BeClaude

self-improving-agent

17.8kCommunity RegistryDevelopmentby Alireza Rezvani

Curate auto-memory, promote learnings to CLAUDE.md and rules, extract patterns into skills. Ships 5 slash commands (/si:review, /si:promote, /si:extract, /si:status, /si:remember) and 2 sub-agents (memory-analyst, skill-extractor).

First seen 4/17/2026

Summary

md and rules, and extracting patterns into reusable skills.

  • It ships five slash commands and two sub-agents to automate code review insights, memory management, and skill extraction, making your coding agent continuously smarter over time.

Overview

345 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 + 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 Agent[^hermes] · Mistral Vibe[^vibe] · Cursor · Aider · Windsurf · Kilo Code · OpenCode · Augment · Antigravity

[^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: <https://docs.mistral.ai/mistral-vibe/agents-skills>.

![License: MIT](https://opensource.org/licenses/MIT) ![Skills](#skills-overview) ![Agents](#agents) ![Personas](#personas) ![Commands](#commands) ![Stars](https://github.com/alirezarezvani/claude-skills/stargazers) ![SkillCheck Validated](https://getskillcheck.com)

5,200+ GitHub stars — the most comprehensive open-source Claude Code skills & agent plugins library.


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 — 579 CLI scripts (all stdlib-only, zero pip installs)
  • Reference docs — 702 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 579 Python tools run anywhere Python runs.

Skills vs Agents vs Personas

SkillsAgentsPersonas
PurposeHow to execute a taskWhat task to doWho is thinking
ScopeSingle domainSingle domainCross-domain
VoiceNeutralProfessionalPersonality-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

Gemini CLI (New)

bash
# 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")

Claude Code (Recommended)

bash
# Add the marketplace
/plugin marketplace add alirezarezvani/claude-skills

# Install by domain
/plugin install engineering-skills@claude-code-skills          # 24 core engineering
/plugin install engineering-advanced-skills@claude-code-skills  # 25 POWERFUL-tier
/plugin install product-skills@claude-code-skills               # 12 product skills
/plugin install marketing-skills@claude-code-skills             # 43 marketing skills
/plugin install ra-qm-skills@claude-code-skills                 # 12 regulatory/quality
/plugin install pm-skills@claude-code-skills                    # 6 project management
/plugin install c-level-skills@claude-code-skills               # 28 C-level advisory (full C-suite)
/plugin install business-growth-skills@claude-code-skills       # 4 business & growth
/plugin install finance-skills@claude-code-skills               # 2 finance (analyst + SaaS metrics)

# Or install individual skills
/plugin install skill-security-auditor@claude-code-skills       # Security scanner
/plugin install playwright-pro@claude-code-skills                  # Playwright testing toolkit
/plugin install self-improving-agent@claude-code-skills         # Auto-memory curation
/plugin install content-creator@claude-code-skills              # Single skill

OpenAI Codex

bash
npx agent-skills-cli add alirezarezvani/claude-skills --agent codex
# Or: git clone + ./scripts/codex-install.sh

OpenClaw

bash
bash <(curl -s https://raw.githubusercontent.com/alirezarezvani/claude-skills/main/scripts/openclaw-install.sh)

Manual Installation

bash
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 all 345 skills to 9 AI coding tools with a single script:

ToolFormatInstall
Cursor.mdc rules./scripts/install.sh --tool cursor --target .
AiderCONVENTIONS.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:

bash
# 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  # Should show 346

Each tool gets:

  • ✅ All 345 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

345 skills across 17 domains:

