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.
47,938 skills from 2,309 repositories · updated 19 minutes ago
10,102 skills
- budget-recontonone-ai/tononeMap AI cost topology — billing attribution, team-level spend, forecast vs actuals, alert gaps. Use when asked to "map our AI spend", "who is spending on LLMs", or "set up AI cost attribution".OtherNo warnings★ 77↓ —
- telegram-checkaAAaqwq/AGI-Super-TeamCheck inbound Telegram messagesOtherNo warnings★ 112↓ —
- github-issue-analysiscxcscmu/SkillLearnBenchAnalyze GitHub issues for a date range, counting totals, bug reports (by label substring), and closed bug reports.OtherNo warnings★ 91↓ —
- run3_skill-1cxcscmu/SkillLearnBench[COLM'26] SkillLearnBench is the first benchmark for evaluating continual learning methods that automatically generate agent skills.OtherNo warnings★ 91↓ —
- 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↓ —
- scope-recontonone-ai/tononeSurvey project IP assets — trademarks, patents, OSS licenses, assignments. Use when asked to "survey our IP assets", "what trademarks do we hold", or "inventory our IP".OtherNo warnings★ 77↓ —
- rss-automationaAAaqwq/AGI-Super-TeamRSS feed aggregation and monitoring. Parse RSS/Atom feeds, filter entries, track new items, and integrate with notification channels for automated content monitoring.OtherNo warnings★ 112↓ —
- run2_schedulercxcscmu/SkillLearnBenchAn improved scheduling algorithm to find the earliest compatible free slots under time constraints.OtherNo warnings★ 91↓ —
- abstract-domain-explorerArabelaTso/Skills-4-SEApplies abstract interpretation using different abstract domains (intervals, octagons, polyhedra, sign, congruence) to statically analyze program variables and infer invariants, value ranges, and relationships. Use when analyzing program properties, inferring loop invariants, detecting potential errors, or understanding variable relationships through static analysis.OtherNo warnings★ 260↓ —
- create-projectaAAaqwq/AGI-Super-TeamCreate new project with breakdownOtherNo warnings★ 112↓ —
- fabric-patternaAAaqwq/AGI-Super-TeamIntegrate Daniel Miessler's Fabric patterns into local workflows for structured prompting, text transformation, and retrieval-assisted processing.OtherNo warnings★ 112↓ —
- run2_time-formattingcxcscmu/SkillLearnBenchFormat dates and times with strict adherence to required formatsOtherNo warnings★ 91↓ —
- run2_ca-small-claimscxcscmu/SkillLearnBenchComprehensive field mapping for California SC-100 Small Claims Court form with field IDs and filling guidance.OtherNo warnings★ 91↓ —
- apex-profiletonone-ai/tononeScope the tonone agent roster for this project — install a curated subset of agents instead of the full 100-agent bundle. Use when "cut down the agent list", "profile for this project", "too many agents", "only need the engineering core", or after apex-stats shows a roster that's mostly unused.OtherNo warnings★ 77↓ —
- glm-netcdf-analysiscxcscmu/SkillLearnBenchExtracting and analyzing GLM NetCDF output to compute RMSE against field observations using exact datetime+depth matching.OtherNo warnings★ 91↓ —
- llm-tuning-patternsparcadei/Continuous-Claude-v3LLM Tuning PatternsOtherNo warnings★ 3.9K↓ —Also in 1 other repo
- whatsapp-sendaAAaqwq/AGI-Super-TeamBaileys WhatsApp message sendingOtherNo warnings★ 112↓ —
- bau-vob-agbThomasMoreAI/legal-skills-openFür Bau VOB/B AGB: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt.OtherNo warnings★ 97↓ —
- mandarin-rhymecxcscmu/SkillLearnBenchRules for rhyming in poetry based on modern Mandarin (Pinyin).OtherNo warnings★ 91↓ —
- tianyancha-cnaAAaqwq/AGI-Super-Team企业信息查询 - 天眼查/企查查/爱企查数据查询（Bloomberg 终端中国版）OtherNo warnings★ 112↓ —
- work-to-skillaAAaqwq/AGI-Super-Team工作即技能：每次完成一项有复用价值的工作后，自动评估并封装为可复用 Skill。让团队在工作中持续进化。OtherNo warnings★ 112↓ —
- d3-interactive-chartscxcscmu/SkillLearnBenchD3.js techniques for tooltips, hover effects, click handlers, and cross-filtering between visualizationsOtherNo warnings★ 91↓ —
- matter-fileThomasMoreAI/legal-skills-openFür Deal-Akte: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt. Fachgebiet: Großkanzlei Corporate/M&A.OtherNo warnings★ 97↓ —
- budget-audittonone-ai/tononeAudit AI spend — per-model cost breakdown, top consumers, waste identification, optimization levers. Use when asked "why is our AI bill so high", "audit LLM spend", or "where is our token waste".OtherNo warnings★ 77↓ —
kv-cache-prefix-optimizer
roedyrustam/vibes-plug
OtherUpdated 16 hours ago
From the author
Expert guide for deterministic prompt prefix engineering, KV-cache locking for Gemini 4 Pro / Claude 5.5 / GPT Astra 6, canonical tool sorting, and achieving 90%+ prompt cache hit rates / Panduan ahli rekayasa prefix prompt deterministik, penguncian KV-cache untuk Gemini 4 Pro / Claude 5.5 / GPT Astra 6, pengurutan kanonikal tool, dan pencapaian 90%+ cache hit rate.
Install
npx skills add roedyrustam/vibes-plug --skill kv-cache-prefix-optimizer -a claude-code
Installs to .claude/skills/kv-cache-prefix-optimizer/ · 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
Provenance65
Maintenance100
Licence100
Adoption36
Files (1)
- SKILL.md