Skill UI

Context Engineering Protocol optimizes agent sessions by curating persistent rules, specs, source files, and feedback so outputs stay focused, accurate, and aligned with conventions whenever you start work or the quality drops.

Explores Feishu/Lark native OpenAPI docs when existing lark-* skills or CLI commands lack coverage, fetching markdown indexes stepwise to surface raw API specs and ready-to-run `lark-cli api` invocations.

Maintains the repository's llms.txt guidance file by auditing current documentation, specs, and structure to ensure the navigation summary matches reality and stays compliant with the official specification.

This skill automatically converts structured data specifications (such as CSV, JSON schemas, SQL DDL, or Protobuf definitions) into functional, production-ready code. It generates complete models, validation logic, full CRUD API endpoints, and unit tests in multiple languages (Python, TypeScript, Go, etc.), significantly reducing boilerplate coding time and ensuring type safety.

This skill orchestrates the entire development lifecycle for approved software tasks. It operates in autonomous or manual modes, rigorously applying Test-Driven Development (TDD). It automatically gathers all necessary context (specs, requirements, design, and historical learnings), validates the repository state, and dispatches specialized sub-agents to implement tasks one by one, ensuring high code quality, adherence to design, and process traceability.

This tool systematically converts a project roadmap into actionable specifications. It first analyzes features by grouping them into dependency waves. It then automatically dispatches sub-agents to generate complete feature specs (requirements, design, tasks, and JSON) for each wave. The core value lies in its comprehensive cross-spec review, which verifies data model consistency, interface alignment, and architectural integrity across the entire project, ensuring a cohesive final product.

This utility conducts a thorough audit of project documentation against the current codebase to ensure complete consistency. It supports 'delta' (detecting changes since merge-base) or 'full' auditing modes. By utilizing Impact Mapping and verifying cross-reference pairs, it identifies outdated specs, missing documentation, or inconsistent references across the entire project ecosystem.