Agent skills

Other skills

21,532 skills an agent can load when the work is Other — read straight from the source repositories, with what each one does, what ships alongside it, and where it came from.

Toolclaude-code 63,296codex 9,782cursor 7,187copilot 2,384windsurf 127cline 83
CategoryWorkflow & Productivity 11,752AI & Agents 4,985Data & Analytics 4,761Code Review & Quality 2,986Security 2,828Backend & API 2,504Design & Presentation 2,373Documentation 2,183Content & Marketing 2,060Testing & QA 1,778DevOps & Cloud 1,275Databases 1,133Frontend 1,043Business & Finance 724Media & Video 514Other 21,532
21,532 found
9,4099,456 · page 197 / 449
code-refactoring-context-restoreUse when working with code refactoring context restoresickn33code-refactoring-tech-debtYou are a technical debt expert specializing in identifying, quantifying, and prioritizing technical debt in software projects.…sickn33code-simplificationSimplifies code for clarity. Use when refactoring code for clarity without changing behavior. Use when code works but is harder…addyosmanicode-simplificationSimplifies code for clarity. Use when refactoring code for clarity without changing behavior. Use when code works but is harder…sickn33codebase-cleanup-tech-debtYou are a technical debt expert specializing in identifying, quantifying, and prioritizing technical debt in software projects.…sickn33codebase-inspectionInspect codebases: LOC, languages, ratios via pygount.HezaoHezaowritesCodenames Russian Clue GeneratorGenerates a single-word verbal clue in Russian for a list of target words within the context of the Codenames board game.ECNU-ICALKcoderabbit-enterprise-rbacConfigure CodeRabbit enterprise access control, seat management, and organization policies. Use when managing who gets AI…jeremylongshorewritescoderabbit-incident-runbookExecute CodeRabbit incident response procedures when reviews stop working or block PRs. Use when CodeRabbit is down, reviews are…jeremylongshorecoderabbit-webhooks-eventsImplement CodeRabbit webhook signature validation and event handling. Use when setting up webhook endpoints, implementing…jeremylongshorewritescodex-profilesUse codex-profiles to run Codex CLI or Codex Desktop with isolated CODEX_HOME profiles for separate accounts, projects, and local…sickn33coding-guidelinesStandardized Python & Stata coding practices for empirical research projectsbrycewang-stanfordcoding-standardsUniversal coding standards - naming, formatting, error handling, immutability, SOLID principlesvibeevalcohere-ci-integrationConfigure CI/CD for Cohere integrations with GitHub Actions and automated testing. Use when setting up automated testing for…jeremylongshorewritescollaboration-contractStart a cross-team project with the collaboration contract that prevents the classic collisions — who decides what, how work…mohitagw15856college-app-parent-guideSupport a teenager through college applications without taking them over — the parent's actual jobs (logistics, finances…mohitagw15856colm-camera-readyUse when converting a COLM acceptance into the final paper — the August 7 camera-ready deadline in 2026, de-anonymization and the…brycewang-stanfordhive.colony-progress-trackerClaim tasks, record step progress, and verify SOP gates in the colony SQLite queue. Applies when your spawn message includes a…aden-hivecolor / skirt / opacityGeneral SOP for common requests related to color, skirt, opacity.ECNU-ICALKcolt-artifact-evaluationUse when deciding what evidence package a COLT (Conference on Learning Theory) paper needs, given that COLT runs no…brycewang-stanfordcolt-author-responseUse when drafting a COLT (Conference on Learning Theory) rebuttal after initial reviews, handling proof-correctness objections…brycewang-stanfordcolt-related-workUse when positioning a COLT (Conference on Learning Theory) submission against prior bounds and models — building the…brycewang-stanfordcolt-submissionUse when auditing a COLT (Conference on Learning Theory) submission for CMT readiness, the 12-page PMLR-format main body…brycewang-stanfordcolt-supplementaryUse when structuring the appendix of a COLT (Conference on Learning Theory) submission — the unlimited-length proof appendix…brycewang-stanfordcolt-topic-selectionUse when deciding whether a result is COLT-shaped (Conference on Learning Theory) — a theorem-first learning-theory contribution…brycewang-stanford生成带Column注释的C#实体类根据数据库字段定义生成C#实体类,属性名采用首字母大写并保留下划线(如 Raw_Id),使用[Column(Description = \"...