-level-skills@claude-code-skills               # C-level advisory (full C-suite)
/plugin install business-growth-skills@claude-code-skills       # business & growth
/plugin install finance-skills@claude-code-skills               # finance
Or install a standalone plugin
/plugin install pw@claude-code-skills                           # Playwright testing toolkit
/plugin install self-improving-agent@claude-code-skills         # Auto-memory curation
/plugin install karpathy-coder@claude-code-skills               # Coding-discipline reviewer
/plugin install grill-me@claude-code-skills                     # Plan interrogator

Only names listed in .claude-plugin/marketplace.json can be installed. Most skills (for example skill-security-auditor or content-creator) ship inside a domain bundle, so install the bundle that contains them. Run /plugin and open the marketplace to browse every installable name.

Gemini CLI

# 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")

OpenAI Codex

npx agent-skills-cli add alirezarezvani/claude-skills --agent codex
Or: git clone + ./scripts/codex-install.sh --category   (no arguments lists categories)

OpenClaw

git clone https://github.com/alirezarezvani/claude-skills.git
cd claude-skills && ./scripts/openclaw-install.sh

Manual Installation

git clone https://github.com/alirezarezvani/claude-skills.git
Copy any skill folder to ~/.claude/skills/ (Claude Code) or ~/.codex/skills/ (Codex)

---

Multi-Tool Support (New)

Convert the skills for 9 more AI coding tools with a single script:

| Tool | Format | Install | |------|--------|---------| | Cursor | .mdc rules | ./scripts/install.sh --tool cursor --target . | | Aider | CONVENTIONS.md | ./scripts/install.sh --tool aider --target . | | Kilo Code | .kilocode/rules/ | ./scripts/install.sh --tool kilocode --target . | | Windsurf | .windsurf/skills/ | ./scripts/install.sh --tool windsurf --target . | | OpenCode | .opencode/skills/ | ./scripts/install.sh --tool opencode --target . | | Augment | .augment/rules/ | ./scripts/install.sh --tool augment --target . | | Antigravity | ~/.gemini/antigravity/skills/ | ./scripts/install.sh --tool antigravity | | Hermes Agent | ~/.hermes/skills/ | python scripts/sync-hermes-skills.py --verbose | | Mistral Vibe | ~/.vibe/skills/ | ./scripts/vibe-install.sh |

How it works:

# 1. Convert all skills to all tools (takes ~15 seconds)
./scripts/convert.sh --tool all
2. Install into your project (with confirmation)
./scripts/install.sh --tool cursor --target /path/to/project
Or use --force to skip confirmation:
./scripts/install.sh --tool aider --target . --force
3. Verify
find .cursor/rules -name "*.mdc" | wc -l  # one file per skill

Each tool gets:

• ✅ All skills converted to native format
• ✅ Per-tool README with install/verify/update steps
• ✅ Support for scripts, references, templates where applicable
• ✅ Zero manual conversion work

Run ./scripts/convert.sh --tool all to generate tool-specific outputs locally.

---

Skills Overview

411 production-ready skills across 20 domains:

