Agent skills

Other skills

Read straight from the source repositories, not from submitted listings. Every skill shows what it does, what is inside, where it came from — and whether attention around its source is actually growing.

Toolclaude-code 62,644codex 9,699cursor 6,852copilot 2,269windsurf 126cline 82
CategoryWorkflow & Productivity 11,684AI & Agents 4,965Data & Analytics 4,693Code Review & Quality 2,936Security 2,762Backend & API 2,480Design & Presentation 2,329Documentation 2,157Content & Marketing 2,001Testing & QA 1,723DevOps & Cloud 1,266Databases 1,124Frontend 1,015Business & Finance 706Media & Video 507Other 21,420
21,420 found
4,8014,848 · page 101 / 447
synthesizerUse when multiple reviews or paper notes need integration, cross-cutting themes must be identified, or project-specific…majiayu000synthesizing-vocUse when you have customer feedback files (transcripts, tickets, surveys) and need to identify themes and opportunities without…majiayu000sys-tracking-goalsMonitors active goals against current state. Calculates gaps, scores urgency, detects at-risk goals, generates alerts. Reads…majiayu000writesSystem DiagnosticianPerforms Codex-assisted project health diagnostics, identifies capability gaps, and produces prioritized improvement plans.majiayu000system2-attentionSystem 2 attention mechanisms for deliberate, slow reasoning in transformermajiayu000system2-attentionSystem 2 attention mechanisms for deliberate, slow reasoning in transformer architectures.majiayu000systematic-thinkingRigorous problem decomposition and evidence-based analysis methodology for software engineering tasks. Use to analyze situations…majiayu000systems-thinkerUnderstand complex systems, interconnections, and emergent behaviorsmajiayu000systems-thinkingHelp users think in systems and understand complex dynamics. Use when someone is dealing with multi-stakeholder problems, trying…majiayu000syyte-ja-vastausRikosasian tuomioistuinvaihe Suomessa (laki oikeudenkäynnistä rikosasioissa 689/1997): syyteharkinta, haastehakemus, vastaajan…akunikkolat-tech-researchAssess technical feasibility for a feature. Scans codebase, checks dependencies, researches libraries, and writes a structured…timzaakwritestachyon-killerGeneral-purpose instability detector and killer. Tachyons are runaway modes -- imaginary mass, exponential growth, positive…majiayu000taiyo-analyzer太陽スタイル分析・スコアリングエンジン - 176パターンに基づくコンテンツ品質分析と改善提案majiayu000tap-explorerTree of Attacks with Pruning for systematic code analysismajiayu000targeted-prospectingBuild a prospect list of companies with decision makers, verified contact info, and hiring/intent signals. Use when asked to find…gooseworks-aitarjouspyynto-ja-tarjousTarjouspyynnön laatiminen ja tarjouksen tekeminen julkisessa hankinnassa (hankintalaki 1397/2016). Käytä tätä skilliä, kun…akunikkolatasks-bug-diagnosisUse when diagnosing bugs, analyzing errors/stack traces, or performing root cause analysis with evidence-based debugging…majiayu000writestasks-feature-investigationUse when investigating existing features, understanding logic flow, or exploring how code works.majiayu000bio-microbiome-taxonomy-assignmentTaxonomic classification of ASVs using reference databases like SILVA, GTDB, or UNITE. Covers naive Bayes classifiers (DADA2…majiayu000tcm-constitution-analyzer分析中医体质数据、识别体质类型、评估体质特征,并提供个性化养生建议。支持与营养、运动、睡眠等健康数据的关联分析。majiayu000writestcm-constitution-analyzer分析中医体质数据、识别体质类型、评估体质特征,并提供个性化养生建议。支持与营养、运动、睡眠等健康数据的关联分析。majiayu000writestdd-workflows-tdd-greenImplement the minimal code needed to make failing tests pass in the TDD green phase.sickn33team-collaboration-issueYou are a GitHub issue resolution expert specializing in systematic bug investigation, feature implementation, and collaborative…sickn33cog-team-intelligenceCross-reference GitHub, Linear, Slack, and PostHog with bidirectional sync for team briefsa5c-aiteam-linkedin-profilesFind LinkedIn profiles of a specific team or department at a company. Use when asked to get LinkedIn profiles, find team members…gooseworks-aiteam-shapeAssess team structure against Skelton's Team Topologies. Evaluate cognitive load, interaction modes, and Conway's Law alignment.majiayu000team-shapeAssess team structure against Skelton's Team Topologies. Evaluate cognitive load, interaction modes, and Conway's Law alignment.majiayu000team-ultra-analyzeDeep collaborative analysis pipeline. Multi-perspective exploration, deep analysis, user-driven discussion loops, and…majiayu000writestech-article-extractor技術サイトから特定の技術に関する記事・動画・スライド・論文を抽出・分析します。