メニュー
Fix multiple review findings in one pass by discovering unaddressed reviews and addressing them all
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Use when evaluating, designing, or pressure-testing the business model of an AI agent product. Triggers on "agent business model", "agent economics", "agent canvas", "evaluate agent product", "agent pricing", "agent unit economics", "agentic business", "AI agent company", "agent cost structure".
Use when someone wants to launch a content brand from scratch on any platform. Triggers on "launch a channel", "start a YouTube channel", "build a podcast", "start a newsletter", "content brand", "creator launchpad", "build my audience", "start creating content", "grow on TikTok", "start a blog".
Use when you have an existing pipeline DOT file that needs review, fixing, or validation. Use when validation produces warnings or errors, when a DOT file was hand-written or generated by another tool, or when you want to verify a pipeline covers 100% of a spec before running it.
Use when you want to build a project but don't have a spec yet and need to brainstorm the idea into a design doc structured for pipeline DOT generation. Use when starting from a vague idea, project concept, or feature request that needs to become a headless autonomous build pipeline.
Use when you have a spec, design doc, structured plan, or prompt_plan and need to generate a pipeline Graphviz DOT file for headless autonomous building. The agent reads the spec, extracts build pipeline phases, determines tech stack, asks about human gates and model preferences, generates a validated DOT digraph with rich self-contained prompts, and saves it to the project root. Handles any language or framework.
Use when a pipeline DOT file has passed structural validation but may still have flow inefficiencies, spec fidelity gaps, or information loss in prompts. Use after dotfile-audit or dotfile-from-spec when you want to deeply verify a pipeline captures everything from the original spec. Use when prompts might be missing critical domain rules, data models, or invariants.
| name | roborev:fix |
| description | Fix multiple review findings in one pass by discovering unaddressed reviews and addressing them all |
Fix all unaddressed review findings in one pass.
$roborev:fix [job_id...]
When the user invokes $roborev:fix [job_id...]:
If job IDs are provided, use those. Otherwise, discover unaddressed reviews:
roborev fix --unaddressed --list
This prints one line per unaddressed job with its ID, commit SHA, agent, and summary. Collect the job IDs from the output.
If no unaddressed reviews are found, inform the user there is nothing to fix.
For each job ID, fetch the full review:
roborev show --job <job_id>
Parse findings from all reviews. Collect every finding with its severity, file path, and line number. Then:
Run the project's test suite to verify all fixes work:
go test ./...
Or whatever test command the project uses.
For each job that was addressed, record a summary comment and mark it as addressed:
roborev comment --job <job_id> "<summary of changes>"
roborev address <job_id>
Ask the user if they want to commit all the changes together.
User: $roborev:fix
Agent:
roborev fix --unaddressed --list and finds 2 unaddressed reviews: job 1019 and job 1021roborev show --job 1019 and roborev show --job 1021roborev comment --job 1019 "Fixed null check and added error handling" then roborev address 1019roborev comment --job 1021 "Fixed missing validation" then roborev address 1021