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.
32,113 skills from 1,400 repositories · updated 14 minutes ago
6,969 skills
- backlink-gap-analysissandbaseai/sandbase-skillsFind and prioritize ethical backlink and digital-PR opportunities using SandBase DataForSEO backlink data. Use when asked to analyze backlink profiles, find referring-domain gaps, compare link competitors, or prepare a link-outreach target list.OtherNo warnings★ 201↓ —
- iso-24495-1GaZmagik/iso-24495Core Plain Language standard (ISO 24495-1:2023). Governs all user-facing responses to ensure clear, structured, findable, understandable, and actionable output.OtherNo warnings★ 200↓ —
- content-performancesandbaseai/sandbase-skillsAnalyze content performance across YouTube, TikTok, Instagram, and Twitter to identify what works. Compares engagement rates, format effectiveness, posting cadence impact, and audience response patterns across platforms for content strategy optimization.OtherNo warnings★ 201↓ —
- cash-flow-snapshotsandbaseai/sandbase-skillsCreate a 30/60/90-day cash-flow forecast from AR, AP, opening cash, payment timing, and fixed-cost data. Use when asked about runway, payroll coverage, liquidity risks, or a near-term cash crunch.OtherNo warnings★ 201↓ —
- dbs-knowledgeskillmds/skillmddontbesilent 文件夹知识库。把用户已有的本地文件夹变成 Agent 能稳定查找、收录和维护的知识库；用户没有资料时建立最小知识库，有资料时生成知识库导航，后续支持放入新资料、查找答案、识别当前版本、检查知识库、精确更新导航，以及对膨胀的知识库导航进行瘦身和分层治理。用户提到「搭建知识库」「我的文件夹就是知识库」「让 AI 读懂这些文件」「把资料放进知识库」「从知识库找东西」「更新知识库」「更新知识库导航」「优化 SOT」「SOT 太大」「瘦身 Source of Truth」「知识库导航太长」「把明细下沉到 README」「刚才的文件加入知识库」「这条路径写错了」「把这个设为最新版」「哪个文件是最新版」「资料太乱」「建立 Source of Truth」时都应使用。用户无需理解 Source of Truth、RAG 或 Agent 配置。 Folder-based knowledge base for AI agents. Use whenever the user wants to build, populate, query, organize, audit, slim, or connect a local folder as a knowledge base, including source-of-truth navigation, layered indexing, and version resolution.OtherNo warnings★ 190↓ —
- retroskillmds/skillmdRun a full retrospective and dev cycle analysis. Chains /recall → /new-features to reconstruct what went wrong, extract lessons learned, identify rework patterns, and synthesize feature ideas from the findings. Triggers: retrospective, retro, dev cycle analysis, what went wrong, lessons learned, postmortem, sprint retro.OtherNo warnings★ 190↓ —
- secret-management-patternsvibeeval/vibecosystemHashiCorp Vault, cloud secret managers, rotation strategies, and zero-trust secret accessOtherNo warnings★ 540↓ —
- file-assistantGoldziher/ai-rulezHelps with data and files of all kinds.OtherNo warnings★ 163↓ —
- iso-24495-styleGaZmagik/iso-24495Hold every response to the ISO 24495 plain-language rules, and route to the sector skills. Codex has no output style, so these rules are a skill.OtherNo warnings★ 200↓ —
- scikit-survival-analysisjaechang-hits/SciAgent-SkillsTime-to-event modeling with scikit-survival: Cox PH (elastic net), Random Survival Forests, Boosting, SVMs for censored data. C-index, Brier, time-dependent AUC; Kaplan-Meier, Nelson-Aalen, competing risks. Pipeline/GridSearchCV compatible. Use statsmodels for frequentist, pymc for Bayesian, lifelines for parametric.OtherNo warnings★ 382↓ —
- tech-radar-patternsvibeeval/vibecosystemThoughtWorks Radar model, technology evaluation framework, ADR format, and stack compatibility analysisOtherNo warnings★ 540↓ —
- prometheus-patternsvibeeval/vibecosystemPromQL queries, alerting rules, recording rules, Grafana dashboard JSON, SLOOtherNo warnings★ 540↓ —
- harvest-competitivevibeeval/vibecosystemCompetitive intelligence - extract features, pricing, tech stack from competitor sitesOtherNo warnings★ 540↓ —
- developer-relationsvibeeval/vibecosystemDeveloper relations - community building, documentation, DevRel metrics.OtherNo warnings★ 540↓ —
- vector-db-patternsvibeeval/vibecosystemEmbedding strategies, ANN algorithms, hybrid search, RAG chunking strategies, and reranking for semantic search and retrieval.OtherNo warnings★ 540↓ —
- prompt-engineeringvibeeval/vibecosystemPrompt templates, few-shot examples, chain-of-thought, structured output, evalsOtherNo warnings★ 540↓ —
- nw-jtbd-corenWave-ai/nWaveCore JTBD theory and job story format - job dimensions, job story template, job stories vs user stories, 8-step universal job map, outcome statements, and forces of progressOtherNo warnings★ 622↓ —Also in 1 other repo
- experiment-enginevibeeval/vibecosystemOtonom deney dongusu. Kod degisikligi yap, olc, karsilastir, kabul et veya geri al. Metrik bazli karar verme ile performans, boyut veya kalite optimizasyonu. Tek basina veya agent ile kullan.OtherNo warnings★ 540↓ —
- data-visualizationskillmds/skillmdGráficos profesionales con Matplotlib, Seaborn, Plotly — del exploratorio al publicable. Elige el gráfico correcto para cada historia. Trigger: Cuando necesitás crear gráficos, visualizar datos, o generar charts para análisis o presentaciones.OtherNo warnings★ 190↓ —
- mongodb-patternsvibeeval/vibecosystemDocument modeling, aggregation pipeline, indexing strategy, change streams, and multi-document transactions.OtherNo warnings★ 540↓ —
- system-overviewvibeeval/vibecosystemShow how vibecosystem works - agents, skills, hooks, and self-learning pipeline.OtherNo warnings★ 540↓ —
- skill-evolutionvibeeval/vibecosystemSelf-evolving skill system. Skills are scored after execution (0-100) on 5 dimensions. Score 90+ over 5 runs = crystallized (locked). Score below 30 = auto-repair attempted. Skills improve themselves through usage feedback.OtherNo warnings★ 540↓ —
- md-formatGoldziher/ai-rulezFormat markdown with prettier.OtherNo warnings★ 163↓ —
- harvest-monitorvibeeval/vibecosystemWeb change monitoring - track changes on pages, detect updates, changelog diffsOtherNo warnings★ 540↓ —