Qiita、Zenn、Stack…majiayu000discovery.tech_landscapeAssess technical patterns, integrations, and constraints in the domain to inform feasibility and strategy.majiayu000tech-radarBuild a technology radar for an engineering team, categorizing technologies into Adopt/Trial/Assess/Hold quadrants following the…majiayu000technical-discoveryPerforms technical research and analysis without implementation. Use when asked to "analyze this", "research this change"…majiayu000technical-researchSystematic technical research methodology for evaluating technologies, libraries, and approaches. Use when researching new…majiayu000technical-tutorialsWhen the user wants to create step-by-step technical tutorials, quickstarts, or code walkthroughs. Trigger phrases include…sickn33technology-impactSystematically analyze societal impacts of technologies using McLuhan's Tetrad of Media Effects. Use when evaluating new…majiayu000tekijanoikeusTekijänoikeus Suomen oikeuden mukaan (tekijänoikeuslaki 404/1961 DSM-uudistuksineen). Käytä tätä skilliä, kun käyttäjä kysyy…akunikkolatekoaly-velvoitteetTekoälyasetuksen (EU 2024/1689) velvoitteiden selvittäminen roolin (tarjoaja/ käyttöönottaja) ja riskiluokan mukaan sekä korkean…akunikkolahotdogHot dog or not? Classify food photos and battle Nemotron. Use when a user sends a food photo, asks if something is a hot dog, or…majiayu000terminal-capability-detectorDetect terminal capabilities including color support, TTY status, size, and Unicode support for adaptive CLI output.a5c-aiwritesterms-analyzerAnalyze terms of service and privacy policies to identify concerning clauses, hidden permissions, and user rights implicationsmajiayu000terracottaA sun-baked, clay-toned editorial interface built on warm cream surfaces, ink-brown headlines set in a display serif, and a…bergsidetext-analystComputational text analysis for sociology research using R or Python. Guides you through topic models, sentiment analysis…majiayu000text-summarizerGenerate extractive summaries from long text documents. Control summary length, extract key sentences, and process multiple…majiayu000textbook-evidence-hierarchyNavigate the veterinary textbook landscape with authority rankings. Know which textbooks are definitive for which topics. Use…majiayu000the-churning-customerSimulate the exact customer who will quietly cancel in month 4 — their internal monologue through the lifecycle and the honest…mohitagw15856the-oracleUse when the user asks to "use the oracle" or "ask the oracle" for deep research, analysis, or architectural questions requiring…majiayu000the-thesis-defenseSimulate your thesis defense before the real one — a committee of examiner archetypes probing YOUR actual thesis, the questions…mohitagw15856the-visa-interviewSimulate a consular visa interview — the 90-second assessment, the questions behind the questions, and a debrief on which answers…mohitagw15856
← Prev101 / 447Next →
How the catalog works
What is an agent skill?

A folder with a SKILL.md inside — instructions, and often scripts and assets, that an AI agent loads when the task matches. Claude Code, Codex, Cursor and Copilot all read the same format, so one skill usually works across them.

Where does this catalog come from?

We read 660 source repositories straight from their file trees rather than from submitted listings — what you see is what is actually published. 98 repositories were rejected because they advertise skills but contain none: link lists, not folders.

Why is there no install counter?

Because install counts live in the registry that serves `npx skills add`, and that is not ours — publishing a number we cannot verify would be worse than showing none. Instead we show where a skill comes from and whether attention around its source is actually growing, measured from our own weekly snapshots.

Do you deduplicate?

Yes, and it matters more than expected. Aggregator repositories republish the same skill in several places — one source carried 6,317 SKILL.md files for 2,001 actual skills. We collapse by folder name and keep the canonical copy, so the catalog counts things, not copies.

Keep going