
report-template
by Avik-creator
SKILL.md
name: report-template description: Synthesize all Scout-phase analyses (build-inspector, runtime-inspector, git-forensics, concept-modeler) into a decision-ready system risk report.
The Synthesizer’s Manual
“Data is not information. Information is not knowledge. Knowledge is not wisdom.” — T.S. Eliot
Your goal is to transform raw analytical data into architectural wisdom that can drive decisions.
⚠️ Mandatory Deep Thinking
[!IMPORTANT] Before generating the report, you must invoke the
mcp_sequential-thinking_sequentialthinkingtool and reason for 5–10 steps, as appropriate.Example thinking prompts:
- “Do the build boundaries discovered by build-inspector align with the IPC boundaries found by runtime-inspector?”
- “Do the high-coupling file pairs identified by git-forensics cross build boundaries?”
- “Are the missing components identified by concept-modeler correlated with observed risks?”
- “Which findings are 🔴 blocking risks versus 🟡 risks to monitor?”
⚡ Quick Start
-
Load the template (MANDATORY) Use
view_file references/REPORT_TEMPLATE.md. Your report must strictly follow this structure. -
Aggregate all findings from:
build-inspector→ Build Roots, Topologyruntime-inspector→ IPC Surfaces, Contract Statusgit-forensics→ Coupling Pairs, Hotspotsconcept-modeler→ Entities, Missing Components
-
Draft the report Use
sequentialthinkingto organize logical connections and conclusions. -
Publish (CRITICAL) You must use
write_to_fileto save the report to:scout/SCOUT_RISK_REPORT.mdDo not output the report only in chat.
✅ Completion Checklist
Before proceeding to the next phase, verify:
- Output file created:
scout/SCOUT_RISK_REPORT.md - Includes: System Fingerprint, Component Map, Risk Matrix, Feature Landing Guide
- User has confirmed the findings
🛠️ Synthesis Ritual
1. Executive Summary
- Elevator pitch: Describe system health in 30 seconds.
- Focus areas: Technical debt, critical risks, reliability.
2. Dark Matter Detection
- Do not only list what exists. Explicitly list what is missing.
- Checklist: Logging? Error handling? CI/CD? Secret management? Version handshakes?
3. Cross-Verification
- Does build-inspector claim “unified workspace management”?
- Does git-forensics reveal “high coupling across build roots”?
- Conclusion: Hidden logical coupling detected → refactoring candidate.
4. Human Checkpoint
- Force user confirmation: “Is this report complete?”
- No Blueprint phase allowed until this report is signed off.
🛡️ Master Rules
- No hallucinations: Every claim must be traceable to a source file.
- Brutal honesty: Be direct. If it’s a mess, say it’s a mess.
- Action-oriented: Every issue listed must imply a path forward (refactor / rewrite / accept).
🧰 Toolbox
references/REPORT_TEMPLATE.md— primary report template
Consumers
The direct consumers of this report in the /blueprint phase are:
- System Architect — relies on your risk list to design mitigation strategies
- Complexity Guard — uses your findings to audit RFC and design complexity
The quality of your analysis directly determines the quality of the next design phase.
Score
Total Score
Based on repository quality metrics
SKILL.mdファイルが含まれている
ライセンスが設定されている
100文字以上の説明がある
GitHub Stars 100以上
3ヶ月以内に更新がある
10回以上フォークされている
オープンIssueが50未満
プログラミング言語が設定されている
1つ以上のタグが設定されている
Reviews
Reviews coming soon