Skills & Agent Building
5,949 results
- Bkit BuildcbartensBuild Feature — Autonomous implementation
- Bkit BuildcbartensBuild Feature — Autonomous implementation
- Bkit DebugcbartensDebug Feature — Autonomous diagnosis and remediation
- Bkit DebugcbartensDebug Feature — Autonomous diagnosis and remediation
- Bkit PlancbartensPlan Feature — Autonomous plan generation
- Bkit PlancbartensPlan Feature — Autonomous plan generation
- Bkit ShipcbartensShip Feature — Autonomous merge and archive
- Bkit ShipcbartensShip Feature — Autonomous merge and archive
- Boardeggs-gdRender a static HTML dashboard of every vacancy in data/vacancies/ — grouped by status, sorted by fit score, with real clickable links to each vacancy's fitment/posting/CV/cover letter. No server, open the file directly in a browser. Use when the candidate wants an overview of everything tracked, not one specific posting ("покажи дошку", "show me the board", "what's the status of everything").
- Brainlib Capturemingweima把用户说的、写的，以及值得留下的观察和资料记进大脑库的收件箱，并标清来源；回答和用户有关的问题前先查库。用户说“记住……”、表达偏好、做了决定，或问到自己的事时使用。
- Brainlib Maintainmingweima给大脑库做体检（断链、过期、冲突、缺说明），理解 L0 到 L3 分层和笔记开头的字段，帮用户查找和归档。brainlib next 提示 health，或者用户想整理库的结构时使用。
- Brainlib Onboardingmingweima用 10 道选择题弄清用户想怎么用大脑库（用途、涉及哪些方面、权限、隐私、节奏、提问方式），并随着时间更新答案。brainlib next 提示 onboarding 或 revisit，或者用户说想改设置时使用。
- Brainlib Organizemingweima把收件箱整理成修改建议，和用户一起审批，然后应用、拒绝或留到以后；也包括撤销和自己提建议。brainlib next 提示 classify、review 或 auto-apply 时使用。
- Brainlib Privacymingweima隐私分级、加密保险箱、密码拦截、私有词表和分享前的检查。处理敏感内容、设置保险箱、发现库里有密码，或者要把库或代码仓库分享出去时使用。
- Brainlib Setupmingweima第一次在一台电脑上安装和设置 brainlib：检查 Python、做自测、选语言、定库的位置、开系统权限和工具权限、把用户的 AI 工具接上大脑库。用户说“帮我装大脑库”“设置 brainlib”，或换了电脑、换了 AI 助手时使用。
- Building MCP ServersceligoBuild Celigo MCP server resources -- endpoints that expose Tools and builder-mode APIs to external AI agents and MCP clients. Use when creating MCP servers, linking tools or APIs, or configuring annotations and overrides.
- Building ToolsceligoBuild Celigo tool resources -- reusable building blocks that encapsulate lookups, imports, transforms, and branching behind input/output contracts. Callable from flows, APIs, AI agents, MCP servers, and other tools. Use when creating tools, adding steps, or configuring routing.
- CavemanoneafrikanUltra-compressed replies, no filler or hedging, technical accuracy kept. Use when the user says "caveman mode", "spartan mode", "terse", "be brief" or "less tokens".
- ckeditor/skillsCKEditor EcosystemCollectionAgent skills to help developers using AI agents with CKEditor
- Claude Agent Sdk BuilderdwfennellGuide for building agents with the Claude Agent SDK (TypeScript/Node.js). Use when creating SDK-based agents, custom tools, in-code subagents, or production agent applications. Provides templates, patterns, and best practices for agent development.
- cockroachdb/claude-pluginCockroachDBCollectionCockroachDB development plugin for Claude
- Code AnalyzerrafaelcallejaThis skill should be used when the user asks to "analyze code", "review code quality", "check code structure", "find code patterns", or mentions code analysis without making changes.
- Communication Logeggs-gdPreserve raw recruiter/client correspondence, approvals, confirmations, interview notes, feedback, or candidate replies under the matching vacancy or engagement as communication.md. Use when the candidate asks to save or log a communication history for an opportunity.
- ConfigureCivalskiClauJev preferences menu and guided setup. Asks the user, in their own language, the basic preferences (language, mode, which features to keep, automatic effort, status line) and saves them. Use when the user runs /claujev:configure, asks to configure ClauJev or Jev, change its language or mode, turn a ClauJev feature on or off, or accepts the guided setup offered on ClauJev's first session.