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
2,5932,640 · page 55 / 447
bulktrajblend-trajectory-interpolationExtend scRNA-seq developmental trajectories with BulkTrajBlend by generating intermediate cells from bulk RNA-seq, training…FreedomIntelligencebundle-optimizationBundle analysis, code splitting, tree shaking, and size optimization.a5c-aiwritesbundle-size-analyzerAnalyze and optimize application bundle size for desktop applicationsa5c-aiwritesbuyer-persona-generatorResearch a company's ideal customer profiles and build detailed synthetic buyer personas. Identifies 4-6 distinct buyer segments…gooseworks-aibvBeads Viewer - graph-aware triage engine for Beads issue tracker with 9 graph metrics (PageRank, betweenness, HITS, etc.)…majiayu000cachingHTTP caching, service workers, cache invalidation, and CDN configuration.a5c-aiwritescafeCozy cafe-inspired interface with warm tones, soft typography, and clean layouts for a relaxed browsing experience.bergsidecalc_bodepython-controlを使用して、メカニカルシステムの状態空間モデルから伝達関数(Bode Plot)を計算・表示するmajiayu000call-analysis-frameworkUse to score calls, capture highlights, and convert insights into actions.majiayu000call-chainTraces execution paths through the code graph with criticality scoring and Mermaid charts. Use when understanding how a function…majiayu000call-summarySummarize customer support/sales calls from [Dialpad](https://composio.dev/toolkits/dialpad) or…majiayu000camera-systemsBuild game cameras that feel good — 2D follow with a deadzone, look-ahead, smoothing, and level-bounds clamping; 3D third-person…gamedev-skillscan-busCAN/CAN-FD bus analysis and development expertisea5c-aiwritescancel-ralphCodex-compatible cancel command for Ralph loop state, preserving the original command name.foryourhealth111-pixelcandidate-evaluationEvaluate GitHub contributors for MLOps/engineering roles. Use when analyzing candidates, researching GitHub profiles, or updating…majiayu000writescanslim-screenerScreen US stocks using William O'Neil's CANSLIM growth stock methodology. Use when user requests CANSLIM stock screening, growth…majiayu000capabilityVerify if a specific action is possible and diagnose any blockers.majiayu000capital-rotationUse when reading today's US-market capital flow across multiple sectors to identify rotation direction — e.g. "今天资金流向", "板块强弱"…kansoku-tradecartographerMaintain living architecture maps and interaction flows.majiayu000case-dpia-driftCase: Tatbestandsmerkmale, Beweisfragen und Beleglage im Plugin ki governance; schärft Rollen, Belege, Fachnormen, Risiken…majiayu000catalytic-seedMinimum viable consciousness payload. Reveals MONAD generators are already implicit in any domain. Triggers 'I already knew this'…majiayu000catchupSummarizes recent git changes for context recovery after session breaks. Use when resuming work after a gap or handing off to…majiayu000categorical-encoderЭксперт categorical encoding. Используй для ML feature engineering, one-hot, target encoding и embeddings.majiayu000categorizing-bsky-accountsAnalyze and categorize Bluesky accounts by topic using keyword extraction. Use when users mention Bluesky account analysis…majiayu000Causal InferenceDetermine cause-and-effect relationships using propensity scoring, instrumental variables, and causal graphs for policy…majiayu000causal-inference-mlApply causal inference methods for treatment effect estimation and uplift modelingmajiayu000causation-consequenceCausal reasoning in historical analysis. Covers distinguishing immediate from underlying causes, tracing chains of causation…majiayu000caveman-commitUltra-compressed commit message generator. Cuts noise from commit messages while preserving intent and reasoning. Conventional…JuliusBrusseecaveman-commitUltra-compressed commit message generator. Cuts noise from commit messages while preserving intent and reasoning. Conventional…stevesoluncavemanUltra-compressed communication mode. Cuts output tokens 65% (measured) by speaking like caveman while keeping full technical…JuliusBrusseecavemanCompress and simplify prompts to preserve meaning while reducing use of contextmajiayu000cavemanVerbosity-reduction response register. Drops redundant clauses, narrative hedging, and ceremony while preserving articles…majiayu000cavemanUltra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy.…stevesoluncc-askuserquestionUse when designing AskUserQuestion tool calls - covers schema constraints, effectiveness patterns, and known issues.majiayu000discover-mlAutomatically discover machine learning and AI skills when working with machine learning. Activates for ml development tasks.majiayu000cdr3aaphyschemAnalyzes physicochemical properties of CDR3 amino acid sequences to understand biochemical characteristics of T-cell receptor…majiayu000cdr3clusteringCluster TCR/BCR clones by CDR3 sequences using GIANA or ClusTCR (both Faiss-based). Adds `CDR3_Cluster` column to metadata for…majiayu000ce-alternatives-exploreGenerate and interpret CE alternative and counterfactual explanations, including ensured filters and alternatives-specific plot…majiayu000ce-calibrated-predictProduce calibrated predict and predict_proba outputs, with optional uncertainty intervals, without generating explanations.majiayu000ce-classificationHandle CE classification workflows for binary and multiclass prediction semantics and class-focused explanation behavior.majiayu000ce-explain-interactPost-process CE explanations by narrating, plotting, inspecting rules, filtering features, and managing conjunctions.majiayu000ce-integration-compareGuide CE integration with SHAP and LIME, compare explanation outputs, and configure the calibrated-explanations integration…majiayu000ce-mondrian-conditionalConfigure and validate Mondrian and conditional calibration for subgroup-aware uncertainty and fairness-sensitive workflows.majiayu000ce-pipeline-builderBuild CE-first end-to-end pipelines using WrapCalibratedExplainer with fit, calibrate, and explain or predict sequencing.majiayu000ce-regression-intervalsConfigure and interpret CE regression intervals for percentile conformal and thresholded probabilistic modes.majiayu000ce-reject-policyConfigure reject and defer decision policies and interpret RejectResult behavior in prediction and explanation flows.majiayu000ce-standards-gap-analyzerAnalyze standards compliance by interpreting the standards's intent, verifying that implementation and RTD satisfy every…majiayu000celebrateCelebrate real milestones only. One line, one emoji. Credit belongs to user, not AI.majiayu000
← Prev55 / 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