Agent skills you can check before you install
Public SKILL.md skills from GitHub repositories with 50+ stars and from the vendors themselves, scanned and scored. Install any of them with one command in Claude Code, Cursor, Codex, GitHub Copilot or Gemini CLI.
46,100 skills from 2,198 repositories · updated 39 minutes ago
9,541 skills
- hyperframes-registrycoco-research/cocoInstall, discover, and wire registry blocks and components into HyperFrames compositions. Use when running hyperframes add or hyperframes catalog, installing one item or every block matching a tag, wiring an installed item into index.html, or working with hyperframes.json. Covers discovery, install locations, block sub-composition wiring, component snippet merging, and authoring a new block or component to contribute upstream (idea → scaffold → validate → PR).OtherNo warnings★ 795↓ —
- Strix•标准扫描asdfgh1445/ctf-super-hubStrix 标准安全评估模式,在系统性与覆盖率之间保持平衡;触发名:strix-standardOtherNo warnings★ 840↓ —
- history-recallOutlineDriven/outline-driven-developmentUse when a user requests the reasoning behind one matched session by query or handle. Not for peer transfer: use history-sync. Not for store registration: use history-source-registry.OtherNo warnings★ 55↓ —
- timeline-creatormhattingpete/claude-skills-marketplaceCreate HTML timelines and project roadmaps with Gantt charts, milestones, phase groupings, and progress indicators. Use when users request timelines, roadmaps, Gantt charts, project schedules, or milestone visualizations.OtherNo warnings★ 689↓ —
- lock-decisiondrobins25/craftThis skill should be used when the user says "lock it", "go with that", "approved", "that's the standard", or explicitly establishes a project-wide pattern like "from now on all forms should use this approach". Formalizes approved decisions into locked standards that the system enforces going forward. Not needed for story-scoped decisions — only for project-wide patterns.OtherNo warnings★ 70↓ —
- find-skillsnaveedharri/benai-skillsHelps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.OtherNo warnings★ 76↓ —Also in 2 other repos
- Prometheus Alert Routeragentskillexchange/skillsRoutes and escalates Prometheus AlertManager notifications based on severity and label matchers. Integrates with PagerDuty, Opsgenie, and Slack webhook APIs for multi-channel incident routing.OtherNo warnings★ 58↓ —
- setupOutlineDriven/outline-driven-developmentUse when the user asks to set up the agent environment. Covers credentials, placeholders, tool access checks, a uv venv, a pack install, or a role-model mapping file. Not for unattended runs.OtherNo warnings★ 55↓ —
- feedback-sweepOutlineDriven/outline-driven-developmentUse when asked to /feedback-sweep [setup|reconfigure] [mode:non-interactive]. Not for pattern discovery: use feedback-pattern-sweep.OtherNo warnings★ 55↓ —
- GraphQL Schema Analyzeragentskillexchange/skillsAnalyzes GraphQL schemas using graphql-js introspection and @graphql-tools/utils. Maps type relationships, detects N+1 query patterns, and generates DataLoader batching recommendations.OtherNo warnings★ 58↓ —
- find-skillscoco-research/cocoHelps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.OtherNo warnings★ 795↓ —
- teachOutlineDriven/outline-driven-developmentUse when the user wants a course, a learning workspace, or ongoing teaching across sessions, with cited lessons and retention-gated advancement. Not for one-off explanations: use explain-concept.OtherNo warnings★ 55↓ —
- assignation-refere-recouvrement-creance-selim-brihilawve-ai/awesome-legal-skillsRédaction d'assignations en référé devant le tribunal de commerce ou des activités économiques pour le recouvrement de créances commerciales. Utiliser ce skill quand l'utilisateur demande de rédiger, préparer ou créer une assignation en référé pour obtenir le paiement d'une créance impayée (factures, prestations de services, ventes de marchandises, etc.) lorsque le débiteur n'a pas honoré ses obligations de paiement et qu'il n'existe pas de contestation sérieuse.OtherNo warnings★ 911↓ —
- decideOutlineDriven/outline-driven-developmentUse when the user has a fork and wants it resolved and applied, not explored: "decide this", "choose the path", or "decide and fix it".OtherNo warnings★ 55↓ —
- catchupOutlineDriven/outline-driven-developmentUse when the human returns after a gap, cannot follow the project, asks what happened, or wants a visual HTML recap page. Not for onboarding: use onboard. Not for handoff: use handoff.OtherNo warnings★ 55↓ —
