
from my-cc-harness118
Create structured implementation plans for multi-step or architectural changes before coding — defines success criteria, trade-offs, and stepwise tasks.
This skill produces a detailed implementation plan before starting complex work. It guides the agent to define success criteria, list assumptions and constraints, compare alternate approaches, break the work into ordered steps (with estimated complexity and verification), and record risks and mitigations. The output is an actionable markdown checklist suitable for review and checkpoints.
Use this skill when a requested change involves 3+ steps, architecture decisions, multiple files, or ambiguous success criteria. Avoid for one-line edits or clear bug fixes. Triggers include requests to "plan", "design", "architecture", "how to implement", and Korean equivalents like "계획", "설계", "플랜".
Works with agents that can read and edit code and files (Codex/Claude-Code/CLI tooling). The skill expects access to repository files when used in a workplace automation flow.
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
SPEC-Based Development Interview
Interactive interview workflow that elicits a detailed SPEC.md specification through targeted, in-depth questions to produce an implementable spec.
Test-Driven Development (TDD)
Guides an agent through the TDD cycle: write a failing test, implement minimal code to pass, then refactor. Useful for disciplined feature development and maint