Claude skill that assesses whether a task is ready for an autonomous /goal loop, then writes the /goal completion contract and rider - or refuses with a readiness verdict

An enterprise-grade, multi-specialist engineering audit plugin for Claude Code.

Claude/agent skill: local events data for AI agents, as structured JSON. Installs via npx skills add.

Claude/agent skill: stage-filtered investor outreach lists with partner contacts and check sizes. Installs via npx skills add.

Claude Code skills that turn OpenAI's Codex CLI into an orchestrated, cost-optimized agent fleet — conducted by Claude. Cross-provider multi-agent workflows with model tiering and verify loops.

React/Vue/TS 前端重构 Agent Skills（行为不变重构、拆文件、绞杀者迁移）

Agent Skills for exchangerate.dev — FX rates API. Currency conversion, FX correctness, portfolio translation, multi-currency pricing. Works keyless.

Written by Fable, for models that aren't — context frameworks that lift Opus/Sonnet-class agents to Fable-grade work discipline.

Universal, agent-agnostic skills for coding agents. Measure first, fix the real constraint, never delete without approval.

Unified dynamic-host agent collaboration policy and signed-runtime client

For solo freelancers: position, productize, price, and run client work like a business.

Free AI supply chain security checks for GitHub repos — right from a Claude conversation

A meta-skill that builds bespoke ideation-coach as a skill for any creative domain — writing, visual art, music, design, collage, poetry, research, or anything where someone captures rough ideas and wants structured help developing them instead of merely automating the process.

Audits real Claude Code usage for effort/model waste — reuses ccusage for raw data, adds the judgment layer it can't provide.

Claude Agent Skill: end-of-session memory audit

The prompt formulary for Claude: symptoms, remedies, exact dosages. Official Anthropic prompting best practices as an Agent Skill.

An Agent Skill that gives your AI agent offline access to Zeal docs on Linux

Claude skill: 連動禁區防護 — analyze a codebase for 'change A, break B' high-risk zones and write guardrails into CLAUDE.md

Run Claude Code as a teammate that owns work end to end. A maintained CLAUDE.md (works as AGENTS.md) plus a plan/execute/review skill pipeline with external verification, adversarial review, and structurally safe parallel execution. Dated changelog, updated when model behaviour changes.

Claude Code plugin marketplace for the hard, production-critical parts of engineering — backend reliability (API contracts, idempotency, rate limiting, resilience, caching, auth), adversarial code review, and frontend motion/UX.

Make your AI agent argue visually. Universal skill pack for Excalidraw diagrams across Claude Code, Cursor, Codex, Gemini CLI, and any MCP-compatible agent.

Intraagent instruction, skill, and config manager for Claude and Codex

AI devops for vibe coders

OpenTelemetry onboarding for Sematext Cloud — reference examples shipping traces, metrics, and logs across multiple languages, an end-to-end multi-service tracing demo, and an open-source AI skill that walks engineers through the setup.

Version control and evolution for AI agent skills — versioned storage, dynamic serving/loadouts, multi-agent git sync, and cross-repo federation.

An Anthropic Agent Skill that enables agents to generate Python code for calling undocumented AWS APIs using AWS Signature Version 4 authentication.

🧪 Provide expert Swift Testing guidance with best practices for XCTest, async tests, parallel execution, and seamless Agent Skills integration.

Runs severity-ranked engineering audits and executes approval-gated refactors to raise prototype code to production quality.

An AI-powered noise suppression and defect triage agent addressing an industry-wide gap in observability of data integration platforms. It enriches alerts with execution context, failed components, downstream dependency impact, and LLM-summarized notifications.

Agent Skills for d9 (Directus 9 fork) — install with: npx skills add LaWebcapsule/d9-skills

Official Claude Code skill for Dock0, the platform for deploying and monetizing MCP servers.

Stop AI agents from writing useless tests. Decision trees for mocking, test layering, and requirement-driven testing that catches real bugs.

Agent Skill for LPM — teaches AI assistants how to create, publish, and manage LPM packages

A curated marketplace of open Agent Skills (SKILL.md) — the real skills I use day to day, compatible with the open skills ecosystem.

Explains automated tests in business language and reviews automation quality, coverage, and traceability.

AI agents are smart but unreliable without procedure. "Agent Skills" are executable checklists that package expertise.

CLI to pull Agent Skills anywhere, anytime

Provide software design guidance based on John Ousterhout’s principles to improve code quality, architecture, and maintainability during development.

Agent Skills para Cursor & Claude Code: revisão crítica + APIs Bun/Elysia/Drizzle/Zod — padrões que o chat não “inventa” de novo a cada conversa.

Agent skills for EVM Copilot — competitive intelligence for the EVM ecosystem

A.I. Smart-Router — Intelligent model routing for multi-provider AI setups. Auto-selects optimal models using tiered classification with fallback chains and cost optimization.

AI Agent Skills for Web Scraping, Proxy Management, and Automation | Compatible with Claude Code, Cursor, Copilot, and all AgentSkills-compatible agents | Install: npx skills add luis2404123/birdproxies-skills

A curated collection of reusable agent skills for the gh-aw GitHub Actions workflow toolkit.

Analyzes requirements and use cases for ambiguity, testability, delivery risk, and missing stakeholder decisions.

A lightweight package manager for AI agent skills.

Guides defects from intake to verified fix with failing confirmation tests, scoped remediation, and structured resolution reporting.

Melxis Toolkit — One mind. Many AIs. Connect your AI clients to coupled memory and tasks.

Securely back up and restore encrypted data for OpenClaw agent systems with Avenger Initiative.

Reviews and improves BDD and Gherkin scenarios with coaching on traceability, coverage gaps, and Given-When-Then quality.

AI agent skills organized as a virtual development team for software development

OpenCLAW persistent memory skill with multi-agent isolation, vector search, and context inheritance.

Repository of skills I use

One command for every skill you need.

Custodian: autonomous operations monitor — detects, classifies, and repairs agent platform failures during quiet hours.

Authorized defensive AppSec review skill for repositories, APIs, CI/CD, IaC, and AI systems with findings-first output.