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.
48,168 skills from 2,325 repositories · updated 3 hours ago
6,204 skills
- orca-cliaiskillstore/marketplaceOperate Orca-managed worktrees, folder contexts, terminals, repos, automations, artifacts, skill sharing, worktree comments, and Orca's embedded browser through the `orca` CLI. Use when the user says "$orca-cli", "Orca worktree", "child worktree", "spawn codex/claude in a worktree", "read/wait/send Orca terminal", "handoff" / "handover" / "give this to another agent", "Orca browser", "orca artifacts", or "share skills". Prefer it over raw git worktree, ad hoc PTYs, or Computer Use when Orca state is involved. Use Computer Use only when a visible window needs GUI control that a CLI, filesystem, or API cannot do.EngineeringNo warnings★ 450↓ —Also in 1 other repo
- commit-message-generatorelisaterumi-ai/agent-skills-in-practiceGenerates standardized and meaningful commit messages following best practices. Use when writing or improving commit messages.EngineeringNo warnings★ 131↓ —
- herdraiskillstore/marketplaceControl Herdr, a terminal multiplexer for coding agents. Use only when the user explicitly mentions Herdr or asks to use Herdr to inspect or control panes, tabs, workspaces, commands, or another agent. Do not use merely because a task could benefit from a background terminal, delegation, or parallel work. Requires HERDR_ENV=1.EngineeringNo warnings★ 450↓ —
- debuggeraiskillstore/marketplace버그 원인을 시스템 로그 기반으로 특정하고 수정·검증·정리까지 완료하는 디버깅 워크플로우 스킬. 트리거: '디버깅해줘', '버그 원인 찾아줘', '어디서 오류나는지', '로그 삽입해줘', 에러 메시지/스택 트레이스 붙여넣기, '--pw'/'--pw --headless'/'--pw --record' 플래그. 지원 언어: JS/TS, Python, Java, Kotlin. 안티-트리거: 단순 코드 리뷰, 신규 기능 구현, 원인이 이미 특정된 경우(수정만 진행), 성능 최적화, 기능 동작 검증/시나리오 PASS-FAIL 판정.EngineeringNo warnings★ 450↓ —
- rpg-stat-catalystkennyzir/7deer_skillsA core TypeScript library for RPG game mathematics. Handles attribute points, leveling curves, and stat derivation (HP, Dmg, etc.).EngineeringNo warnings★ 333↓ —
- review-agentaiskillstore/marketplacePerform a read-only, defect-first review of a specified code change and return every actionable finding. Use when another agent delegates review of uncommitted changes, a base-branch diff, a commit, or custom review instructions.EngineeringNo warnings★ 450↓ —
- commitaiskillstore/marketplaceHelps write conventional commit messages, create atomic commits, and follow git best practices. Use when the agent needs to help with git commits, commit message writing, or git workflow guidance.EngineeringNo warnings★ 450↓ —
- mcp-buildercomposio-community/awesome-claude-pluginsGuide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).EngineeringNo warnings★ 2K↓ —
- antfuaiskillstore/marketplaceAnthony Fu's opinionated tooling and conventions for JavaScript/TypeScript projects. Use when setting up new projects, configuring ESLint/Prettier alternatives, monorepos, library publishing, or when the user mentions Anthony Fu's preferences.EngineeringNo warnings★ 450↓ —
- claude-apilingxling/awesome-skills-cnReference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST EngineeringNo warnings★ 327↓ —
- sealeap-baize-amazon-blue-ocean-validationxjli360/sealeap-amazon-skillsValidate whether an apparent Amazon blue-ocean opportunity is driven by durable differentiated demand or by price, promotion, review, variation, or off-platform distortions. Use for 蓝海选品、低评论高销量、新品异军突起、差异化机会、真假蓝海. This is a pre-screen, not a sourcing decision.EngineeringNo warnings★ 340↓ —
- post-code-review-to-prtestdouble/hanRun a full pull request review and post review comments directly to the current branch's GitHub PR. Requires the gh CLI to be installed and a PR to already exist for the current branch. Use when you want review feedback posted to GitHub as PR comments. For local code review without posting to GitHub, use code-review instead. Does not write or update PR descriptions — use update-pr-description for that.EngineeringNo warnings★ 331↓ —
- sealeap-pixiu-amazon-operator-review-inventoryxjli360/sealeap-amazon-skills聚焦库存管理、Featured Offer、站外流量的 Amazon 跨境经营复盘。在需要将经验判断转成可验证的问题，识别适用前提、替代解释和可迁移的经营动作时使用；根据当前业务问题选择证据卡，避免加载无关主题。EngineeringNo warnings★ 340↓ —
- codexqa-rootcause-analyzeropenqa-cn/codexqaDiagnoses exception root causes from stack traces, logs, call-chain dumps, and debug output using the CodexQA CLI for structured repo analysis. Use when the user mentions codexqa-rootcause-analyzer, exception RCA, crash analysis, AI code diagnosis, stack diagnosis, 异常根因, 堆栈诊断, 崩溃分析, 异常诊断, or asks to turn an exception into a root-cause report. Not structure/impact analysis (that is codexqa-code-analyzer), not SAST + Agent LLM Detection code-risk scan reports (that is codexqa-defect-analyzer), and not CodexQA evidence-pack HTML review (that is codexqa-code-reviewer). Former skill name: root-cause-diagnosis.EngineeringNo warnings★ 236↓ —
