
from my-cc-harness118
Interactive interview workflow that elicits a detailed SPEC.md specification through targeted, in-depth questions to produce an implementable spec.
This skill runs a structured, in-depth interview to produce or refine a SPEC.md specification for a feature. It walks a user (or an agent) through technical, UI/UX, security, scalability, and trade-off questions and then drafts a comprehensive SPEC.md ready for handoff to implementation.
Use this when you need a complete, well-scoped specification before implementation: new feature design, product interviews, or handoff-ready specs for engineering teams. It's NOT for immediate code writing or small fixes — it focuses on design and decisions.
Likely compatible with code-focused assistant environments and agents that support interactive tooling and file read/write (e.g., Claude Code, Codex-style assistants, Cursor).
This skill has not been reviewed by our automated audit pipeline yet.
Harness Health Audit
Assess and score the overall health of a Claude Code harness across architecture, skills coverage, hooks, rules, MCP servers, eval pipelines, and team setup.
Code Evaluation Harness
Spawns an independent evaluator agent to score code outputs on functionality, code quality, originality, and usability/security, producing a structured EVAL_REP
Test-Driven Development (TDD)
Guided Test-Driven Development workflow: write failing tests first (RED), implement minimal code (GREEN), then refactor while keeping tests passing.