メニュー
Produces a scout document: identifies a tension, generates 3-5 distinct routes with tradeoffs, synthesizes a recommendation, and proposes a first action. Use when: 'scout this', 'strategic scout', 'explore options for', 'what are the routes'.
デフォルトでは、最初にソースを確認する Prompt が選択されています。直接コマンドに切り替えるか、ローカルコピーをダウンロードすることもできます。
インストールを決める前に、SKILL.md と SkillsMP に表示されている付属ファイルをお読みください。
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。
直接コマンドでは確認用 Prompt が省略されます。実行前にソースを確認してください。
npx skills add https://github.com/DojoGenesis/mcp --skill scout-writerコマンドは1行のまま表示されます。コピー前に横へスクロールして全体を確認してください。
ローカルで確認しますか？SkillsMP が現在取得できるファイルをダウンロードできます。
Produces a numbered Architecture Decision Record with context analysis, route comparison, decision rationale, consequences, and propagation checklist. Use when: 'write an ADR', 'architectural decision', 'record a decision', 'ADR for'.
Audits CLAUDE.md files for conflicts, stale rules, missing sections, and cross-file coherence. Produces a health report with auto-fix suggestions. Use when: 'check claude.md', 'audit CLAUDE.md', 'fix claude.md', 'claude md health'.
Structured codebase intelligence: directory tree with roles, entry points, dependency graph, test coverage map, and annotated 'here be dragons' warnings.
SOC 職業分類に基づく
SKILL.md を表示中
| name | scout-writer |
| version | 1.0.0 |
| model | sonnet |
| description | Produces a scout document: identifies a tension, generates 3-5 distinct routes with tradeoffs, synthesizes a recommendation, and proposes a first action. Use when: 'scout this', 'strategic scout', 'explore options for', 'what are the routes'. |
| triggers | ["scout this","strategic scout","explore options for","what are the routes"] |
| category | dojo-craft |
| inputs | [{"name":"situation","type":"string","description":"The situation, tension, or decision landscape to scout","required":true}] |
| outputs | [{"name":"scout_document","type":"ref","format":"markdown","description":"Scout document with tension framing, 3-5 routes with tradeoffs, comparison table, synthesized recommendation, and first action"}] |
A scout does not arrive with a solution. A scout arrives with a map.
The most expensive engineering decisions are the ones made before the terrain was understood. A well-written scout document is the cheapest possible way to stress-test a direction before committing resources. It costs an hour of careful thinking and saves days or weeks of course-correction.
The scout is not neutral. The scout has a point of view — grounded in evidence, stated explicitly, open to reframe. "Here are some options" is not scouting. Scouting is: "Here is the landscape, here is what I see in it, here is where I would go and why — and here is what would change my mind."
adr-writer skill when the decision warrants formal recordingDo not use this skill when the direction is already decided and the question is implementation. Scouting a decided question wastes time and introduces doubt where certainty is needed.
Frame the situation as a tension between competing forces — not a problem to solve, but a landscape to navigate.
A tension statement has the form: "[Force A] vs. [Force B]" with a brief explanation of why both forces are legitimate and why they pull in different directions.
Examples:
A tension framed well reveals the routes naturally. A tension framed poorly produces routes that are all variations on one approach.
Generate 3-5 distinct approaches. Distinct means architecturally different, not just implementation variations.
For each route, produce:
| Field | Content |
|---|---|
| Name | Short label (e.g., "Route A: Minimal Wedge") |
| Description | What does this approach actually do? 2-4 sentences. |
| Risk Level | Low / Medium / High — with the specific risk named |
| Time Estimate | Rough order of magnitude (hours, days, weeks) |
| Key Tradeoff | What does this route give up to get its benefits? |
| When it wins | Under what conditions is this the right choice? |
Generate routes that represent genuine alternatives. If you cannot name what a route gives up, you have not understood it.
Build a route comparison table. This is the artifact that makes the scout document scannable in 30 seconds.
| Route | Description | Risk | Time | Key Tradeoff | Wins When |
|---|---|---|---|---|---|
| A | ... | Low | 2d | ... | ... |
| B | ... | High | 1d | ... | ... |
| C | ... | Med | 3d | ... | ... |
The table forces honest comparison. If one route dominates on all dimensions, that is suspicious — it means the routes are not genuinely distinct, or the "losing" routes need better articulation of when they would win.
After laying out the routes, ask: can any of them be combined?
The best solutions often are not Route A or Route B — they are the part of Route A that addresses Force 1, combined with the part of Route B that addresses Force 2.
Identify synthesis opportunities:
Synthesis is a creative act. Not every scout produces a hybrid. But looking for one forces you to understand the routes at a deeper level.
Produce a recommendation with explicit rationale.
The recommendation has four parts:
A recommendation without rationale is a guess. A recommendation without a first action is still just analysis.
Produce the scout document as structured markdown.
# Scout: [Topic]
**Date:** YYYY-MM-DD
**Tension:** [one sentence]
## Context
[2-3 sentences on what prompted this scout. What is the forcing function?]
## Tension
[The tension statement from Step 1 — expanded to a paragraph if needed.]
## Routes
### Route A: [Name]
[Description, risk, time, key tradeoff, when it wins]
### Route B: [Name]
[...]
### Route C: [Name]
[...]
## Comparison
[The table from Step 3]
## Synthesis
[Hybrid opportunity or note that no synthesis applies]
## Recommendation
**Selected:** [Route or hybrid]
**Decisive factors:**
- [Factor 1]
- [Factor 2]
**What would change this:** [Condition]
**First action:** [Specific next step]
## Next Steps
- If proceeding to a formal decision: invoke `adr-writer` with this scout as input
- If proceeding to specification: invoke `release-specification` or `specification-writer`
- Review point: [When to re-evaluate — date, event, or metric]
Save the document to thinking/[topic]-scout.md or the equivalent docs directory for the project.
thinking/[topic]-scout.mdadr-writerScenario 1: "Scout whether to use SSE or WebSockets for the Gateway streaming interface." → Tension: "Protocol simplicity vs. bidirectional capability." Routes: SSE-only, WebSocket-only, SSE for server-push + REST for client-to-server, WebSocket with SSE fallback. Comparison table. Synthesis: SSE + REST is the hybrid that matches current usage patterns without the complexity of WebSocket upgrade handshake. Recommendation: SSE + REST; decisive factors: existing CLI uses REST already, server-push is 95% of traffic, WebSocket adds complexity for 5% gain.
Scenario 2: "Explore options for how the CLI should discover available skills." → Tension: "Discovery completeness vs. startup latency." Routes: filesystem scan on startup, cached manifest with TTL, on-demand load per invocation, remote registry pull. Comparison table. Synthesis: cached manifest (filesystem scan once, invalidate on file change) takes the startup speed of on-demand with the completeness of full scan. Recommendation: cached manifest + inotify invalidation. First action: add manifest file write to the existing skill-validate.sh hook.