- api-skillaiskillstore/marketplaceUpdated API skillEngineeringNo warnings★ 450↓ —
- codexqa-defect-analyzeropenqa-cn/codexqaAI defect detection and code-risk scanning for engineering projects. Use when the user asks for AI defect detection, code-risk scan, review a diff/MR/PR/commit (incremental), baseline-scan a repository (full), OR upload/paste code snippets for adhoc defect detection. Combines two detection dimensions — (1) deterministic SAST/lint/secrets/SCA and (2) one-round Agent LLM Detection by the invoking agent's embedded model (no separate LLM API key) — then dedupes and merges them into the final report. Delivers structured findings ordered by severity (P0–P3) via report_scan.json / report_scan.md / report_scan.html. Do NOT use to apply or autofix code style/formatting — lint may still surface hygiene findings. Code-graph / call-chain MUST use CodexQA CLI for all languages (references/codexqa-cli.md) — never homemade analyzers. Not CodexQA evidence-pack HTML review (that is codexqa-code-reviewer), not structure/impact mapping (that is codexqa-code-analyzer), and not exception RCA (that is codexqa-rootcause-analyzer). EngineeringNo warnings★ 236↓ —
- codexqa-code-revieweropenqa-cn/codexqaGraph-evidence AI code review (codexqa-code-reviewer) for ANY language repo using ONLY the CodexQA CLI symbol graph (call chains, classes, methods, configs, blast radius, test edges), then an order-16 Agent LLM judgment pass by the host agent's embedded model with deterministic dedupe/merge against heuristic findings. Use when the user asks for codexqa-code-reviewer (former name ai-code-reviewer), code review, PR review, 代码评审, impact analysis, 影响面, regression scope, test gaps, full-repo health review, 全仓评审, CodexQA evidence-pack, 证据包, graph-backed review, or LLM semantic CR on a pack. Requires codexqa CLI for every language; never embeds CodexQA source; never substitutes git-diff-only analysis. Not SAST+agent scan reports (that is codexqa-defect-analyzer), not structure/impact mapping alone (that is codexqa-code-analyzer), and not exception RCA (that is codexqa-rootcause-analyzer).EngineeringNo warnings★ 236↓ —
- codexqa-code-wikiopenqa-cn/codexqaBuilds a local architecture wiki for a repository from the CodexQA symbol graph (no model needed): modules, who calls whom and how often, reading paths, and one self-contained HTML page. Use when the user mentions codexqa-code-wiki, code-wiki, wiki, knowledge graph, architecture wiki, module map, reading guide, 代码知识图谱, 架构 Wiki, 模块地图, 阅读导览, wiki inputs, --no-llm, community detection, 社区检测, HTML 报告, or asks to map modules / generate a repo wiki without an LLM. Not change review (that is codexqa-code-analyzer), not CodexQA evidence-pack HTML review (that is codexqa-code-reviewer), and not SAST+agent code-risk scan reports (that is codexqa-defect-analyzer). Former skill name: code-wiki.EngineeringNo warnings★ 236↓ —
- ghNewaiskillstore/marketplacePatterns for invoking the GitHub CLI (gh) from agents. Covers structured output, pagination, repo targeting, search vs list, gh api fallback.EngineeringNo warnings★ 450↓ —
- sealeap-amazon-negative-review-responsexjli360/sealeap-amazon-skillsTriage negative Amazon reviews into policy violations, suspected abuse, and genuine product feedback, then prepare factual official reports and product-remediation actions. Use when the user asks whether a review can be removed, how to report abusive content, or how to respond to a rating decline. Never fabricate evidence, contact reviewers off-platform, or incentivize review changes.EngineeringNo warnings★ 340↓ —
- zach-feature-demand-validatorzach22-1999/amazon-skills功能需求真伪验证器。用三维数据（Review/关键词/社区）验证微创新是否真实需求。 使用时机：品类选定后评估微创新、竞品分析发现差异点后判断要不要跟进。 触发词：/zach-feature-demand-validatorEngineeringNo warnings★ 246↓ —
- foundation-build-risk-reviewproduct-on-purpose/pm-skillsRuns a fast pre-build risk review on a product idea, feature request, or scope change, naming the single assumption most likely to make it fail and returning a clear verdict (build small, validate first, pivot first, or don't build yet) with a no-code validation step. Use before committing build effort, when triaging whether to honor a feature request, or when deciding whether to expand scope, ahead of writing a PRD. For a launched product's pivot-or-persevere decision, use iterate-pivot-decision instead.EngineeringReview first★ 774↓ —
- python-agent-enginekennyzir/7deer_skillsA production-ready Python AI Agent engine using LangChain. Supports ReAct pattern, tool calling, and thinking process tracking.EngineeringNo warnings★ 333↓ —
- perf-code-pathscomposio-community/awesome-claude-pluginsUse when mapping code paths, entrypoints, and likely hot files before profiling.EngineeringNo warnings★ 2K↓ —