メニュー
Analyzes an under-served area to determine what it needs. Assesses current coverage, identifies gaps relative to demand, and recommends build order.
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。
SOC 職業分類に基づく
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/benjam3n/reasoningtool --skill undr-under-represented-analysis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。
SKILL.md を表示中
| name | undr - Under-Represented Analysis |
| description | Analyzes an under-served area to determine what it needs. Assesses current coverage, identifies gaps relative to demand, and recommends build order. |
| output | {"format":"prose"} |
Input: $ARGUMENTS
Define the under-served area precisely. What is it, and why does it seem under-represented?
AREA: [The area under analysis]
BELONGS TO: [The larger category or system it sits within]
SIGNAL OF UNDER-REPRESENTATION: [What made you notice this area is under-served?]
Inventory what currently exists in this area.
EXISTING COVERAGE:
1. [Item 1] — quality: [HIGH/MEDIUM/LOW] — coverage: [what it handles]
2. [Item 2] — quality: [HIGH/MEDIUM/LOW] — coverage: [what it handles]
3. [Item 3] — quality: [HIGH/MEDIUM/LOW] — coverage: [what it handles]
...
TOTAL ITEMS: [count]
QUALITY DISTRIBUTION: [How many high/medium/low]
COVERAGE MAP: [What percentage of the area is currently served?]
Compare current coverage to what the area actually needs.
DEMAND SIGNALS:
- [Evidence of need 1]
- [Evidence of need 2]
- [Evidence of need 3]
GAPS (what's missing relative to demand):
1. [Gap 1] — demand level: [HIGH/MEDIUM/LOW]
2. [Gap 2] — demand level: [HIGH/MEDIUM/LOW]
3. [Gap 3] — demand level: [HIGH/MEDIUM/LOW]
...
MOST CRITICAL GAP: [Which gap causes the most pain if left unfilled?]
For each gap, estimate what it would take to address it.
GAP 1 — [name]:
- Effort: [LOW/MEDIUM/HIGH]
- Dependencies: [What else needs to exist first?]
- Complexity: [Simple addition or requires new infrastructure?]
GAP 2 — [name]:
- Effort: [LOW/MEDIUM/HIGH]
- Dependencies: [What else needs to exist first?]
- Complexity: [Simple addition or requires new infrastructure?]
[Repeat for each gap]
Rank gaps by impact-to-effort ratio and recommend a sequence.
PRIORITY RANKING (by impact / effort):
1. [Gap] — impact: [H/M/L], effort: [H/M/L] — DO FIRST
2. [Gap] — impact: [H/M/L], effort: [H/M/L]
3. [Gap] — impact: [H/M/L], effort: [H/M/L]
...
RECOMMENDED BUILD ORDER:
Phase 1: [What to build first and why]
Phase 2: [What to build next]
Phase 3: [What can wait]
SKIP: [Anything that seems like a gap but isn't worth filling — and why]
Use with:
/satr -> Check if the parent category is over-served elsewhere/ctgp -> Formal category gap analysis/efrt -> Detailed effort estimation for top-priority gaps/benf -> Estimate benefits of filling each gapRoute any input through a branching question tree to narrow down the optimal response strategy before writing. Two stages — PERCEIVE (classify input) then ACT (select response). Covers all prompt types.
Generate exhaustive guesses about user input using ALL search methods with coverage tracking. Guessing is SEARCH through possibility space. Tracks space created vs space covered to ensure comprehensive exploration.
Systematically evaluate and select from a set of guesses, options, or possibilities. Combines ARAW analysis with prioritization to determine which guesses are strong, weak, actionable, or eliminable.