Loading…
Showing 6301–6330 of 10177 skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| claude-spec-interviewerstark-ai-de/agent-skillsTurn ambiguous coding requests into verified Claude Code implementation specs. Use when the user wants requirements, an implementation plan, or a spec before coding; include source checks, needed ADRs, and agreed delivery. Do not use for already specified direct implementation or memory cleanup. | Stars: 8 | Updated | Claude CodeCodex | Verified | Install |
| cursor-spec-interviewerstark-ai-de/agent-skillsTurn ambiguous coding requests into verified Cursor Agent implementation specs. Use when the user wants requirements, an implementation plan, or a spec before coding; include source checks, needed ADRs, and agreed delivery. Do not use for already specified direct implementation or memory cleanup. | Stars: 8 | Updated | Claude CodeCodex | Verified | Install |
| adopt-agent-policyYuimi-chaya/codex-development-guidelinesConfigure Codex user-level AGENTS.md when the user asks to install, adopt, or update these guidelines. Inspect the actual environment, relevant Codex configuration, and exposed models first; research public model facts, recommend a configuration, collect unresolved preferences together, and apply the authorized changes. Honor an explicit project-level target. Reviewing the repository or ordinary coding does not request installation. | Stars: 6 | Updated | Claude CodeCodex | Verified | Install |
| swiftui-expert-skilldeonmenezes/mobile-app-skillUse when writing, reviewing, or refactoring SwiftUI code for iOS or macOS, including state and `@Observable` data flow, view composition, resizable layouts, safe areas, display scale, performance, lists, environment, localization, animation, Liquid Glass, and API migration. Also use for iPhone Duo, foldable, or large-display layouts (`NavigationSplitView` on large displays, iPhone tab sidebar, two-column reflow, foldable grids, `ArrangementView`, `ReservedRegion`), hinge effects, vertical bars, `@State` initialization or synthesized-property diagnostics, `@ContentBuilder` ambiguity, `reorderable` drag/drop, custom `AsyncImage` `URLSession`, swipe actions outside List, item-bound `alert`/`confirmationDialog`, `ToolbarOverflowMenu`, `AnimatableValues`, Document APIs (`Document`/`DocumentReader`), and Instruments `.trace` capture or analysis. | Stars: 7 | Updated | Claude CodeCodex | Verified | Install |
| nobrainer-teamnobrainer-tech/nobrainer-tech-flowUse when an approved non-trivial plan from nobrainer-tech-flow needs an installed-capability inventory, bounded worker assignments, task-local specialist briefs or native parallel execution; do not use to elicit requirements, invent the plan, schedule work, or create sessions. Aliases: nb-team, nobrainer-skill-browser. | Stars: 7 | Updated | Claude CodeCodex | Verified | Install |
| codex-ccDianel555/DSkillsDelegates coding tasks from Codex to local Claude Code in print mode while preserving Claude's normal runtime customizations by default. Use when: (1) You want Codex to call Claude Code locally, (2) You need Claude-side skills, plugins, MCP servers, custom commands, CLAUDE.md rules, or workspace settings to stay active, (3) You want resumable Claude sessions from Codex via SESSION_ID, (4) You need thin `claude mcp` / `claude plugin` passthrough from the same bridge. | Stars: 65 | Updated | Claude CodeCodex | Unverified | Install |
| skillspzfreo/draftwright-python | Stars: 104 | Updated | Claude CodeCodex | Verified | Install |
| shopify-multi-storealex-brecher/shopify-multi-storeConnect, query, compare, report on, and manage multiple Shopify Admin stores from Claude, Codex, Cursor, or another MCP client. Use for multi-store ecommerce reporting, portfolio summaries, catalogs, orders, inventory, customers, parallel GraphQL reads, and guarded store updates. | Stars: 5 | Updated | Claude CodeCodex | Verified | Install |
| data-privacy-complianceJPeetz/agent-skillsUse this skill when handling PII, personal data, privacy regulations, data subject requests, consent management, data breach response, or any GDPR/CCPA/HIPAA compliance task. Provides structured privacy compliance workflows based on regulatory frameworks. | Stars: 19 | Updated | Claude CodeCodex | Verified | Install |
| local-video-production-m5JPeetz/agent-skillsUse this skill when producing local videos on the 16GB M5 executor. | Stars: 19 | Updated | Claude CodeCodex | Verified | Install |
| orchestrationdayfinggg/openai-codex-agent-skillsPlan or coordinate explicitly authorized multi-agent work, including worker briefs, model selection, independent workstreams, integration, and review rounds. | Stars: 8 | Updated | Claude CodeCodex | Verified | Install |
| favcrm-channel-setupfavcrm/mcpUse when checking or connecting FavCRM communication channels, especially WhatsApp Business Embedded Signup from an MCP client or the favcrm CLI. | Stars: 0 | Updated | Claude CodeCodex | Verified | Install |
| favcrm-team-onboardingfavcrm/mcpUse when inviting a teammate to FavCRM, generating a one-time team invite token, accepting an invite, verifying an emailed invite OTP, or issuing an MCP API key for an invited team member. | Stars: 0 | Updated | Claude CodeCodex | Verified | Install |
| ml4t-agent-tool-contractssb-dev/openquantDefine typed and bounded research tools with provenance and policy enforcement outside the model. Use when exposing provider retrieval or evidence to agents. | Stars: 1 | Updated | Claude CodeCodex | Verified | Install |
| openquant-ai-engineeringsb-dev/openquantDevelop and evaluate OpenQuant proposer/critic behaviour, AgentExecutor adapters, structured results, context packs, prompt versions, execution isolation, and model regressions. Use for AI engineering changes in packages/agents or apps/agent-runner. | Stars: 1 | Updated | Claude CodeCodex | Verified | Install |
| bee-luaactboy168/bee.luabee.lua 运行时库指南——Lua 5.4/5.5 上的跨平台系统级绑定(异步 I/O、网络、子进程、线程、文件系统、文件监控、崩溃 dump)。当需要在本项目里编写、修改或排查使用 `require "bee.*"` 的 Lua 代码,涉及 socket/select/epoll/async、thread/channel/serialization、subprocess、filesystem/filewatch、time/sys/crash/debugging/windows,或需要按平台差异处理行为时,使用本 skill。即使用户没有明确提到 bee.lua,只要上下文是在调用 `bee` 命名空间下的模块,也应使用。不要用于纯 Lua 语言/标准库问题、与 bee 无关的第三方 C 模块,或本项目 C++ 层 `bee/`、`binding/` 的实现细节(那些看源码)。 | Stars: 195 | Updated | Claude CodeCodex | Verified | Install |
| termy-obsidian-contextbenoror/obsidianos_workUse when a Codex session launched from the Termy Obsidian plugin needs the current Obsidian note, selected text, active file, open files, vault root, workspace folders, or Termy-provided Obsidian context. Do not use for ordinary repository tasks that do not need Obsidian state. | Stars: 165 | Updated | Claude CodeCodex | Unverified | Install |
| package-agent-pluginpeter-gy/agent-pluginsPackage version-matched agent briefings with a Python project. Use when authoring core skills and references, exposing guidance through Python module help, configuring a build adapter, attaching a plugin to a wheel, or verifying installed handoffs. For consuming an installed package's instructions, use agent-plugins. | Stars: 5 | Updated | Claude CodeCodex | Verified | Install |
| project-quizRuisi-Lu/github-loop-engineering-skillBuild a multiple-choice quiz from a repository's merged pull requests and their issues, then run it with the user, teaching after every answer, so a newcomer learns why the project works the way it does. Read-only through the official GitHub MCP Server. Use only when the user explicitly invokes this skill or asks for a project quiz. | Stars: 8 | Updated | Claude CodeCodex | Verified | Install |