DomainSkillsHighlightsDetails
🔧 Engineering — Core51Architecture, 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 auditengineering-team/
⚡ Engineering — POWERFUL78Agent 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)engineering/
🎯 Product17Product manager, agile PO, strategist, UX researcher, UI design, landing pages, SaaS scaffolder, analytics, experiment designer, discovery, roadmap communicator, code-to-prd, apple-hig-expertproduct-team/
📣 Marketing468 pods: Content, SEO + AEO (aeo — E-E-A-T audit, citation tracking across 5 LLMs), CRO, Channels, Growth, Intelligence, Sales + context foundation + orchestration routermarketing-skill/
🚀 Productivity6capture (brain-dump-to-action), email pair (inbox-setup + inbox-triage), reflect (journal), handoff (Matt Pocock-inspired), andreessen (market-first decision mode)productivity/
🎨 Marketing (top-level)1landing — single-file HTML landing-page generator (4 design styles, GSAP patterns, brand palette validator)marketing/
🔬 Research (academic)8research orchestrator (hybrid router + fallback) + 7 specialists: pulse, litreview, grants (NIH), dossier, patent, syllabus, notebooklmresearch/
🧪 Research Operations ✨v2.9.05Enterprise/cross-functional research: orchestrator + clinical-research (study design), research-finance (R&D program finance), market-research (sizing/survey/segmentation), product-research (user research) — each with onboarding + customization + opt-in autoresearch bridgeresearch-ops/
📋 Project Management9Senior PM, scrum master, Jira, Confluence, Atlassian admin, templates + bundled Atlassian Remote MCPproject-management/
🏥 Regulatory & QM18ISO 13485, MDR 2017/745, FDA, ISO 27001, GDPR, SOC 2, CAPA, risk managementra-qm-team/
🛡️ Compliance OS9Compliance operating system — controls, evidence, audit-readiness workflowscompliance-os/
💼 C-Level Advisory66Full C-suite (CEO/CTO/CFO/CMO/CRO/CPO/COO/CHRO/CISO/GC/CDO/CAIO/CCO/VPE) + founder-mode agents + orchestration + board meetings + culture & collaborationc-level-advisor/
📈 Business & Growth5Customer success, sales engineer, revenue ops, contracts & proposals, BizDev toolkitbusiness-growth/
🏭 Business Operations7Orchestrator + process-mapper, vendor-management, capacity-planner, internal-comms, knowledge-ops, procurement-optimizerbusiness-operations/
🤝 Commercial8Orchestrator + pricing-strategist, deal-desk, partnerships-architect, channel-economics, commercial-policy, rfp-responder, commercial-forecastercommercial/
💰 Finance4Financial analyst (DCF, budgeting, forecasting), SaaS metrics coach, business investment advisorfinance/

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.

PersonaDomainBest For
**Startup CTO**Engineering + StrategyArchitecture decisions, tech stack selection, team building, technical due diligence
**Growth Marketer**Marketing + GrowthContent-led growth, launch strategy, channel optimization, bootstrapped marketing
**Solo Founder**Cross-domainOne-person startups, side projects, MVP building, wearing all hats

Usage:

bash
# 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:

PatternWhatWhen
Solo SprintSwitch personas across project phasesSide projects, MVPs, solo founders
Domain Deep-DiveOne persona + multiple stacked skillsArchitecture reviews, compliance audits
Multi-Agent HandoffPersonas review each other's outputHigh-stakes decisions, launch readiness
Skill ChainSequential skills, no persona neededContent pipelines, repeatable checklists

Example: 6-week product launch

code
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

25 advanced skills with deep, production-grade capabilities:

SkillWhat It Does
agent-designerMulti-agent orchestration, tool schemas, performance evaluation
agent-workflow-designerSequential, parallel, router, orchestrator, and evaluator patterns
rag-architectRAG pipeline builder, chunking optimizer, retrieval evaluator
database-designerSchema analyzer, ERD generation, index optimizer, migration generator
database-schema-designerRequirements → migrations, types, seed data, RLS policies
migration-architectMigration planner, compatibility checker, rollback generator
skill-security-auditor🔒 Security gate — scan skills for malicious code before installation
ci-cd-pipeline-builderAnalyze stack → generate GitHub Actions / GitLab CI configs
mcp-server-builderBuild MCP servers from OpenAPI specs
pr-review-expertBlast radius analysis, security scan, coverage delta
api-design-reviewerREST API linter, breaking change detector, design scorecard
api-test-suite-builderScan API routes → generate complete test suites
dependency-auditorMulti-language scanner, license compliance, upgrade planner
observability-designerSLO designer, alert optimizer, dashboard generator
performance-profilerNode/Python/Go profiling, bundle analysis, load testing
monorepo-navigatorTurborepo/Nx/pnpm workspace management & impact analysis
changelog-generatorConventional commits → structured changelogs
codebase-onboardingAuto-generate onboarding docs from codebase analysis
runbook-generatorCodebase → operational runbooks with commands
git-worktree-managerParallel dev with port isolation, env sync
env-secrets-manager.env management, leak detection, rotation workflows
incident-commanderIncident response playbook, severity classifier, PIR generator
tech-debt-trackerCodebase debt scanner, prioritizer, trend dashboard
interview-system-designerInterview loop designer, question bank, calibrator

🔒 Skill Security Auditor

New in v2.0.0 — audit any skill for security risks before installation:

bash
python3 engineering/skill-security-auditor/scripts/skill_security_auditor.py /path/to/skill/

Scans for: command injection, code execution, data exfiltration, prompt injection, dependency supply chain risks, privilege escalation. Returns PASS / WARN / FAIL with remediation guidance.

Zero dependencies. Works anywhere Python runs.


Recently Enhanced Skills

Production-quality upgrades added for:

  • engineering/git-worktree-manager — worktree lifecycle + cleanup automation scripts
  • engineering/mcp-server-builder — OpenAPI -> MCP scaffold + manifest validator
  • engineering/changelog-generator — release note generator + conventional commit linter
  • engineering/ci-cd-pipeline-builder — stack detector + pipeline generator
  • marketing-skill/prompt-engineer-toolkit — prompt A/B tester + prompt version/diff manager

Each now ships with scripts/, extracted references/, and a usage-focused README.md.


Usage Examples

Architecture Review

code
Using the senior-architect skill, review our microservices architecture
and identify the top 3 scalability risks.

Content Creation

code
Using the content-creator skill, write a blog post about AI-augmented
development. Optimize for SEO targeting "Claude Code tutorial".

Compliance Audit

code
Using the mdr-745-specialist skill, review our technical documentation
for MDR Annex II compliance gaps.

Python Analysis Tools

579 CLI tools ship with the skills (all verified, stdlib-only):

bash
# SaaS health check
python3 finance/saas-metrics-coach/scripts/metrics_calculator.py --mrr 80000 --customers 200 --churned 3 --json

# Brand voice analysis
python3 marketing-skill/content-production/scripts/brand_voice_analyzer.py article.txt

# Tech debt scoring
python3 c-level-advisor/cto-advisor/scripts/tech_debt_analyzer.py /path/to/codebase

# RICE prioritization
python3 product-team/product-manager-toolkit/scripts/rice_prioritizer.py features.csv

# Security audit
python3 engineering/skill-security-auditor/scripts/skill_security_auditor.py /path/to/skill/

# Landing page (TSX + Tailwind)
python3 product-team/landing-page-generator/scripts/landing_page_scaffolder.py config.json --format tsx

Related Projects

ProjectDescription
**Claude Code Skills & Agents Factory**Methodology for building skills at scale
**Claude Code Tresor**Productivity toolkit with 60+ prompt templates
**Product Manager Skills**Senior PM agent with 6 knowledge domains, 12 templates, 30+ frameworks — discovery, strategy, delivery, SaaS metrics, career coaching, AI product craft
**toprank**9 SEO and Google Ads skills for Claude Code — connects Google Search Console, PageSpeed Insights, and Google Ads API; ships meta tag, schema markup, and keyword bid fixes to source or CMS. MIT, 107 stars

FAQ

How do I install Claude Code plugins? Add the marketplace with /plugin marketplace add alirezarezvani/claude-skills, then install any skill bundle with /plugin install <name>@claude-code-skills.

