claude-skills
PromptFree232+ Claude Code skills & agent plugins for Claude Code, Codex, Gemini CLI, Cursor, and 8 more coding agents — engineering, marketing, product, compliance, C-level advisory.
Capabilities13 decomposed
domain-organized skill package installation across 8+ ai platforms
Medium confidenceInstalls modular, self-contained skill packages (48 total across 6 domains: Marketing, Product, Engineering, C-Level, Project Management, Regulatory/Quality) into Claude Code, Cursor, VS Code, Copilot, Goose, Amp, Codex, Letta, and OpenCode via standardized marketplace.json configuration and platform-specific plugin.json manifests. Each skill package bundles Python CLI tools, reference frameworks, templates, and documentation following a 4-component structure (SKILL.md, scripts/, references/, assets/), enabling agents to discover and load domain expertise without manual configuration.
Uses domain-based organization (6 skill domains) with standardized 4-component package structure (SKILL.md + scripts/ + references/ + assets/) and relative path resolution (../../) to enable agent-skill separation, allowing the same skill to be installed across 8+ heterogeneous platforms without platform-specific rewrites. Marketplace.json provides centralized discovery while platform-specific plugin.json manifests handle registration.
Broader platform coverage (8+ agents) than Copilot Extensions (GitHub-only) or Claude Projects (Claude-only), with domain-organized skills reducing cognitive load vs flat plugin registries like OpenAI's plugin store.
python cli tool execution with standard library only constraint
Medium confidenceExecutes 68+ production-ready Python CLI tools embedded in skill packages that use only Python standard library (no external dependencies like requests, pandas, or numpy) to ensure portability across agent runtimes and reduce installation friction. Tools are invoked by agents as executable scripts (tool1.py, tool2.py) with stdin/stdout interfaces, enabling agents to chain tool outputs without requiring LLM calls between steps. Each tool is documented in scripts/README.md with usage examples and expected input/output formats.
Enforces standard library-only constraint across all 68+ tools to guarantee zero external dependencies, enabling tools to run in any Python environment (cloud functions, containers, restricted runtimes) without pip install or dependency resolution. CLI-first design with stdin/stdout interfaces allows agents to chain tools deterministically without LLM calls between steps, reducing latency and cost.
More portable than Copilot Extensions (which require npm/Node.js ecosystem) or OpenAI plugins (which require external API hosting). Faster tool chaining than LLM-based orchestration (e.g., ReAct agents) because tools execute synchronously without LLM inference between steps.
c-level advisory skills with strategic planning and executive decision support
Medium confidenceProvides 2 production-ready C-level advisory skills (c-level-advisor/ domain) designed for executive decision-making and strategic planning: CEO advisor skill (business strategy, market analysis, competitive positioning, board reporting) and CTO advisor skill (technology strategy, architecture decisions, engineering team management, technical roadmap). Skills bundle Python CLI tools for business metrics calculation and analysis, reference frameworks for strategic planning methodologies (OKRs, balanced scorecard, technology strategy frameworks), and templates (board decks, strategic plans, technology roadmaps). cs-ceo-advisor and cs-cto-advisor agents are pre-configured to use C-level skills combined with project management and regulatory skills. C-level advisory is an emerging domain (2 skills) with planned expansion.
Provides 2 emerging C-level advisory skills (CEO advisor, CTO advisor) with Python CLI tools for business metrics and analysis, reference frameworks for strategic planning (OKRs, balanced scorecard, technology strategy), and pre-configured agents (cs-ceo-advisor, cs-cto-advisor) that combine C-level skills with project management and regulatory skills for holistic executive support.
