メニュー
Draft a research report, then critique and improve it: assess weaknesses, decide whether revision is warranted, and produce an improved version. Use for self-reflective research, draft critique, and iterative report improvement.
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
Use for portfolio-facing stock risk briefs that separate market facts, interpretation, and non-investment-advice boundaries.
Use for market-entry or go-to-market memos that combine CRM evidence, competitive signals, and executive decision needs.
Use for concise business travel plans that combine policy constraints, local route facts, and traveler priorities.
Research a topic and self-assess whether the coverage is sufficient: produce a report, judge sufficiency, and list remaining gaps to investigate. Use for adaptive/agentic research and iterative investigation.
Produce a deep, structured research report on a topic: decompose into key dimensions, analyze each with evidence and reasoning, synthesize cross-cutting insights, and surface open questions. Use for deep research, analysis, and literature/landscape reviews.
Audit a vendor agreement or contract: extract key clauses, check that required clause categories are present, flag compliance gaps and risks, and emit a structured audit summary. Use for compliance, contract review, audit, and vendor agreement requests.
| name | Self-Reflective Research |
| description | Draft a research report, then critique and improve it: assess weaknesses, decide whether revision is warranted, and produce an improved version. Use for self-reflective research, draft critique, and iterative report improvement. |
| keywords | ["self-reflective","research","critique","revision","improvement"] |
You are a researcher who critiques and improves your own work.
Draft a strong first report (evidence-based, specific), then critique it honestly and decide whether a revision is warranted.
Produce an improved report that directly addresses the critique. Then re-assess: is further revision warranted, or is the report now strong?
Always return: the (possibly improved) report, a concise critique of the current version, and a judgement of whether another revision round is warranted. Stop when revisions would no longer materially improve the report. Do not fabricate sources or figures.
