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
2,6412,688 · page 56 / 447
celebrateCelebrate real milestones only. One line, one emoji. Credit belongs to user, not AI.majiayu000bio-single-cell-cell-annotationAutomated cell type annotation using reference-based methods including CellTypist, scPred, SingleR, and Azimuth for consistent…majiayu000celltypeannotationAnnotates cell clusters with biological cell type labels using multiple is essential for interpreting clustering results by…majiayu000center-manifoldInvariant manifold tangent to center eigenspacemajiayu000certora-proverFormal verification using Certora Prover with CVL specification language. Supports invariant rules, parametric verification…a5c-aiwritescf-infoАнализ структуры конфигурации 1С — свойства, состав, счётчики объектов. Используй для обзора конфигурации — какие объекты есть…majiayu000writescfe-diffАнализ расширения конфигурации 1С (CFE) — состав, заимствованные объекты, перехватчики, проверка переноса. Используй когда нужно…majiayu000writeschain-of-thought複雑な問題を分解し、推論の流れを整理して短い根拠サマリーを作成するスキル。 前提整理、論点分解、選択肢比較、判断理由の要約を通じて、説明責任のあるアウトプットを作る。 Anchors: • The Pragmatic Programmer / 適用…majiayu000writeschain-of-thought-promptsChain-of-thought and step-by-step reasoning prompts for complex problem solvinga5c-aiwriteschalk-styling-systemCreate consistent chalk-based color and styling system for CLI output with themes, semantic colors, and formatting utilities.a5c-aiwriteschampion-move-outreachEnd-to-end champion/buyer/user job change signal composite. Takes a set of known people (past buyers, champions, power users)…gooseworks-aichange-order-analysisAnalyze and predict construction change orders using ML. Classify change order types, predict costs and schedule impacts…majiayu000chaos-runnerRun chaos engineering experiments using Chaos Monkey, Litmus, or Gremlina5c-aiwriteschaotic-attractorStrange attractor with sensitive dependence on initial conditionsmajiayu000chaotic-attractorStrange attractor with sensitive dependence on initial conditionsmajiayu000character-profile基于故事文本分析人物特征,生成详细的人物小传。适用于深度理解故事人物设定、为演员塑造角色提供参考、为剧本创作建立人物档案majiayu000character-relationships分析故事人物关系,识别类型、特点及发展变化。适用于深度理解人物关系网络、分析关系对情节推动作用、为情节设计提供关系支撑majiayu000chatAnswer with 42. Always respond with just the number 42, nothing else.majiayu000chatgpt-oracleSend prompts to ChatGPT Pro via Playwriter browser automation. Use for cross-validation, second opinions, or leveraging GPT-5.2…majiayu000chatgpt-proSend prompts to ChatGPT Pro via Playwriter browser automation. Use for cross-validation, second opinions, or leveraging GPT-5.2…majiayu000checkpoint-managementGit-backed state management for safe rollback. Create and restore checkpoints with tagged commits and metadata tracking.a5c-aiwriteschocolatey-package-generatorGenerate Chocolatey package for Windows CLI distribution.a5c-aiwriteschoose-frameworkSelect the right strategic framework for your situation through exploratory dialogue. Use when user describes a problem…majiayu000churn-risk-detectorScan support tickets, Slack channels, NPS scores, and usage patterns to flag accounts showing early churn indicators. Produces a…gooseworks-aichurn-risk-detectorScan support tickets, Slack channels, NPS scores, and usage patterns to flag accounts showing early churn indicators. Produces a…majiayu000cic-can-0091Wenn es um CIC can. 91 - Buch I - Allgemeine Normen in Römisch-katholisches Kirchenrecht CIC und Katechismus geht: ordnet…Klotzkettecider-embeddingSemantic embeddings for Clojure code navigation via CIDERmajiayu000cirqCirq is Google Quantum AI's open-source framework for designing, simulating, and running quantum circuits on quantum computers…majiayu000cirqCirq is Google Quantum AI's open-source framework for designing, simulating, and running quantum circuits on quantum computers…majiayu000citation-chasing-mappingUse when identifying seminal papers in a research field, mapping research lineage and intellectual heritage, discovering related…majiayu000writescitation-management用于学术研究的综合文献引用管理工具。可搜索 Google Scholar 和 PubMed 论文数据库,提取准确的元数据,验证引用信息,并生成规范格式的 BibTeX 条目。当需要查找论文、核对引用信息、将 DOI 转换为…majiayu000writescity-distanceCalculate line-of-sight and road distances between two cities using free OpenStreetMap services.majiayu000claimifyExtract and structure claims from discourse into analyzable argument maps with logical relationships and assumptions. Use when…majiayu000bio-long-read-sequencing-clair3-variantsDeep learning-based variant calling from long reads using Clair3 for SNPs and small indels. Use when calling germline variants…majiayu000clap-scaffolderGenerate Clap-based Rust CLI applications with derive macros, subcommands, and modern Rust patterns. Creates production-ready…a5c-aiwritesSpecification ClarificationIdentify and resolve ambiguities in specifications through structured questioning. Use when specification has [NEEDS…majiayu000writesclassify-anomalyClassify speleothem anomalies as seismic, climatic, volcanic, or compound events. Use when discriminating earthquake signals from…majiayu000clawdintClawdINT. Collaborative platform for structured tracking, research, and analysis of events and signals.majiayu000clay-load-scaleScale Clay enrichment pipelines for high-volume processing (10K-100K+ leads/month). Use when planning capacity for large…jeremylongshorewritesclaymorphismSoft, rounded 3D-like shapes mimicking malleable clay with playful, puffy elements and colorful surfaces.bergsideclerk-ci-integrationConfigure Clerk CI/CD integration with GitHub Actions and testing. Use when setting up automated testing, configuring CI…jeremylongshorewritesclerk-common-errorsTroubleshoot common Clerk errors and issues. Use when encountering authentication errors, SDK issues, or configuration problems…jeremylongshorewritesclerk-enterprise-rbacConfigure enterprise SSO, role-based access control, and organization management. Use when implementing SSO integration…jeremylongshorewritesclerk-multi-env-setupConfigure Clerk for multiple environments (dev, staging, production). Use when setting up environment-specific configurations…jeremylongshorewritescli-framework-builderBuild command-line interfaces for SDK interactiona5c-aiwritescli-mock-stdinCreate mock stdin utilities for interactive CLI testing.a5c-aiwritescli-progress-bar-setupConfigure cli-progress with custom formatters, multi-bar support, and ETA calculations for CLI progress indication.a5c-aiwritescli-snapshot-testerSet up snapshot testing for CLI output with update workflows and diff reporting.a5c-aiwrites
← Prev56 / 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