About this skill
Use when about to declare verdict='supported' on any experiment in a quant-research project (mandatory co-gate with bugreview; both must pass). Also use when the user asks for a review of a notebook / experiment / project, at end-of-research-cycle gates, before external sharing / publication / any deployment recommendation, and when inheriting a notebook that needs a fresh-eyes assessment. Asks whether the claim is warranted by what was actually tested — distinct from bugreview which asks whether the implementation is correct. Both layers required for verdict='supported'.
Quick start
- Copy the install prompt. Use the green button above this README.
- Send it to your agent. Paste it into your coding agent’s chat and send.
- Review the setup. Your agent checks the skill’s instructions, requirements, and installation scope.
Review, license & listing details
This is an imported listing. We haven’t certified its safety, license, or compatibility. Skills may include executable scripts.
Only SKILL.md was scanned. Supporting files and scripts were not checked. No safety grade has been assigned.
0 potential findings · Scanned 11/4/2026 · Scanner 0.2.1
Content SHA-256: 62460fb342d751294663324995b0d707920669adc7c0f58cd3252ca301af8173
About this listing
- Category
- Science & research
- Reported license
- Not specified
- Listing language (estimated)
- English
- Review status
- Not individually reviewed
- Agent compatibility
- Atlas installation supports Claude Code, Codex, and Cursor. Skill-specific dependencies and features are checked during setup.