Guidance and snippets for creating/updating Codex skills tailored to the mcp-coding-agent project (AST/dependency tooling). Use when asked to build a new skill or refine one for this repo’s workflows and structure.
Standardize Figma-to-code workflow using Figma MCP - always get_design_context first, then screenshot, use project tokens not hardcoded values, validate 1:1 parity
Defines the rules and constraints for generating code from Figma designs using MCP in this project.
Executable documentation governance with compound engineering and abductive learning. Enforces the Seven Laws through type compilation, schema validation, and hookify-based enforcement. Implements programmatic compound engineering where K' = K ∪ crystallize(assess(τ)) for monotonic knowledge growth. Integrates abstracted abductive learning (OHPT protocol) for systematic debugging and pattern extraction. Trigger when writing code, debugging, establishing governance, or when mentioned vibecode, compound, abductive, or executable documentation. Self-validating and homoiconic.
Édition de code par symboles avec Serena MCP. Utiliser pour modifier des fonctions, hooks, ou composants de manière précise sans réécrire des fichiers entiers.
【WHEN】当用户命令中明确包含"codex协作"、"codex协同"、"与codex合作"等指令时启用； 【WHEN】当用户要求使用 codex MCP 工具进行代码分析、原型生成、review 等协作开发场景时启用。 【WHEN NOT】不用于单独的代码实现任务、不用于纯文档编写、不用于不涉及 codex 的常规开发流程。
Sets up Jira MCP server integration for Claude Code. Use when setting up Jira, connecting to Atlassian, configuring MCP for ticket management, or adding Jira capabilities.
Use when user needs complex data queries, multi-entity joins, aggregations, or analysis across Affinity data. Also use when user wants to filter, group, sort, or aggregate CRM records programmatically. Triggers: "query language", "structured query", "SQL-like", "find all persons where", "count opportunities by", "sum deal values", "average amount", "group by status", "filter AND/OR", "include companies with persons".
Enables Claude to upload, organize, search, and manage files in Google Drive via Playwright MCP
Notion MCPを使って社内ナレッジ検索/追記/整理を行う。議事録や調査結果をNotionに残す時に使う。
Enables Claude to create, manage, and organize tasks in Google Tasks via Playwright MCP
Operate the local Scribe MCP tools for logging, project setup, manage_docs workflows, read_file usage, bridge integrations, and sentinel/project mode discipline. Use whenever you need to follow Scribe tool contracts, document management rules, or bridge development.
Enables Claude to create and edit websites using Google Sites via Playwright MCP
Enables Claude to create, organize, and manage notes and lists in Google Keep via Playwright MCP
Collect and summarize LinkedIn home feed posts using the Playwright MCP. Use when you need to (1) open linkedin.com/feed, (2) extract N feed posts while scrolling, (3) exclude ads/"Promoted" and non-post modules (jobs, in-app promotions), and (4) produce a grouped brief with keywords, per-post core title + insight, and a source link (prefer permalink; fallback to URN-based feed/update URL).
Enables Claude to access, organize, and collaborate on Microsoft SharePoint sites and document libraries via Playwright MCP
Enables Claude to create, edit, and present Microsoft PowerPoint presentations via Playwright MCP
从飞书项目单子自动生成OPML格式的XMind测试用例。通过飞书项目MCP读取需求描述、验收标准和技术设计文档，梳理用户操作流程后生成结构化测试用例。在用户需要为飞书项目单子生成测试用例、创建XMind思维导图测试用例或需要OPML格式测试文档时使用。