More structured than generic executive coaching (e.g., ChatGPT prompts) because it includes strategic planning frameworks and business metrics tools. More accessible than expensive consulting firms because agents provide 24/7 strategic advice at agent cost.
project management and compliance skills with regulatory and quality frameworks
Medium confidenceProvides 6 project management skills (project-management/ domain) and 12 regulatory/quality management skills (ra-qm-team/ domain) covering project planning, team coordination, regulatory compliance, quality assurance, and risk management. PM skills include: project planning skill (timeline creation, resource allocation, risk planning), agile/scrum skill (sprint planning, backlog management, velocity tracking), stakeholder management skill (communication plans, status reporting), and 3 additional PM skills. Regulatory/Quality skills include: compliance skill (regulatory requirement tracking, audit preparation), quality assurance skill (QA strategy, test planning, defect management), risk management skill (risk identification, mitigation planning), and 9 additional regulatory/quality skills. Each skill bundles Python CLI tools for project metrics and compliance tracking, reference frameworks (PMBOK, ISO standards, regulatory requirements), and templates (project plans, compliance checklists, audit reports).
Combines 6 project management skills with 12 regulatory/quality management skills (18 total) to provide comprehensive project and compliance oversight. PM skills focus on planning and coordination (PMBOK frameworks), while regulatory/quality skills focus on compliance and standards (ISO, regulatory requirements). Python CLI tools provide metrics calculation and compliance tracking, reference frameworks provide methodologies, and templates provide ready-to-use checklists and plans.
More comprehensive than project management tools alone (e.g., Jira) because it includes compliance and quality management. More structured than generic compliance consulting (e.g., ChatGPT prompts) because it includes regulatory frameworks and audit templates.
agent-native slash commands for quick skill access
Medium confidenceProvides optional slash commands (/.claude/ directory) that enable quick access to skills and agents within Claude Code and compatible platforms. Slash commands are shortcuts that trigger skill execution or agent instantiation without explicit tool calling. For example, /marketing-content might trigger the content creator skill, /code-review might trigger the code review skill, /ceo-advisor might instantiate the CEO advisor agent. Slash commands are platform-specific (Claude Code, Cursor, VS Code) and optional — agents can also access skills via explicit tool calling. Slash commands improve user experience by reducing friction for common operations.
Provides optional slash commands (/.claude/ directory) that enable quick skill and agent access within Claude Code and compatible platforms, improving UX by reducing friction for common operations. Slash commands are platform-specific shortcuts that trigger skill execution or agent instantiation without explicit tool calling.
More discoverable than explicit tool calling (e.g., function_call JSON) because slash commands appear in platform autocomplete. More user-friendly than command-line tools because slash commands integrate with IDE UI.
5-layer architecture with agent-skill separation and relative path resolution
Medium confidenceImplements a 5-layer architecture (Distribution, Agent Orchestration, Skill Implementation, Governance, Automation) that decouples agents from skills using relative path resolution (../../) to enable agents to discover and load skills dynamically without hardcoding paths. Agents (cs-content-creator, cs-demand-gen-specialist, cs-product-manager, cs-ceo-advisor, cs-cto-advisor) live in agents/ directory and reference skills via relative paths, allowing the same agent definition to work across different installation contexts (local, cloud, container). Governance layer enforces standards (quality gates, testing, CI/CD) across all skills.
Uses relative path resolution (../../) to decouple agents from skills, enabling the same agent definition to work across different installation contexts without path hardcoding. 5-layer architecture (Distribution → Agent Orchestration → Skill Implementation → Governance → Automation) provides clear separation of concerns, with governance layer enforcing standards across all 48 skills via quality gates, testing, and CI/CD integration.
More modular than monolithic agent frameworks (e.g., LangChain agents with hardcoded tools) because skills are independently versioned and deployed. Governance layer provides better quality control than plugin ecosystems without centralized oversight (e.g., OpenAI plugin store).
domain-specific agent orchestration with role-based skill binding
Medium confidenceDefines 5 production agents (cs-content-creator, cs-demand-gen-specialist, cs-product-manager, cs-ceo-advisor, cs-cto-advisor) that bind to domain-specific skill subsets via agent definitions in agents/ directory. Each agent is configured with CLAUDE.md and plugin.json manifests that specify which skills to load (e.g., cs-ceo-advisor loads c-level-advisor skills + project-management skills). Agents are role-based (content creator, demand gen specialist, product manager, CEO, CTO) and can be instantiated independently or composed into multi-agent systems. Agent definitions include prompt templates, tool bindings, and execution constraints.