| Domain | Skills | Highlights | Details | |--------|--------|------------|---------| | 🔧 Engineering — Core | 54 | Architecture, frontend, backend, fullstack, QA, DevOps, SecOps, AI/ML, data, Playwright Pro (test gen, flaky fix, migrations), self-improving agent (auto-memory curation), security suite, a11y audit, named-persona-adversarial-review (review via named engineering philosophies), embedded-iot-mentor (MCU/board selection, firmware-reuse-first, breadboard-MVP discipline) | engineering-team/ | | ⚡ Engineering — POWERFUL | 104 | Agent designer, RAG architect, database designer, CI/CD builder, security auditor, MCP builder, AgentHub, Helm charts, Terraform, self-eval, llm-wiki, tc-tracker, autoresearch-agent, reliability portfolio (feature-flags-architect, kubernetes-operator, chaos-engineering, slo-architect), ship-gate, security-guidance PreToolUse hook, Matt Pocock skills (write-a-skill, caveman, grill-me, handoff, grill-with-docs), zero-hallucination-coder (Discuss→Map→Decompose→Execute→Verify), agent-harness (goal→plan→execute→verify→close loops over any domain), memory-engineering (price the memory write path, pick which cost to pay, audit FACT/SKILL/LOG density, gate on a forgetting policy), skillopt-sleep (nightly gated self-evolution from real Claude Code sessions, vendored from microsoft/SkillOpt), book-to-skill (compile a book, docs folder, or spec collection into a knowledge-base skill, then package it as a plugin), boost-asio-pro (async C++ networking — version-gated coroutine/callback styles, strand discipline), human-gate (batched human review as a structured artifact + a gate that refuses to close on open blockers), agent-memory (four-tier L0-L3 memory ladder over Claude Code hooks; promotion earned by recurrence across sessions and days, redacted or contested claims refuse to promote, nothing reaches CLAUDE.md without a human adopt), skill-retro (grade the agent setup from real session history — rubric-judged, deterministically gated, evidence-traced skill edits), deep-learning-book (companion to the free Goodfellow/Bengio/Courville textbook — 20 chapter files with a 2016→2026 delta layer, reading-path planner, Ch-11 training diagnostic, capacity planner, FLOP/activation-memory calculator), spinning-up-deep-rl (knowledge base compiled from OpenAI's Spinning Up in Deep RL — RL fundamentals, the model-free taxonomy, policy-gradient derivations, and one chapter per reference algorithm), agent-regression-evals (repeated-trial eval gate: trajectory grading, flake detection with pass^k, paired regression statistics that block a merge), coding-agent-rollout (team settings, permissions, MCP and plugin governance, CLAUDE.md layering, privacy-safe adoption counts), commit-craft (split a tangled working tree into a reviewable commit series, block staged secrets, lint messages for the why), i18n-localization (check translation files against CLDR plural rules, find hardcoded UI strings, build pseudo-locales) | engineering/ | | 🎯 Product | 19 | Product manager, agile PO, strategist, UX researcher, UI design, landing pages, SaaS scaffolder, analytics, experiment designer, discovery, roadmap communicator, code-to-prd, apple-hig-expert, UI finish QA (design-qa) | product-team/ | | 📣 Marketing | 50 | 8 pods: Content, SEO + AEO (aeo — E-E-A-T audit, citation tracking across 5 LLMs) + local (local-seo-manager — GBP/NAP/Map-Pack), CRO, Channels, Growth, Intelligence, Sales + business-name-fit (cross-cultural naming) + context foundation + orchestration router | marketing-skill/ | | 🚀 Productivity | 12 | capture (brain-dump-to-action), email pair (inbox-setup + inbox-triage), reflect (journal), handoff (Matt Pocock-inspired), andreessen (market-first decision mode), roast (5-angle idea panel → GO/RESHAPE/KILL), fable-goal (ramble → autonomous /goal prompt), weekly-review (GTD loop with refusal gate), deep-work (time-blocking + shallow-work budget), meetings (cost gate + agenda + action items), swedish-mentor (CEFR-leveled Swedish learning paths) | productivity/ | | 🎨 Marketing (top-level) | 7 | landing — single-file HTML landing-page generator (4 design styles, GSAP patterns, brand palette validator); linkedin — organic LinkedIn presence with User Agreement §8.2 refusals in code (orchestrator + profile, strategy, content, engagement, analytics) | marketing/ | | 🔬 Research (academic) | 10 | research orchestrator (hybrid router + fallback) + 8 specialists: pulse, litreview, grants (NIH), dossier, patent, syllabus, notebooklm, meta-research (rigor-first meta-research), deepread (evidence-first reading of supplied documents) | research/ | | 🧪 Research Operations ✨v2.9.0 | 6 | Enterprise/cross-functional research: orchestrator + clinical-research (study design), research-finance (R&D program finance), market-research (sizing/survey/segmentation), product-research (user research), interview-mapper (transcript coding with quote verification) — each with onboarding + customization + opt-in autoresearch bridge | research-ops/ | | 📋 Project Management | 9 | Senior PM, scrum master, Jira, Confluence, Atlassian admin, templates + bundled Atlassian Remote MCP | project-management/ | | 🏥 Regulatory & QM | 23 | ISO 13505, MDR 2017/745, FDA, ISO 27001, GDPR, SOC 2, CAPA, risk management, access reviews (access-lifecycle), CMMC 2.0 Level 2 (cmmc-readiness), agent-decision-receipts (PQ-signed action receipts) | ra-qm-team/ | | 🛡️ Compliance OS | 9 | Compliance operating system — controls, evidence, audit-readiness workflows | compliance-os/ | | 💼 C-Level Advisory | 46 | Full C-suite (CEO/CTO/CFO/CMO/CRO/CPO/COO/CHRO/CISO/GC/CDO/CAIO/CCO/VPE) + executive mentor + orchestration + board meetings + culture & collaboration | c-level-advisor/ | | 🎩 C-Level Agents (founder mode) | 22 | 13 cs- persona agents + 21 /c-level-agents: commands — office hours, boardroom, strategic sprint pipeline, cross-eval, freeze | c-level-agents/ | | 📈 Business & Growth | 5 | Customer success, sales engineer, revenue ops, contracts & proposals, BizDev toolkit | business-growth/ | | 🏭 Business Operations | 7 | Orchestrator + process-mapper, vendor-management, capacity-planner, internal-comms, knowledge-ops, procurement-optimizer | business-operations/ | | 🤝 Commercial | 8 | Orchestrator + pricing-strategist, deal-desk, partnerships-architect, channel-economics, commercial-policy, rfp-responder, commercial-forecaster | commercial/ | | 💰 Finance | 8 | Financial analyst (DCF, budgeting, forecasting), SaaS metrics coach, business investment advisor, stock-analysis (sector-relative fundamentals, 26 sector playbooks, forensic + IPO modes), passive-deal-screener (LP-side private deal screening, not investment advice), month-end-close (close calendar on its critical path, reconciliation proof with aging, flux gate that refuses boilerplate explanations) | finance/ | | 🧬 Agent Launcher ✨new | 6 | Build/launch/grade/schedule Claude Managed Agents in your own account — orchestrator (context: fork goal router) + interview + stage-launch + grade-iterate (bounded outcome loop) + run-without-you (cron deployment loop) + wrap-up. Every session starts with a goal; deterministic BYOK scaffolders (no API calls). Re-implements Anthropic's launch-your-agent (Apache-2.0) | agent-launcher/ | | 🔄 Loop Library | 1 | loop-library — discover, find, audit/repair, adapt, and design bounded AI-agent loops; reads the live catalog from signals.forwardfuture.ai at runtime (vendored verbatim from Forward-Future/loop-library) | loop-library/ | | 📄 Markdown → HTML | 5 | markdown-html-orchestrator (doctype router) + design-system (WCAG-AA brand tokens) + md-document (long-form) + md-review (2-col code review) + md-slides (single-file deck) — markdown-to-interactive-HTML converter | markdown-html/ |