Do these skills work with OpenAI Codex / Cursor / Windsurf / Aider / Mistral Vibe? Yes. Skills work natively with 13 tools: Claude Code, OpenAI Codex, Gemini CLI, OpenClaw, Hermes Agent, Mistral Vibe, Cursor, Aider, Windsurf, Kilo Code, OpenCode, Augment, and Antigravity. Hermes Agent and Mistral Vibe both use the same agentskills.io SKILL.md standard — run python scripts/sync-hermes-skills.py or ./scripts/vibe-install.sh to install. For other tools run ./scripts/convert.sh --tool all then ./scripts/install.sh --tool <name>. See Multi-Tool Integrations for details.

Will updating break my installation? No. We follow semantic versioning and maintain backward compatibility within patch releases. Existing script arguments, plugin source paths, and SKILL.md structures are never changed in patch versions. See the CHANGELOG for details on each release.

Are the Python tools dependency-free? Yes. All 579 Python CLI tools use the standard library only — zero pip installs required. Every script is verified to run with --help.

How do I create my own Claude Code skill? Each skill is a folder with a SKILL.md (frontmatter + instructions), optional scripts/, references/, and assets/. See the Skills & Agents Factory for a step-by-step guide.


Contributing

We welcome contributions! See CONTRIBUTING.md for guidelines.

Quick ideas:

  • Add new skills in underserved domains
  • Improve existing Python tools
  • Add test coverage for scripts
  • Translate skills for non-English markets

License

MIT — see LICENSE for details.


Star History

![Star History Chart](https://star-history.com/#alirezarezvani/claude-skills&Date)


Built by [Alireza Rezvani](https://alirezarezvani.com) · Medium · Twitter

Install & Usage

1
Create the agents directory
mkdir -p .claude/agents
2
Save the agent file

Add the configuration to .claude/agents/self-improving-agent.md

3
Invoke with @agent-name
@self-improving-agent

Use Cases

Automatically review recent code changes and suggest improvements based on past learnings stored in memory.
Promote a key insight or best practice discovered during a coding session into CLAUDE.md for future reference.
Extract a recurring pattern or workflow from your codebase into a reusable skill that can be invoked later.
Check the current status of stored memories and learnings to understand what the agent has retained.
Manually remember a specific fact or instruction so the agent can recall it in future sessions.
Analyze your codebase to identify patterns that should be formalized as skills or rules.

Usage Examples

1

/si:review Review the last 10 commits and suggest improvements based on our coding standards.

2

/si:promote The rule that all API endpoints must validate input using Zod should be added to CLAUDE.md.

3

/si:extract Extract the pattern for setting up a new React component with tests into a skill called 'react-component-setup'.

View source on GitHub
code-reviewagentmemoryauto-memoryself-improvementlearning

Security Audits

LicenseUnknownSourceWarnRepositoryPass

Frequently Asked Questions

What is self-improving-agent?

The self-improving-agent skill enables Claude Code to curate its own memory by promoting learnings to CLAUDE.md and rules, and extracting patterns into reusable skills. It ships five slash commands and two sub-agents to automate code review insights, memory management, and skill extraction, making your coding agent continuously smarter over time.

How to install self-improving-agent?

To install self-improving-agent: create the agents directory (mkdir -p .claude/agents), then add the config to .claude/agents/self-improving-agent.md. Finally, @self-improving-agent in Claude Code.

What is self-improving-agent best for?

self-improving-agent is a agent categorized under Development. It is designed for: code-review, agent, memory, auto-memory, self-improvement, learning. Created by Alireza Rezvani.

What can I use self-improving-agent for?

self-improving-agent is useful for: Automatically review recent code changes and suggest improvements based on past learnings stored in memory.; Promote a key insight or best practice discovered during a coding session into CLAUDE.md for future reference.; Extract a recurring pattern or workflow from your codebase into a reusable skill that can be invoked later.; Check the current status of stored memories and learnings to understand what the agent has retained.; Manually remember a specific fact or instruction so the agent can recall it in future sessions.; Analyze your codebase to identify patterns that should be formalized as skills or rules..