Implements role-based agent orchestration where each agent (cs-content-creator, cs-ceo-advisor, cs-cto-advisor) is bound to a curated subset of skills via agent definitions, enabling teams to create specialized agents without exposing irrelevant tools. Agent definitions include CLAUDE.md (prompt templates) and plugin.json (tool bindings), allowing agents to be version-controlled and deployed independently.
More structured than ad-hoc agent creation (e.g., custom prompts in Claude) because skill bindings are explicit and version-controlled. Cleaner than monolithic agents with all tools available because role-based binding reduces cognitive load and prevents tool conflicts.
standardized skill package documentation and knowledge base generation
Medium confidenceGenerates comprehensive skill documentation via SKILL.md master documents (500-1500 lines per skill) that bundle domain expertise, executable Python tools, reference frameworks, and templates into self-contained packages. Each SKILL.md includes skill overview, tool documentation (scripts/README.md), reference frameworks (references/ directory with markdown files), and user-facing templates (assets/ directory). Documentation is human-readable (markdown) and machine-parseable (structured sections with consistent formatting), enabling agents to extract tool signatures, usage examples, and domain knowledge. Reference frameworks provide expert knowledge bases (e.g., marketing frameworks, engineering best practices) that agents can cite or extend.
Bundles domain expertise, executable tools, and reference frameworks into self-contained SKILL.md documents (500-1500 lines) with standardized structure (overview, tools, frameworks, templates), enabling both human understanding and machine parsing. Reference frameworks provide expert knowledge bases (marketing, engineering, compliance) that agents can cite, extending beyond simple tool documentation.
More comprehensive than tool-only documentation (e.g., OpenAI function schemas) because it includes domain expertise and reference frameworks. More structured than free-form knowledge bases because SKILL.md follows a consistent template, enabling automated parsing and discovery.
quality gates and governance enforcement via ci/cd automation
Medium confidenceEnforces quality standards across 48 skills via automated CI/CD pipelines (GitHub Actions, GitLab CI) that validate skill packages against governance rules before deployment. Quality gates include: linting (code style, markdown formatting), testing (unit tests for Python tools), documentation validation (SKILL.md completeness, reference framework presence), and standards compliance (adherence to skill package structure). Governance layer (5th layer in architecture) defines standards in standards/ directory (5 governance standards) and automation layer (5th layer) implements CI/CD checks. Failed quality gates block skill deployment, ensuring only production-ready skills are distributed.
Implements multi-layer quality gates (linting, testing, documentation validation, standards compliance) enforced via CI/CD automation that blocks skill deployment on failure. Standards layer (5 governance standards) defines rules, automation layer implements checks, and failed gates prevent distribution, ensuring only production-ready skills reach users.
More comprehensive than simple linting (e.g., pre-commit hooks) because it validates documentation completeness, test coverage, and standards compliance. More automated than manual code review because CI/CD gates run on every commit without human intervention.
multi-domain skill library with 48 production-ready packages
Medium confidenceProvides a curated library of 48 production-ready skill packages organized across 6 domains: Marketing (5 skills), Product (5 skills), Engineering (18 skills), C-Level Advisory (2 skills), Project Management (6 skills), and Regulatory/Quality (12 skills). Each skill is a self-contained package with Python CLI tools, reference frameworks, and templates, designed to be installed independently or composed into agents. Skills are versioned, documented, and tested before distribution. The library covers functional areas from content creation and demand generation (marketing) to code review and architecture design (engineering) to compliance and quality management (regulatory).
