model-critique-coach
Skill5 starsChanged 29 days agoNo licenceView on GitHub
当使用者说“帮我批判这个模型”“找漏洞和反例”“模拟评委审稿”“这个结论站得住吗”“为什么验证不充分”时使用。先重建现有模型及其证据链，再从核心主张倒查方程、参数、数据、代码与假设，检查量纲、边界、可辨识性、泄漏、基线、验证、灵敏度、稳健性和可复现性；按对结论的影响分级，每条给最低成本反证检查与修复方向，不伪造审稿意见或验证结果，不整套重写。
In this repository63 other files it gives its agents.
- ai-answer-triageSkill
- ai-code-onboarding-checklistSkill
- ai-diff-review-protocolSkill
- ai-generated-test-auditorSkill
- ai-output-fact-checkerSkill
- ai-session-handoff-writerSkill
- prompt-brief-builderSkill
- bento-infographicSkill
- event-venue-kitSkill
- keynote-deck-builderSkill
- launch-summary-panelSkill
- maestrwave-ui-systemSkill
- photo-spread-composerSkill
- radio-quote-cardSkill
- ui-design-system-builderSkill
- program-maturity-navigatorSkill
- latex-paper-formatterSkill
- modeling-assumption-builderSkill
- modeling-code-builderSkill
- modeling-problem-reading-coachSkill
- model-selection-tutorSkill
- paper-enhancement-builderSkill
- paper-structure-coachSkill
- team-role-coachSkill
- photo-caption-writerSkill
- photo-cinematic-gradeSkill
- photo-exif-frameSkill
- photo-poster-stylistSkill
- photo-series-layoutSkill
- shoot-outing-review-cardSkill
- answer-plausibility-checkerSkill
- competition-scenario-extractorSkill
- concept-to-formula-deriverSkill
- dataset-systematic-error-hunterSkill
- derivation-step-checkerSkill
- dimensional-analysis-checkerSkill
- fermi-estimation-coachSkill
- limiting-case-validatorSkill
- model-fit-auditorSkill
- numerical-stability-auditorSkill
- physics-mechanism-decomposerSkill
- physics-problem-routerSkill
- problem-formalization-coachSkill
- problem-representation-scoutSkill
- reference-frame-choice-guideSkill
- symbolic-first-discipline-coachSkill
- uncertainty-propagatorSkill
- skill-creatorSkill
- adversarial-lyric-writerSkill
- llm-midi-compositionSkill
- lyric-concept-builderSkill
- lyric-doctorSkill
- lyric-structure-mapperSkill
- activity-list-optimizerSkill
- activity-profile-builderSkill
- admissions-readerSkill
- application-timeline-builderSkill
- deadline-to-study-planSkill
- project-brainstormSkill
- reflection-interviewerSkill
- The first 60 shown.
The file
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.