메뉴
Safely reset a blocked or failed Evoloop story back to the build stage — clears deploy attempts and failure notes while preserving verification data
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
| name | reset-story |
| description | Safely reset a blocked or failed Evoloop story back to the build stage — clears deploy attempts and failure notes while preserving verification data |
| argument-hint | <US-XXX> |
| disable-model-invocation | true |
| allowed-tools | ["Read","Glob","Bash(jq *)","Bash(mv *)","Write"] |
Story ID from $ARGUMENTS. If empty → print usage. If prd/$ARGUMENTS.json missing → list available stories.
Read and display: title, stage, deploy attempts/notes, validation data. If complete → warn about full re-run. If build with 0 attempts → "No reset needed", stop.
Ask: "Reset from '' to 'build'? Clears deploy attempts and notes."
jq '.stage = "build" | .status.deploy.attempts = 0 | .status.deploy.notes = "" | .status.deploy.passes = false | .status.build.passes = false | .status.build.notes = "" | .status.review.passes = false | .status.review.notes = ""' prd/<ID>.json > prd/<ID>.json.tmp.$$ && mv prd/<ID>.json.tmp.$$ prd/<ID>.json
Critical: .stage is top-level. Preserve .status.validation entirely.
Display old vs new stage, cleared attempts, preserved validation. Suggest: ./orchestrator.sh run --tool claude --story <ID>
Show planning area readiness status -- statuses, open questions, blockers, and next actions
Clone an existing Evoloop story as a template for a new one — copies structure, resets status, prompts for changes to title, requirements, and dependencies
Estimate the total prompt size that will be sent to an AI agent when processing an Evoloop story — warns if approaching model context limits
Visualize the Evoloop story dependency graph as text tree and Mermaid flowchart — shows critical path, blocked chains, and ready-to-run stories
Run Evoloop doctor checks and auto-fix common issues — missing directories, non-executable scripts, missing templates, and provide remediation for manual fixes
Deep-dive into a specific story's state — stage, failures, dependencies, last agent output, requirement verification, and suggested next action