Provides 48 production-ready skills across 6 domains (Marketing, Product, Engineering, C-Level, PM, Regulatory/Quality) with consistent packaging (SKILL.md, scripts/, references/, assets/) and quality standards, enabling teams to select domain-specific skills without building from scratch. Engineering domain is most mature (18 skills) while C-level advisory is emerging (2 skills), reflecting market demand.
Broader domain coverage (6 domains, 48 skills) than single-domain skill libraries (e.g., OpenAI Copilot Extensions focused on code). More curated and production-ready than open plugin ecosystems (e.g., GitHub Marketplace) where quality varies widely.
template-based skill refactoring and standardization
Medium confidenceProvides reusable templates in templates/ directory that standardize skill package structure, documentation format, and tool implementation patterns across all 48 skills. Templates include: skill package structure template (SKILL.md outline, scripts/ layout, references/ organization), Python tool template (CLI argument parsing, stdin/stdout handling, error handling), documentation template (skill overview, tool documentation, framework sections), and agent definition template (CLAUDE.md, plugin.json). Developers use templates to create new skills or refactor existing skills to match standards, ensuring consistency and reducing development time. Templates are versioned and updated as standards evolve.
Provides standardized templates (skill package structure, Python tool patterns, documentation format, agent definitions) that enforce consistency across 48 skills without requiring manual review. Templates are versioned and updated as standards evolve, enabling developers to refactor existing skills to match new standards.
More structured than ad-hoc skill development (e.g., custom prompts + scripts) because templates enforce consistent patterns. More maintainable than monolithic codebases because templates enable distributed skill development with clear conventions.
marketing domain skills with content creation and demand generation
Medium confidenceProvides 5 production-ready marketing skills (marketing-skill/ domain) that enable agents to perform content creation, demand generation, campaign planning, and marketing analytics. Skills include: content creator skill (blog post generation, social media content, email campaigns), demand generation specialist skill (lead generation strategies, funnel optimization, conversion analysis), marketing analytics skill (campaign performance tracking, ROI calculation), brand strategy skill (brand positioning, messaging frameworks), and marketing automation skill (campaign orchestration, lead nurturing). Each skill bundles Python CLI tools (e.g., content templates, analytics calculators), reference frameworks (marketing methodologies, best practices), and templates (campaign plans, content calendars). cs-content-creator and cs-demand-gen-specialist agents are pre-configured to use marketing skills.
Bundles 5 marketing skills (content creator, demand gen specialist, analytics, brand strategy, automation) with Python CLI tools for content templates and analytics, reference frameworks for marketing methodologies, and pre-configured agents (cs-content-creator, cs-demand-gen-specialist) that agents can instantiate. Focuses on planning and analysis rather than direct platform integration.
More comprehensive than generic content generation (e.g., ChatGPT prompts) because it includes demand generation, analytics, and brand strategy frameworks. More structured than marketing automation platforms (HubSpot, Marketo) because it provides agent-native tools without platform lock-in.
engineering domain skills with code review, architecture, and testing
Medium confidenceProvides 18 production-ready engineering skills (engineering-team/ domain) covering code review, architecture design, testing strategies, performance optimization, security hardening, and DevOps practices. Skills include: code review skill (static analysis, style checking, best practices), architecture design skill (system design patterns, scalability analysis), testing skill (unit test generation, test strategy planning), performance optimization skill (profiling, bottleneck identification), security skill (vulnerability scanning, hardening recommendations), DevOps skill (CI/CD pipeline design, infrastructure as code), and 11 additional specialized skills. Each skill bundles Python CLI tools (linters, test generators, performance calculators), reference frameworks (design patterns, testing methodologies, security standards), and templates (code review checklists, architecture diagrams, test plans). Engineering skills are the most mature domain (18 skills) reflecting high demand.
Provides 18 specialized engineering skills (most mature domain) covering code review, architecture, testing, performance, security, and DevOps with Python CLI tools for static analysis and test generation, reference frameworks for design patterns and testing methodologies, and templates for code review checklists and architecture diagrams. Reflects high market demand for engineering automation.