- devexpress-wpf-mvvmDevExpress/agent-skillsBuild WPF applications with the DevExpress MVVM Framework — view-model strategies (compile-time GenerateViewModel source generator, runtime POCO ViewModelSource, ViewModelBase, BindableBase), DelegateCommand/AsyncCommand, predefined services (IMessageBoxService, IDialogService, IDocumentManagerService, INotificationService, INavigationService, IDispatcherService), behaviors (EventToCommand, KeyToCommand, FocusBehavior, ConfirmationBehavior), and view-model communication (ISupportParameter, ISupportParentViewModel, Messenger). Use when choosing a view-model strategy (recommend compile-time GenerateViewModel for new projects); wiring commands via [GenerateCommand]/[Command]; calling services via GetService<T>(); adding behaviors via dxmvvm:Interaction.Behaviors; or passing data between view models. Also use when someone mentions "ViewModelSource", "DXMessageBoxService", "DialogService", "EventToCommand", "Messenger.Default", "DevExpress.Mvvm", or "dxmvvm:".OtherNo warnings★ 66↓ —
- cost-reductionOutlineDriven/outline-driven-developmentUse when a measured cost surface needs one-change-at-a-time reduction under frozen guardrails. Not for speed-only optimization: use optimize.OtherNo warnings★ 55↓ —
- Unified AI System Gatewayagentskillexchange/skillsTurn plain-language requests into structured, reviewable prompts and inspect a self-hosted MCP gateway with provider-free defaults.OtherNo warnings★ 58↓ —
- requete-cph-licenciement-faute-grave-selim-brihilawve-ai/awesome-legal-skillsRédaction de requêtes devant le Conseil de prud'hommes pour contester un licenciement pour faute grave. Utiliser ce skill quand l'utilisateur demande de rédiger une requête CPH, contester un licenciement pour faute grave, préparer une saisine du CPH pour un litige lié à un licenciement, ou créer un document de contestation de licenciement en droit du travail français.OtherNo warnings★ 911↓ —
- seed-casebookOutlineDriven/outline-driven-developmentUse when a user opens a build cycle in a repo with an iteration convention and wants the casebook seeded with real content. Not for ongoing triage or multi-repo setup.OtherNo warnings★ 55↓ —
- handoffOutlineDriven/outline-driven-developmentUse when work reaches a session boundary or the user asks to hand off, delegate, or get a clipboard-ready prompt. Mode brief packages continuity; mode prompt builds the delegation prompt.OtherNo warnings★ 55↓ —
- alpha-deskJingHao-Leon/dsh-alpha-deskAI 投研工作台——在 deepseek-harness 里编排 virattt/ai-hedge-fund（美股多策略 AI 基金，支持回测）、iFinD 权威数据源（经 plugins/ifind 访问，财报/公告/股东/预测/选股，A股港股美股）与本地 A股/港股技术分析技能，配合 risk-gate 风控钩子、定时盯盘与投资记忆，完成"分析→回测→解读→复盘"的完整投研闭环。当用户要求分析美股、运行 AI 基金、回测策略、比较投资大师观点、生成投研报告、定时盯盘、复盘投资假设，或查询财报/财务报表/公告/股东户数/业绩预测/智能选股/iFinD/同花顺数据时使用。触发词：AI 基金、对冲基金、回测、巴菲特、格雷厄姆、投研、美股分析、盯盘、复盘、iFinD、同花顺、股东户数、财务报表、公告、业绩预测。OtherNo warnings★ 168↓ —
- Check Agent Counterparty Trust with Agent Guildagentskillexchange/skillsChecks evidence about an unfamiliar autonomous agent before delegation, verifies signed Agent Guild passports, and returns a bounded hire, caution, or avoid recommendation without taking consequential action.OtherNo warnings★ 58↓ —
- post-to-slackOutlineDriven/outline-driven-developmentUse when the user explicitly asks to share a message on Slack through an incoming webhook. Not for posting without an explicit request or for retrying an ambiguous delivery.OtherNo warnings★ 55↓ —
constitutional-ai
KalarisLabs/research-agent-skills
OtherUpdated 4 days ago
From the author
Anthropic's method for training harmless AI through self-improvement. Two-phase approach - supervised learning with self-critique/revision, then RLAIF (RL from AI Feedback). Use for safety alignment, reducing harmful outputs without human labels. Powers Claude's safety system.
Install
npx skills add KalarisLabs/research-agent-skills --skill constitutional-ai -a claude-code
Installs to .claude/skills/constitutional-ai/ · Each command fetches the skill straight from GitHub with the open skills CLI.
Download .zip
Byte-identical to the scanned commit, with the repository’s licence and a SOURCE.txt.
What it can touch
Instructions onlyNo network use seenLicence: MIT
Safety checks on SKILL.md
No warnings.
Why 82
Security100
Provenance62
Maintenance100
Licence100
Adoption32
Files (1)
- SKILL.md