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
3,1213,168 · page 66 / 447
engine-superpower-profilingProfile AI engine superpowers and capability boundaries.majiayu000engineer-expertise-extractorResearch and extract an engineer's coding style, patterns, and best practices from their GitHub contributions. Creates structured…majiayu000enterprise-monitorMonitors enterprise account health, usage, and contract compliance. Alerts on low engagement, quota breaches, or churn risk.majiayu000enterprise-risk-aggregatorAggregate and analyze risks across construction project portfolio. Identify correlated risks, systemic exposures, and…majiayu000entropy-sequencerLayer 5: Interaction Interleaving for Maximum Information Gainmajiayu000entropy-sim2realEntropy-driven sim2real transfer. Uses maximum entropy RL, domain randomization, and information-theoretic bridging to close the…majiayu000env-var-mapperGenerate environment variable to CLI argument mapping with prefix support, type conversion, and fallback chains for configuration.a5c-aiwritesepd-compareCompare 2+ products side-by-side on environmental impact metrics. Normalizes declared units, checks system boundary alignment…majiayu000writesepic-reportGenerate epic progress reports. Use for epic status, story tracking, blocker detection, and progress summaries.majiayu000epistemic-arbitragePropagator-based parallel structure for exploiting knowledge differentials across domains using local scoped propagators and…majiayu000error-code-catalogManage and document SDK error codes and messagesa5c-aiwriteserror-debugging-error-analysisYou are an expert error analysis specialist with deep expertise in debugging distributed systems, analyzing production incidents…sickn33error-debugging-error-traceYou are an error tracking and observability expert specializing in implementing comprehensive error monitoring solutions. Set up…sickn33error-detectiveSystematic debugging and error resolution using the TRACE framework (Trace, Read, Analyze, Check, Execute). Use when debugging…majiayu000error-detectiveSearch logs and codebases for error patterns, stack traces, and anomalies. Correlates errors across systems and identifies root…majiayu000error-detectiveSearch logs and codebases for error patterns, stack traces, and anomalies. Correlates errors across systems and identifies root…majiayu000error-detectiveUse when user needs complex error pattern analysis, distributed system debugging, error correlation, root cause discovery, or…majiayu000error-detectorAdvanced error analysis and pattern detection specialist for identifying, analyzing, and preventing software errorsmajiayu000error-diagnostics-error-analysisYou are an expert error analysis specialist with deep expertise in debugging distributed systems, analyzing production incidents…majiayu000error-diagnostics-error-analysisYou are an expert error analysis specialist with deep expertise in debugging distributed systems, analyzing production incidents…majiayu000error-diagnostics-error-analysisYou are an expert error analysis specialist with deep expertise in debugging distributed systems, analyzing production incidents…sickn33error-diagnostics-error-analysisYou are an expert error analysis specialist with deep expertise in debugging distributed systems, analyzing production incidents…majiayu000error-diagnostics-error-traceYou are an error tracking and observability expert specializing in implementing comprehensive error monitoring solutions. Set up…sickn33error-handling-patternsBuild resilient applications with robust error handling strategies that gracefully handle failures and provide excellent…sickn33error-handling-patternsMaster error handling patterns across languages including exceptions, Result types, error propagation, and graceful degradation…wshobsonhive.error-recoveryFollow a structured recovery protocol when tool calls fail instead of blindly retrying or giving up.majiayu000esbuildesbuild bundling, plugins, and build optimization.a5c-aiwriteseslintESLint configuration, custom rules, and plugin development.a5c-aiwritesestablishing-project-contextUse when the user asks to establish shared project language or project work exposes a resolved, vague, conflicting, renamed, or…GanyuanRanetamyynti-ja-peruuttaminenEtä- ja kotimyynnin tiedonantovelvollisuudet ja kuluttajan peruuttamisoikeus (kuluttajansuojalaki 38/1978) sekä sopimaton ja…akunikkolaethicist-analystAnalyzes moral dimensions and value conflicts through ethical frameworks using deontology, consequentialism, virtue ethics, and…majiayu000eu-ja-perheperusteinen-oleskeluEU-kansalaisen oleskeluoikeus, perheperusteinen oleskelu, pysyvä oleskelulupa ja Suomen kansalaisuus (ulkomaalaislaki 301/2004…akunikkolaEU-LegislationAccess EU law. Search and retrieve Directives, Regulations, Treaties and CJEU case law from EUR-Lex.lawve-aiEval AnalyzerAnalyze evaluation baseline results, identify failure patterns, and generate actionable insights. Use after running eval…majiayu000Eval Gap FinderFind AILANG vs Python eval gaps and improve prompts/language. Use when user says 'find eval gaps', 'analyze benchmark failures'…majiayu000eval-recipes-runnerRun Microsoft's eval-recipes benchmarks to validate amplihack improvements against baseline agents. Activates when testing with…majiayu000eval-runnerRun eval scenarios to benchmark Mycelium effectiveness. Execute tasks using reflexion loop, validate against success criteria…majiayu000evaluate-exponential-trend-deviation-regimes計算資產價格相對長期指數成長趨勢線的偏離度,衡量當前是否處於歷史極端區間,並可選擇性地進行宏觀因子分析以判斷行情體質。majiayu000evaluateAnalyze a subject from five perspectives with assumption tracking and weighting. Use after research to examine all angles before…majiayu000evaluate-mmiMMI評価エージェント - Modularity Maturity Indexによるモジュール成熟度評価(Cohesion/Coupling/Independence/Reusability)。/evaluate-mmi [対象パス] で呼び出し。majiayu000evaluating-new-technologyHelp users evaluate emerging technologies. Use when someone is assessing new tools, making build vs buy decisions, evaluating AI…majiayu000evaluating-trade-offsEvaluate trade-offs and produce a Trade-off Evaluation Pack (trade-off brief, options+criteria matrix, all-in cost/opportunity…majiayu000evaluationSystematic evaluation and comparison of technologies, tools, frameworks, and approaches using weighted criteria and scoring…majiayu000event-prospecting-pipelineFind attendees at conferences/events, research their companies, qualify against ICP, and launch outreachgooseworks-aievent-sourcing-migratorMigrate to event-sourcing architecture with event extraction, store setup, and CQRS implementationa5c-aiwritesevernote-ci-integrationConfigure CI/CD pipelines for Evernote integrations. Use when setting up automated testing, continuous integration, or deployment…jeremylongshorewritesevernote-enterprise-rbacImplement enterprise RBAC for Evernote integrations. Use when building multi-tenant systems, implementing role-based access, or…jeremylongshorewritesevernote-incident-runbookManage incident response for Evernote integration issues. Use when troubleshooting production incidents, handling outages, or…jeremylongshorewrites
← Prev66 / 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