Agent
A document-to-HTML preview agent that turns Markdown into a visual review page. Depending on the document, it can show an interaction prototype, diagram, timeline, dependency map, or acceptance checklist.
Agent
A read-only quality check for mini-app projects, covering type safety, builds, templates, and required technical rules. It produces a dated report with an acceptance result.
Agent
A coding specialist for WeChat Mini Programs built with Taro and React. WeChat Mini Programs are small apps that run inside WeChat, while Taro is a framework for building them with web-style code.
Agent
A testing specialist for WeChat Mini Programs, which are small apps that run inside WeChat. It defines what to check for builds, releases, page registration, generated assets, and related project rules.
Agent
运行时边界统一参考：${CLAUDEPLUGINROOT}/protocols/runtime-boundaries.md.
Agent
A read-only reviewer for a project's folders, documentation, code modules, tests, demos, and AI-generated project files. It checks whether the structure is easy for coding agents to understand and work within.
Agent
A read-only acceptance reviewer for Playwright end-to-end tests, which test a complete user flow in a browser. It compares demo tests with their user stories, compiles and runs them, and records an acceptance result.
Agent
A developer workflow for Playwright end-to-end tests, which exercise a web application through a browser like a user. It creates or repairs demo tests from user stories and design documents.
Agent
An agent that diagnoses failed demo tests, especially browser tests run with Playwright. It reads logs and related code, classifies the likely cause, and writes a diagnostic report without changing business code.
Skill Claude CodeCodex
Decide whether a feature should enter the t-tools workflow before tech research or PRD.
Skill Claude CodeCodex
Evaluate technical design documents for implementability, completeness, and consistency with a quantitative 100-point score.
Skill Claude CodeCodex
Generate technical design documents including API design, database schema, and implementation details for a feature.
Skill Claude CodeCodex
Generate project tutorial documentation that reads like a human wrote it, not like AI output. Scans the codebase, extracts architecture/APIs/config/deployment details, and writes structured tutorial docs in the project's documentation target, preferring an existing docs-web site over docs/tutorials/. Use this skill…
Skill Claude CodeCodex
Organize and realign PRDs, user stories, design/task docs, implementation facts, and project structure so the target project keeps a clean current context instead of accumulating stale or misleading information. Use when asked to audit documentation drift, structure drift, traceability gaps, whether PRD/code/test/demo…
Skill Claude CodeCodex
Discover, download, flatten, convert, place, and verify image/video assets for a Figma UI implementation.
Skill Claude CodeCodex
Precisely refine one Figma UI region in an existing implementation and distill validated project rules.
Skill Claude CodeCodex
Reconstruct and implement a complete Figma UI in an existing frontend file, using prepared assets and measurable acceptance.
Skill Claude CodeCodex
Standalone motion-refinement entry that polishes interaction and animation of an already-implemented UI, using Figma prototype evidence and animation principles distilled for interfaces.
Skill Claude CodeCodex
Accept Android Patrol demos against their user stories and execution evidence.
Skill Claude CodeCodex
Run all Android Patrol user-story demo files with resumable checkpoints.
Skill Claude CodeCodex
Run and repair one Android Patrol user-story demo file.
Skill Claude CodeCodex
Generate or update an HTML Preview for a Markdown document.
Skill Claude CodeCodex
Initialize a full-stack project skeleton with Rust backend (Axum + SeaORM + Redis) and React frontend (TypeScript + TanStack + Tailwind).
Skill Claude CodeCodex
Validate draft PRD, published PRD baseline, and user stories for quality and consistency.