\")]特性注释,并支持可空类型处理。ECNU-ICALKcombat_sports_narrative_generatorGenerates detailed, commentary-style narratives for professional wrestling and MMA fights. Adapts structure and personas to the…ECNU-ICALKcomment-checkerUse when Codex needs to understand or respond to automatic comment-checker feedback emitted after an edit-like PostToolUse hook.code-yeongyucomment-code-generate-a-tutorialTransform this Python script into a polished, beginner-friendly project by refactoring the code, adding clear instructional…githubcommercial-chamber-vs-commercial-courtWenn es um Commercial Chamber oder Commercial Court in commercial-courts-deutschland geht: entwickelt Verhandlungsziel…Klotzkettecommercial-court-kaltstart-interviewWenn es um Kaltstart-Interview in commercial-courts-deutschland geht: klärt Rolle, Ziel, Frist, Unterlagen und den passenden…Klotzkettecommercial-court-versandmappe-endfertigenEndfertigt deutsch- oder englischsprachige Commercial-Court-Schriftsätze: prüft Spruchkörper, Streitwert, Sprachvereinbarung…Klotzkettecommercial-litigation-budgetWenn es um Commercial Litigation Budget in Kanzlei-Mandant Lifecycle geht: erstellt den passenden Entwurf aus Sachverhalt, Norm…KlotzkettecommitStage and create a Conventional Commits message for the current changeEverMind-AIcommit-push-prCommit current changes, push to remote, and create or update a pull request. Use when the user wants to commit and create a PR…dyoshikawacommit-trailersCommit mesajlarina yapilandirilmis karar trailer'lari ekle. Constraint, Rejected, Confidence, Scope-risk, Not-tested trailer'lari…vibeevalcommittee-agenda-report-schreiben-managingWenn es um Management-Committee-Agenda in Kanzlei Management geht: rechnet Schwellen, Beträge, Varianten und Kontrollannahmen…Klotzkettecommres-rebuttalUse when revising a Communication Research (CR) manuscript after a revise-and-resubmit. CR requires two independent reviews to…brycewang-stanfordcommres-tables-figuresUse when building tables and figures for a Communication Research (CR) manuscript so exhibits are self-contained, accessible, and…brycewang-stanfordcommres-theory-buildingUse when building the theoretical argument and hypotheses of a Communication Research (CR) manuscript into a testable…brycewang-stanfordcommunicating-conciselyUse when the user asks for caveman mode, fewer tokens, brief responses, compressed communication, or otherwise explicitly…GanyuanRancommunications-on-pure-and-applied-mathematicsUse when targeting Communications on Pure and Applied Mathematics (CPAM) or deciding whether an analysis, PDE, or…brycewang-stanfordcompactnessProblem-solving strategies for compactness in topologyparcadeiwritesCompany Awards and Client ResearchResearches and lists exactly 3 notable awards and a selection of high-profile client brands for a specified company.ECNU-ICALKcompany-briefBuild a candidate's research brief on a company before an application or interview. Use when asked to research a company for a…mohitagw15856company-event-planung-hr-riskWenn es um Company Event Planung HR Risk in Start-up-HR-Personalabteilung Berlin geht: entwickelt Verhandlungsziel…Klotzkettecomparable-transaction-finderSearches M&A and funding databases for relevant comparable transactionsa5c-aiwritescomparative-literatureUse when targeting Comparative Literature or deciding whether a cross-national, cross-linguistic, translation, or…brycewang-stanford
← Prev197 / 449Next →
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 655 source repositories straight from their file trees rather than from submitted listings — what you see is what is actually published. 103 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