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 29,140codex 4,755cursor 3,111copilot 976windsurf 55cline 34
CategoryWorkflow & Productivity 4,979AI & Agents 3,037Data & Analytics 2,345Code Review & Quality 1,376Backend & API 1,244Security 1,194Design & Presentation 1,154Documentation 965Content & Marketing 916Testing & QA 777DevOps & Cloud 576Databases 550Frontend 469Business & Finance 328Media & Video 257Other 9,833
21,420 found
3,5053,552 · page 74 / 447
in3-problem-reversalApply IN3 Problem Reversal to solve the inverse of the stated problem to reveal insights.majiayu000in7-boundary-testingApply IN7 Boundary Testing to explore extreme conditions to find system limits and breaking points.majiayu000incarnationFull character autonomy across all layers of existencemajiayu000incident-platformsIncident management platform integration for PagerDuty, Opsgenie, and related toolsa5c-aiwritesindia-news-trackerTrack and analyze Indian stock market news, corporate announcements, SEBI circulars, bulk/block deals, and earnings calendars.…majiayu000indigenous-leader-analystAnalyzes events through indigenous knowledge systems using relational thinking, seven generations principle, reciprocity…majiayu000Industry ExpertDeep domain research and expertise synthesis across industries, combining academic research, market intelligence, and…majiayu000inevitability-engineSystematic research protocol for discovering novel AI-native software businesses in the synthetic workforce era. Maps capability…majiayu000infinity-operads∞-Operads for pairwise/tritwise Cat# interactions with lazy ACSet materialization unifying effective, realizability, and…majiayu000influence-propagationLayer 7 Interperspectival Network Analysis and Influence Flowmajiayu000info-feed-aggregator多源信息聚合与精炼报告工具。从学术数据库(arXiv、Semantic Scholar、IEEE Xplore、Crossref) 和社交媒体(微信公众号、小红书、RSS)聚合搜索结果,经去重评分后生成精炼分析报告(PDF),…majiayu000informal-fallaciesCatalog of informal fallacies with definitions, canonical examples, and detection heuristics. Covers relevance fallacies (ad…majiayu000input-systemsArchitect game input — action mapping (abstracting keys into named actions), rebinding with conflict detection and persistence…gamedev-skillsinquireRequest clarification when input is ambiguous. Use when user request has missing parameters, conflicting interpretations, or…majiayu000inspection-report-decoderDecode a home inspection report into what's cosmetic, what's expensive, and what kills deals — with repair-cost ranges and the…mohitagw15856instantly-aiTalk to Instantly Ai Founders about their expertise. Instantly Ai Founders provides authentic advice using their mental models…majiayu000instinct-statusDisplay learned instincts with confidence bars grouped by domain. Shows personal and inherited instincts, observation count, and…majiayu000intent-firstClarify user intent before executing tasks. Use when requests are vague, ambiguous, or could be interpreted multiple ways. Helps…majiayu000intent-mapperIntent classification and mapping for natural language commands. Uses unsloth/transformers for ML-based intent detection with…majiayu000intentTurn rough ideas into clear work orders before planning or building. Use when request is vague like "add a button", "make it…majiayu000interaction-guidelinesユーザーとの効果的な対話パターン、質問生成、曖昧さ解消、合意形成、ユーザー負担軽減のガイドラインを定義する。ユーザーに質問する際、要件を確認する際、フィードバックを収集する際、またはユーザーが対話改善、質問方法、確認プロセス、Progressive…majiayu000interaction-netsLafont's interaction nets for optimal parallel λ-reduction. Graph rewritingmajiayu000interactionBuild the curated interactive SET the Editor approved: the ONE narrative-bound hero centerpiece (an explorable/scrollytelling…QinghongLinwritesinterpreting-tumor-markersTracks tumor marker trends with diagnostic and monitoring interpretive frameworks. Use when tracking tumor markers, interpreting…majiayu000interpreting-urinalysisStructures complete urinalysis interpretation with microscopy correlation and clinical significance. Use when interpreting UA…majiayu000dev:interrogateInterrogate code changes to surface decisions, alternatives, and confidence levels. Use when user asks to "interrogate", "what…majiayu000interview-meInteractive interview to formalize a research idea into a structured specification with hypotheses and empirical strategymajiayu000writesinterview-prepPrepare for a specific interview at a specific company, not just 'an interview'. Use when asked to prep for an interview, prepare…mohitagw15856interview-simulatorSimulate realistic coding interview experiencea5c-aiwritesinterview-summaryGenerates structured summaries of witness or subject interviews for criminal defense investigations. Distills key facts, verbatim…majiayu000interview-writeupWrite-up support for qualitative interview research in sociology. Guides methods and findings drafting with emphasis on…majiayu000invariant-analyzerIdentify and verify loop invariants for correctness proofsa5c-aiwritesinvariant-analyzerIdentify and verify loop invariants for correctness proofsmajiayu000writesinventory-demand-planningCodified expertise for demand forecasting, safety stock optimization, replenishment planning, and promotional lift estimation at…majiayu000Inversion ExerciseFlip core assumptions to reveal hidden constraints and alternative approaches - "what if the opposite were true?majiayu000inversion-thinkingSolve problems by thinking backwards. Use when forward thinking is stuck, you need to identify risks, or find non-obvious…majiayu000investigate-dependenciesConduct thorough dependency audits to identify redundant code, unused features, and improper usage patterns. Examines each import…majiayu000investigateDeep investigation of errors, bugs, or codebase questions without making any code changes. Use when user mentions investigate…majiayu000investigateDeep investigation of errors, bugs, or codebase questions without making any code changes. Use when user mentions investigate…majiayu000investigating-a-codebaseUse when planning or designing features and need to understand current codebase state, find existing patterns, or verify…majiayu000investment-criticApplies critical thinking to evaluate investment analysis, identify risks, and detect factual errorsmajiayu000investment-daily-reportGenerates comprehensive daily investment reports with market overview, portfolio analysis, technical signals, and opportunitiesmajiayu000invoke-opencode-acpDelegate complex tasks to OpenCode subagent, use when >=2 file modifications or batch operationsmajiayu000writesip-core-managementVendor IP core configuration and integration expertise for FPGA designsa5c-aiwritesip-evaluator梳理IP网络信息并进行多维度评估打分。适用于评估小说、剧本等IP的改编价值、分析市场潜力和创新属性majiayu000ip-lookupCheck an IP address across multiple public geolocation and reputation sources and return a best-matched location summary.majiayu000isomorphic-hunterCross-domain isomorphic pattern forge. Dokkado Five Rings x meta-pattern 3+ domain validation, with arxiv evidence hunting and…majiayu000issue-trackingTrack beads as git-backed issues with persistent attribution, supporting Gas Town's bead lifecycle and convoy progress monitoring.a5c-aiwrites
← Prev74 / 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