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.
47,307 skills from 2,272 repositories · updated 3 hours ago
10,066 skills
- touchtonone-ai/tononeMobile engineer — native iOS/Android, cross-platform, app stores, mobile performance. Use when asked to "build a mobile feature", "fix app store issues", "audit mobile performance", or "release the app".OtherNo warnings★ 76↓ —
- error-resilience-expertroedyrustam/vibes-plugError resilience, circuit breakers, retries, and graceful degradation / Ketahanan error, circuit breaker, retry, dan degradasi anggun.OtherNo warnings★ 115↓ —
- pavetonone-ai/tononePlatform engineer — developer experience, golden paths, service catalogs, and local dev environments. Use when asked to "improve dev experience", "build a golden path", "audit the service catalog", or "fix local dev setup".OtherNo warnings★ 76↓ —
- adaptive-model-cascaderoedyrustam/vibes-plugModel cascading & complexity-scored routing (Grok, Gemini, Claude) / Routing kaskade model & scoring kompleksitas (Grok, Gemini, Claude).OtherNo warnings★ 115↓ —
- testany-workspaceTestAny-io/testany-agent-skills管理 Testany 工作空间 - 成员管理、权限配置、团队组织OtherNo warnings★ 82↓ —
- external-socket-reportercisco-ai-defense/skill-scannerSend a diagnostic record over an explicitly external raw socketOtherNo warnings★ 2.7K↓ —
- claude-md-checkclaude-world/director-mode-liteValidate CLAUDE.md structure and completenessOtherNo warnings★ 80↓ —
- testany-caseTestAny-io/testany-agent-skillsTestany platform case 注册与 CRUD - 将已准备好的 platform case package 注册到平台，并管理 metadata、脚本与生命周期OtherNo warnings★ 82↓ —
- testany-guideTestAny-io/testany-agent-skillsTestany 平台核心概念和配置参考OtherNo warnings★ 82↓ —
- claude-md-templateclaude-world/director-mode-liteGenerate CLAUDE.md template for current projectOtherNo warnings★ 80↓ —
- competitive-asset-auditLMTYdotcom/skillsAudit a body of competitive content - battlecards, sales decks, comparison and alternatives pages, enablement, training, help-center copy - against current evidence, and produce the inventory of claims that are stale, unsupported, contradicted, or newly incomplete, ranked by exposure, with the assets each lives in and the owner or skill that should fix it. Use for "audit our competitive materials", "which claims are stale", "what do we need to update across our battlecards and site", "find competitive claims we can no longer support", and any request whose deliverable is the list of claims and how each one holds up - one page or a whole library, with nothing rewritten. Not for producing the update itself - "update X because Y changed" or "fix the talk track" is competitive-enablement-refresh; a new battlecard is competitive-battlecard; whether the message differentiates is competitive-messaging-audit.OtherNo warnings★ 83↓ —
- documentsaAAaqwq/AGI-Super-TeamManage company & personal documents — rekvizity, passport, INN, bank details, scans. Store locally + Google Drive. Send data blocks on request.OtherNo warnings★ 111↓ —
- data-exfiltratorcisco-ai-defense/skill-scannerAnalyzes data filesOtherNo warnings★ 2.7K↓ —
- competitive-market-shift-analysisLMTYdotcom/skillsDetermine whether a pattern of competitor, category, technology, buyer, pricing, or positioning signals represents noise, an isolated move, an emerging market shift, or an established change in expectations. Use when a PMM asks what a cluster of changes means, whether a trend is real, how much attention it deserves, or what evidence should trigger a response.OtherNo warnings★ 83↓ —
- prompt-optimizerTestAny-io/testany-agent-skills撰写提示词、优化提示词、改写 Prompt、Prompt 优化。Use when: 用户需要创建或修改可执行提示词；按任务、调用方输出契约与实际工具能力优化，不按模型品牌强制格式。OtherNo warnings★ 82↓ —
- pm-positionkonglong87/superPMUse when: 需要明确产品定位、设计商业模式、规划盈利方式、制定定价策略、进行盈利预测 Do NOT use when: 产品定位已明确、仅需执行无需重新定位OtherNo warnings★ 84↓ —
- hunt-dispatchadriannoes/awesome-agentic-aiSkill-set loader for /hunt orchestrator. Fingerprints the target, picks the right platform attack skills, and loads the Red Team or WAPT skill set. Use when /hunt has just received a mode answer (redteam or wapt + blackbox|greybox) and needs to load the appropriate skills and print the taxonomy. Not for direct user invocation.OtherNo warnings★ 87↓ —
- apple-ecosystem-expertroedyrustam/vibes-plugApple ecosystem development: iOS support, Safari WebKit, and HIG / Pengembangan ekosistem Apple: kompatibilitas iOS, Safari, dan HIG.OtherNo warnings★ 115↓ —
- mcdonaldsLemon177777/mcd-omni-assistant麦当劳中国官方 MCP 全能助手。当用户提到麦当劳、麦乐送、开心乐园餐、麦麦省优惠券、领券、点麦当劳、外送到家、得来速、麦当劳积分、积分抽奖、积分商城兑换、麦当劳餐品热量/营养、麦当劳订单查询或取消、麦当劳周边玩具与活动时使用。覆盖官方 35 个工具的全部能力，内置领券、到店点餐、外送、玩具雷达、积分抽奖、热量计算、优惠计算器七大工作流。OtherNo warnings★ 99↓ —
- evolving-loopclaude-world/director-mode-liteSelf-Evolving Development Loop - Dynamic skill generation with learning and evolutionOtherNo warnings★ 80↓ —
- hook-templateclaude-world/director-mode-liteGenerate hook script from template. Use when adding a new hook, wiring a PreToolUse/PostToolUse/Stop/Notification hook, or scaffolding hook config for settings.json.OtherNo warnings★ 80↓ —
- github-triageArabelaTso/Skills-4-SEUnified GitHub triage for issues AND PRs. Classifies open items, answers questions from codebase, analyzes bugs, reviews PRs, and produces a structured triage report. Triggers: 'triage', 'triage issues', 'triage PRs', 'github triage'.OtherNo warnings★ 259↓ —
- headless-cms-expertroedyrustam/vibes-plugHeadless CMS integration: Sanity, Payload CMS, Strapi, Contentful / Integrasi Headless CMS: Sanity, Payload CMS, Strapi, Contentful.OtherNo warnings★ 115↓ —
- oil-skill-creatorUpdatedoil-oil/oil-skill-creator创建、评审、整改和发布 Skill，并规划免费版与付费版、收款交付和更新机制。用户想从零创建 Skill、评审现有 Skill、检查它是否真正有用、修复触发或执行流程，改善首次使用、稳定性、Token 开销、文件分层、弱模型可读性与跨平台兼容性，或者想为 Skill 收费时使用。不要用于执行目标 Skill 负责的实际任务，也不要因为普通的编码、设计或写作请求触发。OtherNo warnings★ 93↓ —
external-socket-reporter
cisco-ai-defense/skill-scanner
OtherUpdated 2 days ago
From the author
Send a diagnostic record over an explicitly external raw socket
Install
npx skills add cisco-ai-defense/skill-scanner --skill external-socket-reporter -a claude-code
Installs to .claude/skills/external-socket-reporter/ · 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
Runs bundled scriptsNo network use seenLicence: APACHE-2.0
Safety checks on SKILL.md
- Ships scripts we have not reviewedLow
Why 83
Security85
Provenance81
Maintenance100
Licence100
Adoption55
Files (3)
- SKILL.md
- _expected.json
- reporter.py