---

Personas

Pre-configured agent identities with curated skill loadouts, workflows, and distinct communication styles. Personas go beyond "use these skills" — they define how an agent thinks, prioritizes, and communicates.

| Persona | Domain | Best For | |---------|--------|----------| | Startup CTO | Engineering + Strategy | Architecture decisions, tech stack selection, team building, technical due diligence | | Growth Marketer | Marketing + Growth | Content-led growth, launch strategy, channel optimization, bootstrapped marketing | | Solo Founder | Cross-domain | One-person startups, side projects, MVP building, wearing all hats |

Usage:

# Claude Code
cp agents/personas/startup-cto.md ~/.claude/agents/

Any tool
./scripts/convert.sh --tool cursor  # Converts personas too

See agents/personas/ for details. Create your own with TEMPLATE.md.

---

Orchestration

A lightweight protocol for coordinating personas, skills, and agents on work that crosses domain boundaries. No framework required.

Four patterns:

| Pattern | What | When | |---------|------|------| | Solo Sprint | Switch personas across project phases | Side projects, MVPs, solo founders | | Domain Deep-Dive | One persona + multiple stacked skills | Architecture reviews, compliance audits | | Multi-Agent Handoff | Personas review each other's output | High-stakes decisions, launch readiness | | Skill Chain | Sequential skills, no persona needed | Content pipelines, repeatable checklists |

Example: 6-week product launch

Week 1-2: startup-cto + aws-solution-architect + senior-frontend → Build
Week 3-4: growth-marketer + launch-strategy + copywriting + seo-audit → Prepare
Week 5-6: solo-founder + email-sequence + analytics-tracking → Ship and iterate

See orchestration/ORCHESTRATION.md for the full protocol and examples.

---

POWERFUL Tier

A selection of the advanced skills with deep, production-grade capabilities:

| Skill | What It Does | |-------|-------------| | agent-designer | Multi-agent orchestration, tool schemas, performance evaluation | | agent-workflow-designer | Sequential, parallel, router, orchestrator, and evaluator patterns | | rag-architect | RAG pipeline builder, chunking optimizer, retrieval evaluator | | database-designer | Schema analyzer, ERD generation, index optimizer, migration generator | | database-schema-designer | Requirements → migrations, types, seed data, RLS policies | | migration-architect | Migration planner, compatibility checker, rollback generator | | skill-security-auditor | 🔒 Security gate — scan skills for malicious code before installation | | ci-cd-pipeline-builder | Analyze stack → generate GitHub Actions / GitLab CI configs | | mcp-server-builder | Build MCP servers from OpenAPI specs | | pr-review-expert | Blast radius analysis, security scan, coverage delta | | api-design-reviewer | REST API linter, breaking change detector, design scorecard | | api-test-suite-builder | Scan API routes → generate complete test suites | | dependency-auditor | Multi-language scanner, license compliance, upgrade planner | | observability-designer | SLO designer, alert optimizer, dashboard generator | | performance-profiler | Node/Python/Go profiling, bundle analysis, load testing | | monorepo-navigator | Turborepo/Nx/pnpm workspace management & impact analysis | | changelog-generator | Conventional commits → structured changelogs | | codebase-onboarding | Auto-generate onboarding docs from codebase analysis | | runbook-generator | Codebase → operational runbooks