Use when creating or editing skills, before deployment, to verify they work under pressure and resist rationalization - applies RED-GREEN-REFACTOR cycle to process documentation by running baseline without skill, writing to address failures, iterating to close loopholes.
A workflow for connecting an application to an outside service such as payments, messaging, login, text messages, file storage, maps, or an AI provider.
Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection and safety verification.
Use when starting any conversation - establishes mandatory workflows for finding and using skills, including using Skill tool before announcing usage, following brainstorming before coding, and creating TodoWrite todos for checklists.
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always.
End-to-end workflow that writes Chinese WeChat tech articles from either the latest tech news or a user-provided custom topic, with source verification, readable technical depth, and ready-to-paste inline HTML. Use when asked to write a WeChat article, custom topic tech post, AI weekly, 科技新闻 / 科技周报, 公众号, 微信文章, or AI…
Use when design is complete and you need detailed implementation tasks for engineers with zero codebase context - creates comprehensive implementation plans with exact file paths, complete code examples, and verification steps assuming engineer has minimal domain knowledge.
Use when creating new skills, editing existing skills, or verifying skills work before deployment - applies TDD to process documentation by testing with subagents before writing, iterating until bulletproof against rationalization.
Engineering Harness as MCP server + CLI: ship a complete software engineering governance kit (spec, skills, rules, templates, checks) to any AI IDE (Cursor, Claude Code, Codex) with one config line. Runs locally from the harness-engineering-mcp npm package.