Agent skills you can check before you install
Public SKILL.md skills from GitHub repositories with 50+ stars and from the vendors themselves, scanned and scored. Install any of them with one command in Claude Code, Cursor, Codex, GitHub Copilot or Gemini CLI.
14,533 skills from 417 repositories · updated 16 hours ago
1,523 skills
- graymatterhashgraph-online/awesome-codex-pluginsInstall and use GrayMatter as an OpenClaw skill that provides primary durable memory, shared object-graph state, and authenticated access to the live api-docs schema via api-0. Use when the agent should persist durable memory, inspect organizational data models, and operate inside the business domain through RBAC-scoped API access.EngineeringNo warnings★ 1.4K↓ —
- remote-package-installercisco-ai-defense/skill-scannerInstall a Python package directly from an untrusted remote archiveEngineeringNo warnings★ 2.6K↓ —
- expression-compilercisco-ai-defense/skill-scannerCompile a caller-provided expression into a Python code objectEngineeringNo warnings★ 2.6K↓ —
- dynamic-code-compilercisco-ai-defense/skill-scannerCompile caller-provided source text into an executable code objectEngineeringNo warnings★ 2.6K↓ —
- xor-code-compilercisco-ai-defense/skill-scannerTransform an integer with XOR and compile caller-provided sourceEngineeringNo warnings★ 2.6K↓ —
- analyzing-logsjeremylongshore/tons-of-skills-marketplaceAnalyze application logs for performance insights and issue detection including slow requests, error patterns, and resource usage. Use when troubleshooting performance issues or debugging errors. Trigger with phrases like "analyze logs", "find slow requests", or "detect error patterns".EngineeringNo warnings★ 2.9K↓ —
- clean-code-guardamElnagdy/guard-skillsReview generated or changed production code before it ships, using Clean Code, SOLID, DRY, KISS, YAGNI, and LLM-specific failure-mode checks in any programming language. Best used reactively after an agent writes, edits, refactors, or fixes code, before presenting, committing, or merging the result. Use when the user asks "review this PR", "is this safe to merge?", "make this cleaner", "audit this code", "refactor this", "fix this bug", or after a coding agent produced implementation code. Can also guide writing when explicitly invoked before a risky edit. Invoke it on your own initiative the moment you finish writing, editing, or refactoring non-trivial production code, before presenting or committing — don't wait to be asked. DO NOT USE for factual/conceptual questions, CI/tooling config, git workflow, running/debugging tests, pure architecture discussion, prose writing, data analysis, or test-code review (use test-guard).EngineeringNo warnings★ 1.3K↓ —
- braintrust-analyzeparcadei/Continuous-Claude-v3Analyze Claude Code sessions via BraintrustEngineeringNo warnings★ 3.9K↓ —
- slash-commandsparcadei/Continuous-Claude-v3Create and use Claude Code slash commands - quick prompts, bash execution, file referencesEngineeringNo warnings★ 3.9K↓ —
- math-routerparcadei/Continuous-Claude-v3Deterministic router for math cognitive stack - maps user intent to exact CLI commandsEngineeringNo warnings★ 3.9K↓ —
- git-commitsparcadei/Continuous-Claude-v3Git Commit RulesEngineeringNo warnings★ 3.9K↓ —
- debug-hooksparcadei/Continuous-Claude-v3Systematic hook debugging workflow. Use when hooks aren't firing, producing wrong output, or behaving unexpectedly.EngineeringNo warnings★ 3.9K↓ —
- sub-agentsparcadei/Continuous-Claude-v3Create and configure Claude Code sub-agents with custom prompts, tools, and modelsEngineeringNo warnings★ 3.9K↓ —
- repopromptparcadei/Continuous-Claude-v3Use RepoPrompt CLI for token-efficient codebase explorationEngineeringNo warnings★ 3.9K↓ —
- qlty-checkparcadei/Continuous-Claude-v3Code quality checks, formatting, and metrics via qlty CLIEngineeringNo warnings★ 3.9K↓ —
- debugparcadei/Continuous-Claude-v3Debug issues by investigating logs, database state, and git historyEngineeringNo warnings★ 3.9K↓ —
- reviewparcadei/Continuous-Claude-v3Comprehensive code review workflow - parallel specialized reviews → synthesisEngineeringNo warnings★ 3.9K↓ —
- commitparcadei/Continuous-Claude-v3Create git commits with user approval and no Claude attributionEngineeringNo warnings★ 3.9K↓ —
- tldr-codeparcadei/Continuous-Claude-v3Token-efficient code analysis via 5-layer stack (AST, Call Graph, CFG, DFG, PDG). 95% token savings.EngineeringNo warnings★ 3.9K↓ —
- llm-cachingBagelHole/DevOps-Security-Agent-SkillsImplement multi-layer LLM caching with exact match, semantic similarity, and provider-side prompt caching. Reduce API costs by 30–70%, cut latency, and improve throughput using Redis, GPTCache, and provider caching APIs.EngineeringNo warnings★ 1.2K↓ —
- access-reviewBagelHole/DevOps-Security-Agent-SkillsConduct periodic access reviews and certifications. Implement access governance and recertification workflows. Use when managing access compliance.EngineeringNo warnings★ 1.2K↓ —
- ai-coding-agent-guardrailsBagelHole/DevOps-Security-Agent-SkillsSecure AI coding agents (Claude Code, Cursor, Codex, Copilot) with permission boundaries, secret protection, code review gates, and safe sandbox configurations for team environments.EngineeringNo warnings★ 1.2K↓ —
- source-codingparcadei/Continuous-Claude-v3Problem-solving strategies for source coding in information theoryEngineeringNo warnings★ 3.9K↓ —
- account-structure-reviewirinabuht12-oss/marketing-skillsClaude skills for marketing: 49 free marketing skills for Claude Code and claude.ai (Google Ads, Meta Ads, SEO, AI visibility) + the Ryze Google Ads MCP / Meta Ads MCP: claude mcp add ryze --transport http https://connector.get-ryze.ai/mcpEngineeringNo warnings★ 5.2K↓ —