一键导入
claude_harness_eng_v1
claude_harness_eng_v1 收录了来自 cwijayasundara 的 18 个 skills,并提供仓库级职业覆盖和站内 skill 详情页。
这个仓库中的 skills
Autonomous build loop with Karpathy ratcheting, GAN evaluator, and session chaining. Iterates story groups until all features pass or stopping criteria met.
Socratic interview to create a Business Requirements Document. First step in the SDLC pipeline.
Generate system architecture, machine-readable schemas, and UI mockups. Spawns planner + ui-designer concurrently.
Evaluation patterns — sprint contract format, three-layer verification, scoring rubric references.
Standard GitHub issue workflow. Branch, reproduce, fix, test, PR.
Generate production code and tests for a story group using agent teams for parallel execution.
Refactor existing code for quality, performance, or maintainability. Enforces six quality principles with ratchet gate.
Code generation quality principles — TDD, typing, error handling, logging, API integration, LLM integration.
Full SDLC pipeline. Runs all phases end-to-end with human gates on phases 1-3.
Generate Docker Compose stack, Dockerfiles, environment config, and init.sh bootstrap script.
Run the application and verify sprint contract criteria via API tests, Playwright interaction, and schema validation.
Enhance existing features through story-driven development with full verification.
Scan codebase for pattern drift and generate targeted cleanup PRs. Entropy control for agent-generated code.
Run evaluator and security reviewer concurrently for comprehensive quality gate.
Decompose BRD into epics, stories, dependency graph, and feature list for agent team execution.
Generate test plan, test cases, test data fixtures, and Playwright E2E tests mapped to acceptance criteria.
Layered architecture rules — one-way imports, module boundaries, file organization.
Testing patterns — Playwright E2E, test structure, fixture management, mock boundaries.