Menu
Compress an AI research experiment batch or branch into lessons, updated claims/questions, and a continue/stop/pivot decision.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
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.
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-synthesis |
| description | Compress an AI research experiment batch or branch into lessons, updated claims/questions, and a continue/stop/pivot decision. |
Use after about five serious experiments, at branch end, or when the user asks what the research has learned.
Read only what is needed:
RESEARCH.mdexperiments/index.ymlCLAIMS.md, OPEN_QUESTIONS.md, DECISIONS.mdAnswer:
Also glance at repo health while here: stale running experiments, a dashboard
turning into a diary, or a failed mechanism reappearing under a new name.
Update or create:
research-log/YYYY-MM-DD-branch-synthesis.md note;CLAIMS.md;OPEN_QUESTIONS.md;DECISIONS.md with one continue/stop/pivot decision if behavior changes;RESEARCH.md dashboard.Status: lines if the next experiment or priority changed.Prefer one strong conclusion over many loose observations. Mark stale claims or
questions superseded instead of leaving them quietly misleading.
If the synthesis mostly adds chronology to RESEARCH.md or CLAIMS.md, stop
and compress instead. The dashboard should point to synthesis notes; it should
not become the synthesis note.