メニュー
Review and sync skill for Q agent. Monitors changes across tasks/projects/roadmaps, maintains update logs, and ensures consistency. Use after bulk changes or during standups.
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
Bosun configuration — models, sandbox, daemon, Pi settings. Use when changing models, editing config, or understanding how bosun is set up.
Bootstrap a new project using bosun as a foundation — via bun dependency (recommended) or git submodule. Creates a downstream project that inherits bosun's multi-agent infrastructure while adding custom agents, skills, and extensions. Works standalone — fetchable by any pi agent via raw GitHub URL.
Search curated markdown memory like sessions, plans, docs, and skills. Use when recalling prior context or looking for relevant historical/project knowledge.
Analyze Pi session JSONL files using jq patterns. Use when extracting metrics, tool usage, costs, or reviewing session history. Load for session export, summarization, or workflow analysis.
Session-based browser plan review primitives for Bosun. Provides a local-first state model, markdown-aware anchor extraction, and review-session persistence for reviewing existing plan files in dedicated CDP browser windows. Triggers: "plan-review", "review this plan", "review markdown plan".
Session-based browser diff review primitives for Bosun. Provides transport- agnostic v1 schemas plus local state and git snapshot helpers for immutable review rounds. Triggers: "diff-review", "reround", "review round", "snapshot-backed review".
| name | q-review |
| description | Review and sync skill for Q agent. Monitors changes across tasks/projects/roadmaps, maintains update logs, and ensures consistency. Use after bulk changes or during standups. |
Cross-module sync and consistency layer for the Q agent system.
Use this skill when:
Do NOT use for:
When tasks are marked done:
When project progress changes:
When a blocking task is done:
Append timestamped entries to _update-log.md:
## 2026-01-08
### a3f9: Deploy GTT v2
- **12:30** Status: active -> done
- **12:30** Unblocked: b2c4, c3d5
Run these checks during review:
| Check | Issue | Resolution |
|---|---|---|
| Orphan tasks | Task has invalid project ref | Clear project field |
| Ghost deps | blocked_by refs non-existent task | Remove from blocked_by |
| Stale items | No updates in 30+ days | Tag for review |
| Progress mismatch | Project progress != task counts | Recalculate |
1. Complete tasks via qt done
2. Load q-review skill
3. Run sync to propagate changes
4. Review update logs
1. Check blocked tasks
2. Review stale items
3. Sync progress across modules
4. Identify inconsistencies
question: "Found 3 orphan tasks. How to handle?"
header: "Orphans"
options:
- label: "Clear refs"
description: "Remove invalid project references"
- label: "Create project"
description: "Group under 'Uncategorized'"
- label: "Review each"
description: "Show tasks for manual review"
question: "5 tasks haven't been updated in 30+ days"
header: "Stale"
options:
- label: "Show list"
description: "Display stale tasks"
- label: "Tag for review"
description: "Add 'needs-review' tag"
- label: "Skip"
description: "Ignore for now"
workspace/users/{user}/tasks/_update-log.mdworkspace/users/{user}/projects/_update-log.mdworkspace/users/{user}/roadmaps/_update-log.mdThe q-review-agent handles:
It does NOT: