메뉴
Visualize the Evoloop story dependency graph as text tree and Mermaid flowchart — shows critical path, blocked chains, and ready-to-run stories
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 | deps |
| description | Visualize the Evoloop story dependency graph as text tree and Mermaid flowchart — shows critical path, blocked chains, and ready-to-run stories |
| argument-hint | [US-XXX] |
| allowed-tools | ["Read","Glob","Grep","Bash(jq *)","Write"] |
Optional $ARGUMENTS story ID. If provided → show only transitive ancestors/descendants subgraph. If empty → full graph.
Glob prd/US-*.json. For each: extract id, title, dependencies, .stage (top-level), priority via jq. Build adjacency list (depends-on + depended-by).
Edge cases: No stories → "No stories in prd/". Filtered story not found → list available. All complete → "Fully resolved."
1. Overview Table: | ID | Title | Stage | Priority | Dependencies |
2. Text Tree (roots = no dependencies):
US-001 [complete] — Setup auth
└── US-002 [build] — Add API
└── US-003 [blocked] — Deploy infra
3. Mermaid Flowchart:
graph TD
US-001["US-001: Setup auth"]:::complete
US-001 --> US-002
classDef complete fill:#22c55e,color:#fff
classDef build fill:#3b82f6,color:#fff
classDef review fill:#3b82f6,color:#fff
classDef deploy fill:#f59e0b,color:#fff
classDef blocked fill:#ef4444,color:#fff
Offer to save to flowchart/dependencies.mmd.
4. Critical Path: Longest root-to-leaf chain. Compare with .plan/dependencies.md if exists.
5. Ready to Run: Stories with all deps complete and own stage build.
6. Blocked Chains: Stories blocked by incomplete upstream.
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
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
Show log output from Evoloop pipeline runs — latest run summary, specific story logs, last agent invocation, or a specific run