一键导入
research-claims
Maintain the research workspace belief layer: open questions, claims, decisions, confidence levels, evidence links, and revisit conditions.
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。
菜单
Maintain the research workspace belief layer: open questions, claims, decisions, confidence levels, evidence links, and revisit conditions.
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.
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.
Remote CUDA development workflow for the local NVIDIA DGX Spark at spark-f0a3.local. Use when Codex needs to probe the DGX Spark, choose a developer experience, mirror a research workspace with rsync, run CUDA/PyTorch/NAC/Le-WM training remotely while the agent stays on the Mac, use tmux/screen, manage TensorBoard tunnels, sync artifacts back, or decide between direct SSH, Docker, NVIDIA AI Workbench, and native Python setup.
| name | research-claims |
| description | Maintain the research workspace belief layer: open questions, claims, decisions, confidence levels, evidence links, and revisit conditions. |
Use when interpreting evidence, updating beliefs, closing questions, or changing research direction.
OPEN_QUESTIONS.md: uncertainties ranked by information gain.CLAIMS.md: compressed belief state.DECISIONS.md: choices that change future behavior.RESEARCH.md: short dashboard summary.supported, weakened, mixed, refuted, superseded,
unknown. Mark falsified beliefs refuted; do not soften a dead idea to
weakened.low, medium, high.Primary claims: line current;
it is the per-program view of CLAIMS.md.Each Q### should have:
open, answered, paused, or superseded.A decision changes future behavior. Every D### needs:
Do not create a decision for every run. Create one when the next branch changes, when a path stops, or when a default practice changes.
After evidence:
facts -> claim status/confidence -> question status -> decision if behavior changes
Then update the RESEARCH.md evidence snapshot if the current thesis changes.