菜单
Deep-dive into a specific story's state — stage, failures, dependencies, last agent output, requirement verification, and suggested next action
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | inspect |
| description | Deep-dive into a specific story's state — stage, failures, dependencies, last agent output, requirement verification, and suggested next action |
| argument-hint | <US-XXX> |
| allowed-tools | ["Read","Glob","Grep","Bash(jq *)"] |
Story ID from $ARGUMENTS (format: US-XXX). If empty → print usage. If prd/$ARGUMENTS.json missing → list available stories.
prd/<ID>.json — all fields. .stage is top-level.prd/<ID>.mddependencies array → read JSON for id, title, .stageprd/US-*.json for stories listing this ID in dependencies.log/run-*/run.md for story ID.state/pipeline.json → check if currentStory matches=== Story: <ID> — <title> ===
Area: <area> | Priority: <priority> | Risk: <riskTier> | Size: <sizing> | Autonomy: <autonomy>
Stage: <stage> | Deploy attempts: <status.deploy.attempts>/3 | Deploy notes: <notes>
Pipeline: <"Active" / "Not active">
Requirements: | REQ ID | Implemented | Verified |
Dependencies (upstream): <ID> — <title> [<stage>] BLOCKING/OK
Dependents (downstream): <ID> — <title> [<stage>] WAITING/OK
Deploy Safety: strategy, healthChecks, rollbackTrigger, rollbackCommand, verification
Recent Logs (max 5): Run <ID>: <agent> | <outcome>
Tracker Notes: <summary from .md>
build/review → ./orchestrator.sh run --tool claude --story <ID>deploy (gated) → ./orchestrator.sh run --tool claude --story <ID> --approve-deploy <ID>complete → No actionblocked → Review notes, /reset-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
Show log output from Evoloop pipeline runs — latest run summary, specific story logs, last agent invocation, or a specific run