| custom-agent-usagebg-szy/TOP-SKILLSDiscover, validate, and invoke .agent.md custom agents. Use when finding agent files in the local Claude or VS Code Insiders directories, checking frontmatter, verifying disable-model-invocation, or determining agentName for runSubagent calls. | Stars: 6 | Updated | Claude CodeCodex | Verified | Install |
| skill-evolutionrwang23/skill-evolutionTurn repeated corrections, reviewer feedback, and usage evidence into Skill or harness proposals. Use for Skill evolution, routing regressions, evals or hooks, whether an incident should become a Skill rule, and 技能进化; not for applying edits. | Stars: 5 | Updated | Claude CodeCodex | Verified | Install |
| open-loopshaorantang97/LabKit当用户希望找回长对话中没有被看见、确认或明确取舍的信息点时使用。包括四类情况:用户提了但 AI 没答、AI 提了但用户没接住、AI 替用户做了选择,以及 AI 本该提问却自行决定。用户说「对账」 「建清单」「哪些没闭环」「open loops」,或抱怨对话跑偏、旧问题消失、AI 替自己做主时触发。 长项目进行到一半才开始审计,也属于正常入口。用户明确启用后,在该项目或任务中持续逐轮运行, 直到用户明确暂停或停止,不要求每轮重新点名。不要用于单轮编号问答、普通任务进度追踪,或用户 已经明确看见但暂缓执行的事项。仅检查、调试、修改或发布 Open Loops 本身的轮次属于维护通道: 可以使用本 skill 排障,但不得写进业务项目的原文存档或未闭环清单。 | Stars: 8 | Updated | Claude CodeCodex | Verified | Install |
| publish-to-githubhaorantang97/LabKitPublish a prepared AI skill or rule repository to GitHub, or repair an existing publication, using available CLI, API or browser tools. Use when the user asks to upload, push, create a GitHub repository or make it live. Covers repository metadata and verification of the published result. Use the authoring modules for unfinished content and submit-to-directories for community listings. | Stars: 8 | Updated | Claude CodeCodex | Verified | Install |
| axDiogenesoftoronto/keatingThis skill helps with using the @ax-llm/ax TypeScript library for building LLM applications. Use when the user asks about ax(), ai(), f(), s(), agent(), flow(), AxGen, AxAgent, AxFlow, signatures, streaming, or mentions @ax-llm/ax. | Stars: 40 | Updated | Claude CodeCodex | Unverified | Install |
| zoom-mcp/contact-center-adminzoom/skillsZoom Contact Center User Administration MCP guidance for users, queues, roles, skills, templates, routing profiles, inboxes, and phone numbers. | Stars: 93 | Updated | Claude CodeCodex | Verified | Install |
| zoom-mcp/meetingszoom/skillsZoom Meetings MCP server guidance for semantic meeting search, meeting assets, cloud recording listings, and recording-resource retrieval. Use for the dedicated Meetings MCP endpoint and its four read-oriented tools rather than meeting CRUD or generic Zoom search. | Stars: 93 | Updated | Claude CodeCodex | Verified | Install |
| zoom-mcp/productivityzoom/skillsZoom AI Productivity Suite MCP guidance for creating and managing Sheets. Use for the documented Sheets MCP tools and their OAuth scopes. | Stars: 93 | Updated | Claude CodeCodex | Verified | Install |
| zoom-mcp/revenue-acceleratorzoom/skillsZoom Revenue Accelerator MCP server guidance for conversation transcripts and analysis, scorecards, deals, customer accounts/contacts, indicators, teams, and users. Use when an AI agent needs read-oriented ZRA sales intelligence through the dedicated MCP endpoint. | Stars: 93 | Updated | Claude CodeCodex | Verified | Install |
| zoom-mcp/taskszoom/skillsZoom Tasks MCP server guidance for creating, reading, updating, trashing, commenting on, assigning, and collaborating on tasks and task steps. Use for agent-driven Tasks workflows over the dedicated Zoom Tasks MCP endpoint. | Stars: 93 | Updated | Claude CodeCodex | Verified | Install |
| context-window-and-token-economics-architectimMamdouhaboammar/anti-slop-engineeringReview LLM context selection, retrieval evidence, prompt cache boundaries, time to first token, and structured output contracts. Use for changes that affect what an LLM sees, reuses, or returns. | Stars: 5 | Updated | Claude CodeCodex | Verified | Install |