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
3,4573,504 · page 73 / 447
hugging-face-gradioBuild Gradio web UIs and demos in Python. Use when creating or editing Gradio apps, components, event listeners, layouts, or…sickn33hugging-face-paper-publisherPublish and manage research papers on Hugging Face Hub. Supports creating paper pages, linking papers to models/datasets…majiayu000hugging-face-vision-trainerTrain or fine-tune vision models on Hugging Face Jobs for detection, classification, and SAM or SAM2 segmentation.majiayu000huggingface-gradioBuild Gradio web UIs and demos in Python. Use when creating or editing Gradio apps, components, event listeners, layouts, or…waybarrioshuggingfaceImport GGUF models from HuggingFace into Ollama. Pull models directly using the hf.co/ prefix, track download progress, and use…majiayu000hybrid-search-rrfReciprocal Rank Fusion for merging full-text and vector search results in this project. Convex native searchIndex + vectorIndex…majiayu000hydrodynamic-analysisHydrodynamic analysis using BEM, RAOs, added mass, damping, and wave loads for offshore structuresmajiayu000hydrodynamicsManage hydrodynamic coefficients, wave spectra, and environmental loading\ \ for vessel response analysis. Use for 6\xD76 matrix…majiayu000hype-assessmentAssess overall hype levels across AI topics by comparing lab researcher enthusiasm against critic skepticism. Use after topic…majiayu000hyperbolic-bulkOn-chain GF(3) entropy storage via Aptos Move - bulk-boundary correspondence where entropy lives in the interior and observables…majiayu000hyperbolicityNo eigenvalues on imaginary axis (robust dynamics)majiayu000hypothesesManages the project's testable hypotheses — surfacing new ones, refining existing ones, updating status, reviewing the full set…davepoonhypothesis-buildingBuild falsifiable causal hypotheses: DAGs, FPCI, equivalence testing.brycewang-stanfordhypothesis-extractionIdentify, structure, and catalog testable hypotheses from pilot signals and strategic inputs. Use when transforming unstructured…majiayu000hypothesis-trackingTrack and manage research hypotheses with confidence levels. Use when the user asks about prior research, wants to validate…majiayu000hypothesis-trackingConfidence level management and hypothesis lifecyclemajiayu000ic-curateCurate external IC10 resources without generating code. Use when user wants to find existing scripts, tutorials, or community…majiayu000icp-identificationResearch a company or idea, define the Ideal Customer Profile, and route to the right next step — either mapping the TAM or…gooseworks-aiidea-creatorGenerate and rank research ideas given a broad direction. Use when user says "找idea", "brainstorm ideas", "generate research…majiayu000writesidea-generatorBrainstorm and rank iOS/macOS app ideas tailored to developer skills. Use when user says "what should I build", "give me app…rshankraswritesidea-scanAnalyze standing-intelligence pack diffs and produce scan-proposals.md for IDEAS-02 backlog updates.majiayu000identification-theoryDAG and potential outcomes frameworks for causal mediation identificationbrycewang-stanfordidp-configuratorConfigure Internal Developer Platform (IDP) componentsa5c-aiwritesihara-zetaIhara zeta function for graphs: non-backtracking walks, prime cycles, and spectral analysis via det(I - uB).majiayu000image-analysisReference for auction item image analysis — what to look for in photos of auction items, how to extract catalog-relevant…majiayu000image-comparison-toolCompare images with SSIM similarity scoring, pixel difference highlighting, and side-by-side visualization.majiayu000imageGenerate and edit images using AI models via OpenRouter. Supports Nano Banana Pro (Gemini 3 Pro Image), FLUX, and other image…majiayu000writesimage-genGenerate website images with Gemini 3 Native Image Generation. Covers hero banners, service cards, infographics with legible…majiayu000image-gen图片生成, 架构图, 流程图, 时序图, 泳道图, diagram, architecture, flowchart, sequence, swimlane, image generation, nano banana, 生图, 画图, 画一个, 生成图片…majiayu000image-gen图片生成, 架构图, 流程图, 时序图, 泳道图, diagram, architecture, flowchart, sequence, swimlane, image generation, nano banana, 生图, 画图, 画一个, 生成图片…majiayu000Image Generation AssistantGenerate images from prompts; style and composition guidancemajiayu000image-generationGenerate images from text prompts using Ollama.majiayu000image-generationGenerate AI image prompts for website assets using Imagen (infographics, diagrams, icons, maps).majiayu000image-miningI mine pixels for atoms. Reality is just compressed resources.majiayu000image-miningI mine pixels for atoms. Reality is just compressed resources.majiayu000image-nano-bananaGenerate/edit images with Nano Banana Pro (Gemini 3 Pro Image). Use for image create/modify requests incl. edits. Supports…majiayu000image-optimizationImage formats, responsive images, lazy loading, and CDN integration.a5c-aiwritesbio-tcr-bcr-analysis-immcantation-analysisAnalyze BCR repertoires for somatic hypermutation, clonal lineages, and B cell phylogenetics using the Immcantation framework.…majiayu000impact_analyzerAnalyze and document the impact of planned changes.majiayu000impact-analyzer**IMPACT ANALYZER v1.0** - '영향도', '영향 범위', '변경 영향', '리팩토링 영향', '이거 바꾸면', '어디에 영향', '위험도' 요청 시 자동 발동. codebase-graph 기반 변경 전파 분석.…majiayu000impactAnalyze system-wide impact of changes before making them. Use before modifying shared utilities, changing APIs, or refactoring…majiayu000implement_planImplement technical plans from thoughts/shared/plans with verificationparcadeiimplementation-executionExecute development tasks to build features, producing code, tests, and configuration artifacts that satisfy specification…a5c-aiwritesimprove-codebase-architectureScan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.rengwuimprove-conversationAnalyze conversations to identify improvements for prompts, instructions, skills, or workflows. Use when something went wrong…majiayu000in-app-eventsGenerates In-App Event metadata templates for App Store Connect — event names, descriptions, badge types, image specs, and deep…rshankraswritesin-silico-perturbation-oracleVirtual gene knockout simulation using foundation models to predict transcriptional changesmajiayu000in2-premortem-analysisApply IN2 Premortem Analysis to assume failure has occurred and work backward to identify causes.majiayu000
← Prev73 / 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