Implement a feature safely with planning, focused edits, tests, docs, and verification.
Implement a feature safely with planning, focused edits, tests, docs, and verification.
npx skills add https://github.com/s-hiraoku/claude-harnesses --skill feature-implementationこのコマンドをClaude Codeにコピー＆ペーストしてスキルをインストール
Teach the human everything that happened in this session until they can demonstrably explain it, using an incremental checklist, restate-first probing, and AskUserQuestion quizzes. Use after a non-trivial change, debugging session, or hand-off when the goal is the human's understanding, not just a working result.
Inspect recent Claude Code activity (history, sessions, shell, existing assets), surface repeated patterns, and promote only the high-confidence ones into Skills, subagents, or hooks. Read-only investigation; creation is gated by user approval.
Iteratively improve a skill or prompt by having a fresh subagent execute it against fixed scenarios, scoring two-sided (executor self-report + a pre-frozen requirements checklist), and looping until improvements plateau. Use after authoring or revising any skill, slash command, or CLAUDE.md addition.
Fix bugs with reproduction, minimal changes, regression coverage, and targeted verification.
Remove AI-generated boilerplate (vague comments, unused try/except, defensive validation, restated docstrings) from changed code without changing behavior.
Update documentation after code or behavior changes while keeping docs concise and relevant.
| name | feature-implementation |
| description | Implement a feature safely with planning, focused edits, tests, docs, and verification. |
Use this workflow when adding or changing product behavior.
Include:
