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
2,9773,024 · page 63 / 447
deepagents-filesystem使用 FilesystemMiddleware 实现虚拟文件系统、后端(State、Store、Filesystem、Composite)和 Deep Agents 的上下文管理。majiayu000deepagents-hitl在 Deep Agents 中实现人工审批工作流,使用 interruptOn 参数对敏感工具操作进行人工干预。majiayu000deepagents-implementationImplements agents using Deep Agents. Use when building agents with create_deep_agent, configuring backends, defining subagents…majiayu000deepagents-subagents在 Deep Agents 中使用 SubAgentMiddleware 启动子代理进行任务委托、上下文隔离和专门工作。majiayu000deepchemMolecular ML with diverse featurizers and pre-built datasets. Use for property prediction (ADMET, toxicity) with traditional ML…majiayu000deepchemMolecular ML with diverse featurizers and pre-built datasets. Use for property prediction (ADMET, toxicity) with traditional ML…majiayu000deepchemMolecular ML with diverse featurizers and pre-built datasets. Use for property prediction (ADMET, toxicity) with traditional ML…majiayu000writesdeepface-basic-usageBasic usage guide for the DeepFace library (face recognition, verification, analysis).majiayu000deepgram-ci-integrationConfigure Deepgram CI/CD integration for automated testing and deployment. Use when setting up continuous integration pipelines…jeremylongshorewritesdeepgram-incident-runbookExecute Deepgram incident response procedures for production issues. Use when handling Deepgram outages, debugging production…jeremylongshorewritesdeepgram-multi-env-setupConfigure Deepgram multi-environment setup for dev, staging, and production. Use when setting up environment-specific…jeremylongshorewritesdeepgram-reference-architectureImplement Deepgram reference architecture for scalable transcription systems. Use when designing transcription pipelines…jeremylongshorewritesdeepgram-webhooks-eventsImplement Deepgram callback and webhook handling for async transcription. Use when implementing callback URLs, processing async…jeremylongshorewritesdeeptoolsNGS analysis toolkit. BAM to bigWig conversion, QC (correlation, PCA, fingerprints), heatmaps/profiles (TSS, peaks), for…majiayu000deepxivSearch and progressively read open-access academic papers through DeepXiv. Use when the user wants layered paper access…majiayu000deepxivSearch and progressively read open-access academic papers through DeepXiv. Use when the user wants layered paper access…majiayu000writesdefi-protocolsIntegration expertise for major DeFi protocols including Uniswap, Aave, Compound, Chainlink, Curve, and Balancer. Supports swaps…a5c-aiwritesdeliverability-opsUse when investigating inbox placement, reputation, and compliance signals across senders.majiayu000demographic-fiscal-trap-analyzer分析人口老化、債務動態、官僚膨脹與通膨稀釋交互作用下的「財政陷阱」風險,量化各國/地區的財政脆弱度並識別潛在的貨幣稀釋路徑majiayu000dependency-analysis依存関係の可視化、循環依存検出、安定度評価を体系化するスキル。 アーキテクチャの健全性を測定し、改善優先度を整理する。 Anchors: • Clean Architecture / 適用: 安定依存の原則 / 目的: 依存方向の評価 •…majiayu000writesdependency-graphGenerates a Mermaid dependency graph showing import relationships between modules. Use when analyzing coupling, finding circular…majiayu000dependency-graph-generatorGenerate module dependency graphs with circular dependency detection and coupling metricsa5c-aiwritesdependency-graph-generator生成GOAL/SubPlan依赖DAG和关键路径分析,并执行SubPlan划分。当需要分析技术依赖、业务依赖、识别关键路径、发现并行执行机会、执行SubPlan分配时使用。