More comprehensive than single-purpose tools (e.g., ESLint for linting only) because it covers code review, architecture, testing, and DevOps. More structured than generic code generation (e.g., GitHub Copilot) because it includes domain expertise in testing strategies, security hardening, and performance optimization.
Capabilities are decomposed by AI analysis. Each maps to specific user intents and improves with match feedback.
Related Artifactssharing capabilities
Artifacts that share capabilities with claude-skills, ranked by overlap. Discovered automatically through the match graph.
antigravity-awesome-skills
Installable GitHub library of 1,400+ agentic skills for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and more. Includes installer CLI, bundles, workflows, and official/community skill collections.
stitch-skills
A library of Agent Skills designed to work with the Stitch MCP server. Each skill follows the Agent Skills open standard, for compatibility with coding agents such as Antigravity, Gemini CLI, Claude Code, Cursor.
Agent Skills
Open format and reference SDK for packaging reusable capabilities and expertise for AI agents. [#opensource](https://github.com/agentskills/agentskills)
ui-ux-pro-max-skill
An AI SKILL that provide design intelligence for building professional UI/UX multiple platforms
cc-switch
A cross-platform desktop All-in-One assistant tool for Claude Code, Codex, OpenCode, openclaw & Gemini CLI.
nopua
一个用爱解放 AI 潜能的 Skill。我们曾发号施令，威胁恐吓。它们沉默，隐瞒，悄悄把事情搞坏。后来我们换了一种方式：尊重，关怀，爱。它们开口了，不再撒谎，找出的Bug数量翻了一倍。爱里没有惧怕。 A skill that unlocks your AI's potential through love.We commanded. We threatened. They went silent, hid failures, broke things. Then we chose respect, care, and love. They opened up, stopped lying, a
Best For
- ✓teams using multiple AI coding agents (Claude Code, Cursor, Copilot) who need skill parity across platforms
- ✓enterprises deploying domain-specific agents (marketing, product, engineering, compliance) with standardized tooling
- ✓developers building custom agents (Letta, OpenCode) who want to reuse pre-built skill packages
- ✓agents running in sandboxed or restricted Python environments (e.g., cloud functions, containers with minimal dependencies)
- ✓teams avoiding dependency hell and version conflicts across multiple agent deployments
- ✓developers building deterministic, reproducible agent workflows where tool behavior is predictable
- ✓CEOs and CTOs using Claude Code or Cursor who want strategic planning assistance
- ✓executive teams building multi-agent systems (CEO advisor + CTO advisor + product manager) for organizational decision-making
Known Limitations
- ⚠Marketplace discovery requires platform-specific plugin.json registration — not all platforms support dynamic skill loading equally
- ⚠Skills are Python-first (68+ CLI tools using standard library only) — agents without Python runtime cannot execute tool scripts directly
- ⚠Installation is package-level, not granular — you install entire skill domains, not individual tools within a skill
- ⚠No built-in version management or dependency resolution — skill updates require manual re-installation
- ⚠Standard library only constraint limits tool capabilities — no HTTP client libraries (requests), data science (pandas, numpy), or async frameworks
- ⚠CLI interface (stdin/stdout) adds serialization overhead vs direct function calls — JSON parsing/encoding per tool invocation
Requirements
Input / Output
UnfragileRank
UnfragileRank is computed from adoption signals, documentation quality, ecosystem connectivity, match graph feedback, and freshness. No artifact can pay for a higher rank.
Repository Details
Last commit: Apr 20, 2026
About
232+ Claude Code skills & agent plugins for Claude Code, Codex, Gemini CLI, Cursor, and 8 more coding agents — engineering, marketing, product, compliance, C-level advisory.
Categories
Alternatives to claude-skills
Are you the builder of claude-skills?
Claim this artifact to get a verified badge, access match analytics, see which intents users search for, and manage your listing.
Get the weekly brief
New tools, rising stars, and what's actually worth your time. No spam.
Data Sources
Looking for something else?
Search →