メニュー
8-phase autonomous research pipeline with multi-source discovery, 4-layer citation verification, hypothesis generation, and PIVOT/REFINE/PROCEED decision loops. Confidence-gated — loops until 95%+ confidence.
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
ProductionOS — dual-target AI engineering operating system for repo-wide audits, upgrade plans, code reviews, strategic product reviews, security sweeps, UX audits, and recursive quality improvement.
ProductionOS — dual-target AI engineering operating system for repo-wide audits, upgrade plans, code reviews, strategic product reviews, security sweeps, UX audits, and recursive quality improvement.
Ads composite — audit campaigns, create ad copy, optimize bids, and report performance with persistent campaign memory. Replaces 20 fragmented ads skills.
Build composite — brainstorm, plan, implement, and test with project memory. Replaces 6 fragmented build skills.
Content composite — strategy, writing, audit, and refresh with brand voice memory. Replaces 10 fragmented content skills.
Debug composite — reproduce, hypothesize, test, fix with bug pattern memory. Replaces 4 debug skills.
| name | deep-research |
| description | 8-phase autonomous research pipeline with multi-source discovery, 4-layer citation verification, hypothesis generation, and PIVOT/REFINE/PROCEED decision loops. Confidence-gated — loops until 95%+ confidence. |
| argument-hint | [topic, depth, or source mix] |
Use this as the Codex-first research workflow for ProductionOS. It should take a topic, break it into concrete research questions, gather and verify sources, synthesize competing hypotheses, and only deliver claims that are evidence-backed.
Source references:
.claude/commands/deep-research.mdscripts/arxiv-scraper.shtopic: required research question or areadepth: quick, standard, deep, or exhaustivesources: arxiv, web, docs, or all