基于GOAL的dependencies字段和业务逻辑分析生成Mermaid依赖图和Sub…majiayu000dependency-graphVisualize system dependencies and relationshipsmajiayu000dependency-scannerSoftware Composition Analysis (SCA) and dependency vulnerability scanning. Scan npm, pip, maven, gradle dependencies. Check CVE…a5c-aiwritesdependency-updaterAutomated dependency update execution with breaking change detection and rollback capabilitya5c-aiwritesdepsVisualize and analyze issue dependencies in Linear. Finds blocking chains, circular dependencies, and critical path items.majiayu000depsVisualize and analyze issue dependencies in Linear. Finds blocking chains, circular dependencies, and critical path items.majiayu000depth-searchDeep multi-source research combining academic MCPs (arxiv, semantic-scholar, paper-search, deepwiki), Exa semantic search, and…majiayu000describe-canonical-locationsFile locations for laws, style, phases, and docs. Load when locating or creating Ushabti state files.majiayu000detect-atr-squeeze-regime以 14 日指數平滑 ATR 偵測市場是否從秩序型趨勢轉為波動主導的擠壓(squeeze)行情,並輸出對技術位、停損、交易持有期的可行性評估。majiayu000detect-fed-unamortized-discount-pattern檢查聯準會持有證券的未攤銷折價(Unamortized Discounts)是否出現與特定歷史危機期間相似的走勢模板,並用多指標交叉驗證是否真的屬於「金融壓力升高」而非單純會計/利率效果。majiayu000detect-freight-led-inflation-turn透過美國卡斯貨運指數 (CASS Freight Index) 的週期轉折,偵測美國通膨壓力是否進入放緩或反轉階段。用於判斷「通膨是否正在降溫」,並驗證市場對降息、通膨回落的宏觀敘事是否有實體經濟數據支撐。majiayu000detect-palladium-lead-silver-turns以鈀金的先行轉向作為確認條件,檢驗白銀短期漲跌是否獲得工業景氣與風險情緒的同步支持,並標記缺乏鈀金參與度的失敗走勢。majiayu000detect-recurrence-patternDetect recurring patterns in issues and events. Identifies temporal, resource-based, cluster, and cascading patterns. Suggests…majiayu000detect-shanghai-silver-stock-drain以公開交易所庫存資料為核心,量化上海白銀庫存耗盡的方向、速度與加速度,並將其轉成可交易的供給緊縮訊號。majiayu000detecting-stalenessScan all artifacts for confidence metadata and report staleness using pure derived scoring.majiayu000writesdev-askAnswer a question with facts only. No changes, no suggestions, no opinions. Brief and precise. Usage: /dev-ask <question>majiayu000dev-explainExplain something in detail with investigation. No changes, no suggestions, no opinions. Facts and technical depth only. Usage…majiayu000dev-work-summaryScan ~/dev recursively for git repos and report today's work with commits, branches, stats, and detailed change analysis. Use…majiayu000writesdevbooks-entropy-monitordevbooks-entropy-monitor:定期采集系统熵度量(结构熵/变更熵/测试熵/依赖熵),生成量化报告,当指标超阈值时建议重构。用户说"熵度量/复杂度趋势/重构预警/代码健康/技术债务度量"等时使用。majiayu000writesdevbooks-impact-analysisdevbooks-impact-analysis:跨模块/跨文件/对外契约变更前做影响分析,产出可直接写入 proposal.md 的 Impact 部分(Scope/Impacts/Risks/Minimal Diff/Open…majiayu000writesdevcomInvoke DEVCOM_RESEARCH for deep research, cross-disciplinary analysis, and novel problem solving. Use when exploring cutting-edge…majiayu000developer-churnWhen the user wants to understand, reduce, or recover from developer churn. Trigger phrases include "why developers leave,"…sickn33developer-portal-builderBuild unified developer portals with Backstage or custom frameworksa5c-aiwritesdevils-advocateSystematically challenge current assumptions before major decisions. Counters confirmation bias, groupthink, and overconfidence.majiayu000devils-advocateSystematically challenge current assumptions before major decisions. Counters confirmation bias, groupthink, and overconfidence.majiayu000devils-advocateUse when a proposal has unanimous support or relies on a single high-impact assumption—constructs the strongest possible…majiayu000
← Prev63 / 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