analyze-project
lllllllama/rigorpilot-skills
Read-only analysis skill for understanding deep learning research repositories and flagging suspicious patterns.
What is analyze-project?
Analyze-project is a read-only inspection tool for deep learning research codebases. Use it when you need to understand repository structure, map model and training entrypoints, review configurations, and identify suspicious implementation patterns without modifying code or running heavy computations.
- Inspect model architecture and structure in deep learning repositories
- Map training and inference entrypoints and their relationships
- Review configuration files and identify insertion points for modifications
- Flag suspicious implementation patterns using heuristic analysis
- Generate structured analysis outputs (SUMMARY.md, RISKS.md, status.json)
- Run lightweight static inspection helpers without modifying code
How to install analyze-project
npx skills add https://github.com/lllllllama/rigorpilot-skills --skill analyze-projectHow to use analyze-project
- 1.Install the skill using: npx skills add https://github.com/lllllllama/rigorpilot-skills --skill analyze-project
- 2.Point the skill at your deep learning repository directory
- 3.Request analysis of specific aspects: model structure, training entrypoints, configs, or suspicious patterns
- 4.Review the generated analysis_outputs/SUMMARY.md for repository overview
- 5.Check analysis_outputs/RISKS.md for flagged implementation patterns
- 6.Use analysis_outputs/status.json for structured findings
Use cases
- Understanding a new research repository before making modifications
- Identifying where to insert custom layers or modifications in a model pipeline
- Reviewing training configurations and hyperparameter relationships
- Detecting potential implementation issues or non-standard patterns in research code
- Planning reproduction or adaptation work by mapping code structure first
- ML researchers reproducing or adapting published models
- Engineers auditing deep learning codebases for structure and quality
- Teams planning modifications to research repositories
- Anyone needing to understand a codebase before making changes
analyze-project FAQ
No. This is a read-only skill that inspects code but does not make changes to the repository.
No. This skill is for understanding repository structure, not for executing commands or debugging tracebacks. Use it before or alongside execution-focused debugging.
It uses heuristic analysis to identify non-standard implementations, unusual patterns, and potential issues in model code and training logic. Flagged patterns are suggestions, not confirmed bugs.
No. This skill focuses on code analysis. Environment setup and asset downloads are out of scope.
The skill generates SUMMARY.md (repository overview), RISKS.md (flagged patterns), and status.json (structured findings).
Full instructions (SKILL.md)
Source of truth, from lllllllama/rigorpilot-skills.
name: analyze-project description: Rigor 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 patterns without modifying code or running heavy jobs. Do not use for active command execution, broad refactoring, speculative code adaptation, or automatic bug fixing.
analyze-project
Use this as the Rigor Analyze / Rigor Audit read-only skill. The installed slug
remains analyze-project for compatibility.
Use the shared operating principles in
../ai-research-reproduction/references/agent-operating-principles.md; this skill should guide
read-only analysis without constraining the model's project-specific reasoning.
When to apply
- The user wants to understand a deep learning repository before changing it.
- The user needs a map of model structure, training entrypoints, inference entrypoints, and config relationships.
- The user wants conservative suggestions about likely insertion points or suspicious implementation patterns.
- The user explicitly wants read-only analysis and not heavy execution.
When not to apply
- When the main task is to execute a failing command or debug a traceback.
- When the user wants environment setup or asset download only.
- When the user wants speculative adaptation or broad exploratory patching.
- When the task is a general literature summary without repository analysis.
Clear boundaries
- This skill is read-mostly.
- It may run lightweight static inspection helpers.
- It does not patch repository code.
- It does not own final reproduction outputs.
- It should mark suspicious patterns as heuristics, not confirmed bugs.
Output expectations
analysis_outputs/SUMMARY.mdanalysis_outputs/RISKS.mdanalysis_outputs/status.json
Notes
Use references/analysis-policy.md and the shared ../ai-research-reproduction/references/research-pitfall-checklist.md.
Related skills
More from lllllllama/rigorpilot-skills and the wider catalog.
env-and-assets-bootstrap
Prepare conda environments and asset paths for README-documented deep learning repo reproduction.
explore-code
Auditable exploratory code modifications for deep learning research on isolated branches with rollback records.
explore-run
Plan and execute bounded exploratory runs for deep learning research with fair-comparison tracking.
minimal-run-and-audit
Execute and audit deep learning repo smoke tests with standardized evidence capture and scientific changelog tracking.
paper-context-resolver
Resolve reproduction-critical paper details when README and repo files leave gaps.
repo-intake-and-plan
README-first repository scanner for deep learning reproduction planning.