菜单
Add or update research paper cards, reference notes, external repo links, and evidence links from papers to claims and experiments.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Turn a research agenda into one cold-readable `/goal` prompt for autonomous AI research loops, with evidence-graph notebook rules, experiment cadence, verification, scope edges, and a finite, batch, or continuous completion contract.
Maintain the research workspace belief layer: open questions, claims, decisions, confidence levels, evidence links, and revisit conditions.
Rank candidate experiments, decide what not to run next, maintain the factory queue, and choose one decisive next research goal before autonomous loops spend compute.
Create, run, and record AI research experiments with manifests, run records, artifact paths, metrics, and experiment index updates.
Compress an AI research experiment batch or branch into lessons, updated claims/questions, and a continue/stop/pivot decision.
Route AI research workspace work across the evidence graph. Use for broad research tasks, choosing which research sub-skill applies, or updating the dashboard after experiment, claims, synthesis, or reference work.
| name | research-references |
| description | Add or update research paper cards, reference notes, external repo links, and evidence links from papers to claims and experiments. |
Use when adding papers, external repos, datasets, benchmark docs, or reference notes.
Store source PDFs and primary paper artifacts under papers/. Store concise
research interpretation under references/paper-cards/.
Use P### IDs for external evidence. Prefer concise paper cards over loose
links.
references/paper-cards/P001_short_name.md
papers/P001_short_name.pdf
unread, skimmed, read, implemented, or superseded;Papers support hypotheses; local experiments decide project claims. When a paper changes a claim, link both the paper ID and the local experiment/blocker that makes it relevant.