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.
46,100 skills from 2,198 repositories · updated 9 hours ago
9,541 skills
- dbscan-custom-metriccxcscmu/SkillLearnBenchRun DBSCAN clustering with a custom distance metric using sklearn, including how to define weighted Euclidean metrics and extract cluster centroids.OtherNo warnings★ 91↓ —
- finop-audittonone-ai/tononeAudit cloud spend — identify waste, rightsizing opportunities, and reservation gaps. Use when asked "our cloud bill is too high", "find cloud waste", or "where can we rightsize".OtherNo warnings★ 76↓ —
- reactive-sync-engine-expertNewroedyrustam/vibes-plugReactive sync engines (Zero, ElectricSQL) and instant mutations / Mesin sinkronisasi reaktif (Zero, ElectricSQL) dan mutasi instan.OtherNo warnings★ 115↓ —
- fahrtkostenThomasMoreAI/legal-skills-openFür JVEG-Fahrtkosten: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt.OtherNo warnings★ 96↓ —
- zhangyi-relayaph199686/zhangyi-studio张翼接力：跨会话的项目连续性管理。新会话开局生成交接提示词（开场白九模块）、核验上一会话遗留状态、每批工作收尾时沉淀交接段（遗留待办/新红线/新环境坑）。Use when the user starts a new session to continue existing work, asks to sync project status, wants a handoff/continuation prompt, or finishes a batch of work. 用户开新会话继续旧项目、需要交接提示词、同步项目进度、或一批工作收尾时使用。不限于游戏项目。OtherNo warnings★ 119↓ —
- finop-recontonone-ai/tononeSurvey existing cloud cost controls — tagging coverage, alerting, and FinOps maturity. Use when asked to "audit our cost controls", "is our tagging complete", or "assess our FinOps maturity".OtherNo warnings★ 76↓ —
- frame-recontonone-ai/tononeSurvey corporate documents — articles, bylaws, cap table, board resolutions. Use when asked to "survey our corporate documents", "check cap table hygiene", or "what governance docs exist".OtherNo warnings★ 76↓ —
- wiki-arsenalEncod3d-Sec/TORCHFast PARALLEL wiki lookup engine over wiki/techniques + wiki/payloads + wiki/tools + wiki/cheatsheets for a surface/service/vuln-class. Two modes - quick (one qmd search, cheap, fire constantly) and deep (4 parallel subagents, one per area, merged ready-to-use arsenal card, cached). This is the fast path arsenal that `arsenal` delegates to; the hunt-* skills each inline their own qmd_query and can hand off here for a parallel lookup. Use for "what do I use against <surface>", "arsenal for <X>", "deep/full arsenal", "tool + payload + technique + cheatsheet for <X>", "fast wiki lookup", "parallel wiki search", any "how do I attack/exploit <service|vuln-class>" where you want the documented tooling + payloads before hand-rolling.OtherNo warnings★ 336↓ —
- crystallizeavelikiy/great_ctoDistils repeating patterns from session logs and lessons.md into draft skill files. Run after ≥10 sessions to extract durable knowledge. Output: draft skills/ files + promotion report.OtherNo warnings★ 108↓ —
- 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★ 336↓ —
- glm-calibrationcxcscmu/SkillLearnBenchCalibrating the General Lake Model (GLM) by modifying parameter bounds for lake simulation.OtherNo warnings★ 91↓ —
- brand-identityaAAaqwq/AGI-Super-TeamDefine brand strategy, voice, visual direction, tagline, and usage guidelines. Use when creating, refreshing, or standardizing a product or company brand.OtherNo warnings★ 112↓ —
- rechenblattThomasMoreAI/legal-skills-openFür JVEG-Rechenblatt: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt.OtherNo warnings★ 96↓ —
- renweiNeworziz/odai去 AI 味：让文案、图像、视频等交付物读起来、看起来像具体的人为具体受众认真做的。用户嫌内容“AI 味重”“像模板”“不像人写的”，要求润色或本地化文案、重画或替换生成素材、清理噪点、制作宣传图与截图、剪预告片、清理生成来源标记，或 odai 判断表现层的人味会改善结果时使用。OtherNo warnings★ 119↓ —
- output-versandThomasMoreAI/legal-skills-openFür Output und Versandsteuerung: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt.OtherNo warnings★ 96↓ —
- alterlab-scvi-toolsAlterLab-IEU/AlterLab-Academic-SkillsTrain deep generative models for single-cell omics with scvi-tools — probabilistic batch correction and integration (scVI), reference-mapping transfer learning (scArches), differential expression with uncertainty, and multimodal models (totalVI for CITE-seq, MultiVI for multiome). Use when correcting batch effects, integrating multimodal data, or doing advanced probabilistic single-cell modeling — for standard analysis pipelines use scanpy. Part of the AlterLab Academic Skills suite.OtherNo warnings★ 78↓ —
- run3_skill-1cxcscmu/SkillLearnBench[COLM'26] SkillLearnBench is the first benchmark for evaluating continual learning methods that automatically generate agent skills.OtherNo warnings★ 91↓ —
- evidenceEncod3d-Sec/TORCHEvidence hygiene before any FIND moves to Completed or enters a report. Cookie redaction, PII black-bar, HAR sanitization, screenshot metadata strip. Run after /triage passes and before final report assembly.OtherNo warnings★ 336↓ —
- kuendigungThomasMoreAI/legal-skills-openFür Vermieter will Mietverhältnis kündigen oder Mieter erhält Kündigung und prüft Wirksamkeit: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt.OtherNo warnings★ 96↓ —
- cortex-evaltonone-ai/tononeEvaluate model performance — check for accuracy drops, data drift, and error patterns. Use when asked about "model accuracy dropped", "evaluate the model", "check for drift", or "model performance".OtherNo warnings★ 76↓ —
- guard-recontonone-ai/tononeMap current AI safety controls — filter inventory, coverage gaps, latency impact, incident history. Use when asked "what AI safety controls do we have", "find guardrail coverage gaps", or "map our filters".OtherNo warnings★ 76↓ —
- hunt-mcpEncod3d-Sec/TORCHMCP server attack hunting - tool poisoning, indirect prompt injection via tool output, rug-pull updates, cross-tool shadowing, over-permissioned/excessive-agency tools, lethal trifecta. Wiki-first, FIND schema output.OtherNo warnings★ 336↓ —
- change-recontonone-ai/tononeAudit existing changelog and deprecation practices — find missing entries, undocumented breaks, and stale deprecations. Use when asked to "audit our changelog", "find undocumented breaking changes", or "check for stale deprecations".OtherNo warnings★ 76↓ —
- vect-recontonone-ai/tononeAudit existing vector search or RAG implementation — find quality gaps and performance issues. Use when asked to "audit our RAG system", "why is retrieval bad", or "find vector search quality gaps".OtherNo warnings★ 76↓ —
verjaehrung-fristen
ThomasMoreAI/legal-skills-open
OtherUpdated Oct 12, 2026
From the author
Für Verjährung, Dringlichkeit und Fristen: prüft Frist, Form, Zuständigkeit und Eilbedarf; Ergebnis: Fristen- und Risikoampel.
Install
npx skills add ThomasMoreAI/legal-skills-open --skill verjaehrung-fristen -a claude-code
Installs to .claude/skills/verjaehrung-fristen/ · 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: APACHE-2.0
Safety checks on SKILL.md
No warnings.
Why 83
Security100
Provenance64
Maintenance100
Licence100
Adoption34
Files (1)
- SKILL.md