analyze-project
installsforks
How to install analyze-project?
lllllllama/rigorpilot-skills/analyze-project
$npx -y skills add lllllllama/RigorPilot-Skills --skill analyze-projectRigor Analyze / Rigor Audit read-only skill for deep learning research repositories. Use when the user wants to read and understand a repository, inspect model structure and training or inference entrypoints, review configs and insertion points, or flag suspicious implementation
SKILL.md
| 1 | # analyze-project |
| 2 | |
| 3 | Use this as the Rigor Analyze / Rigor Audit read-only skill. The installed slug |
| 4 | remains `analyze-project` for compatibility. |
| 5 | |
| 6 | Use the shared operating principles in |
| 7 | `../../references/agent-operating-principles.md`; this skill should guide |
| 8 | read-only analysis without constraining the model's project-specific reasoning. |
| 9 | |
| 10 | ## When to apply |
| 11 | |
| 12 | - The user wants to understand a deep learning repository before changing it. |
| 13 | - The user needs a map of model structure, training entrypoints, inference entrypoints, and config relationships. |
| 14 | - The user wants conservative suggestions about likely insertion points or suspicious implementation patterns. |
| 15 | - The user explicitly wants read-only analysis and not heavy execution. |
| 16 | |
| 17 | ## When not to apply |
| 18 | |
| 19 | - When the main task is to execute a failing command or debug a traceback. |
| 20 | - When the user wants environment setup or asset download only. |
| 21 | - When the user wants speculative adaptation or broad exploratory patching. |
| 22 | - When the task is a general literature summary without repository analysis. |
| 23 | |
| 24 | ## Clear boundaries |
| 25 | |
| 26 | - This skill is read-mostly. |
| 27 | - It may run lightweight static inspection helpers. |
| 28 | - It does not patch repository code. |
| 29 | - It does not own final reproduction outputs. |
| 30 | - It should mark suspicious patterns as heuristics, not confirmed bugs. |
| 31 | |
| 32 | ## Output expectations |
| 33 | |
| 34 | - `analysis_outputs/SUMMARY.md` |
| 35 | - `analysis_outputs/RISKS.md` |
| 36 | - `analysis_outputs/status.json` |
| 37 | |
| 38 | ## Notes |
| 39 | |
| 40 | Use `references/analysis-policy.md` and the shared `references/research-pitfall-checklist.md`. |
People who liked this also viewed
6 picksType
- hyperframes-cliUse the HyperFrames CLI development loop: init, add, catalog, capture, lint, check, snapshot, compare, grade-compare, preview, play, present, beats, keyframes, single or batch render, publish, cloud, SkillsJul 2026
- request-refactor-planSkills for Real Engineers. Straight from my .agents directory.SkillsJul 2026
- explore-codeRigor Improve implementation leaf skill for auditable candidate implementation in deep learning research repositories. Use when the researcher explicitly authorizes exploratory work on an isolated braSkillsMay 2026
- ubiquitous-languageSkills for Real Engineers. Straight from my .agents directory.SkillsJul 2026
- scaffold-exercisesSkills for Real Engineers. Straight from my .agents directory.SkillsJul 2026
- writing-shapeSkills for Real Engineers. Straight from my .agents directory.SkillsJul 2026
