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.
46,700 skills from 2,243 repositories · updated 3 hours ago
10,031 skills
- pm-techkonglong87/superPMUse when: 需要与技术团队对接技术方案、评估技术可行性、制定技术架构、评估第三方服务 Do NOT use when: 技术方案已由技术团队确定、仅需功能描述无需技术评估OtherNo warnings★ 84↓ —
- pm-brand-motionkonglong87/superPMUse when: 需要为品牌设计动效方向、制作 logo 动画 demo、定义品牌动效性格、从静态 logo 到动态展示的过渡 Do NOT use when: 需要专业级动效交付（应交给设计师）、已有成品动效无需方向验证、仅需要文字描述不需要 demoOtherNo warnings★ 84↓ —
- graceful-degradationparcadei/Continuous-Claude-v3Graceful Degradation with Helpful MessagesOtherNo warnings★ 3.9K↓ —Also in 1 other repo
- next-moveEncod3d-Sec/TORCHRanked next offensive moves from engagement state. Reads state/loot/Killchain, runs the deterministic analyzer, elaborates the top move. Use when asked "what next", "where to focus", "prioritize", or at the start of an engagement session.OtherNo warnings★ 335↓ —
- search-toolsparcadei/Continuous-Claude-v3Search Tool HierarchyOtherNo warnings★ 3.9K↓ —
- hunt-cacheEncod3d-Sec/TORCHWeb cache poisoning + cache deception hunting - unkeyed input poisoning, cache-key analysis, path-confusion deception, header/parameter cloaking. Wiki-first, FIND schema output.OtherNo warnings★ 335↓ —
- redteamleadEncod3d-Sec/TORCHOn-demand senior red-team lead advisor. Call at a decision point or obstacle to get wiki-grounded direction instead of hammering blindly. Dispatches a fresh RTL subagent that reads the engagement state + evidence + wiki and returns ranked directions with an explicit STOP. Use for "redteamlead", "RTL", "I'm stuck", "where do I go", "what next", "which vector", "should I keep hammering this".OtherNo warnings★ 335↓ —
- camp-projectsObedience-Corp/festivalManage a camp's projects. Use when committing inside `projects/*`, deciding status/pull/push scope (root vs submodule vs all), or creating/removing project worktrees.OtherNo warnings★ 88↓ —Also in 3 other repos
- leann-searchparcadei/Continuous-Claude-v3Semantic search across codebase using LEANN vector indexOtherNo warnings★ 3.9K↓ —
- reading-payment-statementkazukinagata/shinkoku支払調書の画像を読み取り構造化データを返す。 他のスキルから呼び出されるほか、直接ユーザーが呼び出すことも可能。OtherNo warnings★ 366↓ —
- llm-tuning-patternsparcadei/Continuous-Claude-v3LLM Tuning PatternsOtherNo warnings★ 3.9K↓ —Also in 1 other repo
- codebase-inspectionHezaoHezao/poirotInspect codebases: LOC, languages, ratios via pygount.OtherNo warnings★ 256↓ —
- async-repl-protocolparcadei/Continuous-Claude-v3Async REPL ProtocolOtherNo warnings★ 3.9K↓ —Also in 1 other repo
- agent-orchestrationparcadei/Continuous-Claude-v3Agent Orchestration RulesOtherNo warnings★ 3.9K↓ —Also in 1 other repo
- bmod-alphaalvin-reyes/better-agentic-ideBetter Agentic Development EnvironmentOtherNo warnings★ 85↓ —
- environment-triageparcadei/Continuous-Claude-v3Environment TriageOtherNo warnings★ 3.9K↓ —Also in 1 other repo
- github-repo-managementHezaoHezao/poirotClone, create, fork repos; manage remotes, releases.OtherNo warnings★ 256↓ —
- compound-learningsparcadei/Continuous-Claude-v3Transform session learnings into permanent capabilities (skills, rules, agents). Use when asked to "improve setup", "learn from sessions", "compound learnings", or "what patterns should become skills".OtherNo warnings★ 3.9K↓ —Also in 1 other repo
- bmad-build-autoalvin-reyes/better-agentic-ideOne iteration of an unattended development loop. Use when invoked by nameOtherNo warnings★ 85↓ —Also in 1 other repo
- 1c-db-listDesko77/claude-code-skills-1cУправление реестром баз данных 1С (.v8-project.json). Используй когда пользователь говорит про базы данных, список баз, "добавь базу", "какие базы есть"OtherNo warnings★ 86↓ —
- arch-ai-strategyalvin-reyes/better-agentic-ideAI Automation Strategist: Decide what to automate: opportunity mapping, ROI, build vs buy, rollout and change management.OtherNo warnings★ 85↓ —
- skill-upgraderparcadei/Continuous-Claude-v3Upgrade any skill to v5 Hybrid format using decision theory + modal logicOtherNo warnings★ 3.9K↓ —Also in 1 other repo
- bmod-methodalvin-reyes/better-agentic-ideRequired bmod metadata. Never invoke this skill.OtherNo warnings★ 85↓ —Also in 1 other repo
- create-handoffparcadei/Continuous-Claude-v3Create handoff document for transferring work to another sessionOtherNo warnings★ 3.9K↓ —
mandarin-rhyme
cxcscmu/SkillLearnBench
OtherUpdated Oct 2, 2026
From the author
Rules for rhyming in poetry based on modern Mandarin (Pinyin).
Install
npx skills add cxcscmu/SkillLearnBench --skill mandarin-rhyme -a claude-code
Installs to .claude/skills/mandarin-rhyme/ · Each command fetches the skill straight from GitHub with the open skills CLI.
Download .zip
Byte-identical to the scanned commit, with the repository’s licence and a SOURCE.txt.
What it can touch
Instructions onlyNo network use seenLicence: MIT
Safety checks on SKILL.md
No warnings.
Why 83
Security100
Provenance64
Maintenance100
Licence100
Adoption34
Files (1)
- SKILL.md