PluginBench
Skill
Pass
Audit score 90

analyze-project

lllllllama/rigorpilot-skills

Read-only analysis of deep learning repositories to understand structure, configs, and suspicious patterns.

What is analyze-project?

Analyze-project is a read-only skill for inspecting deep learning research repositories without modifying code or running heavy jobs. Use it to map model architecture, identify training/inference entrypoints, review configurations, and flag implementation concerns before making changes.

  • Inspect model structure and architecture
  • Identify training and inference entrypoints
  • Review configuration files and insertion points
  • Flag suspicious implementation patterns
  • Generate static analysis reports without code modification
  • Map config relationships and dependencies

How to install analyze-project

npx skills add https://github.com/lllllllama/rigorpilot-skills --skill analyze-project
Claude Code
Cursor
Windsurf
Cline

How to use analyze-project

  1. 1.Run the skill to perform static analysis of the target repository
  2. 2.Review the generated SUMMARY.md for repository structure and entrypoints
  3. 3.Check RISKS.md for flagged suspicious patterns and concerns
  4. 4.Examine status.json for analysis metadata and findings
  5. 5.Use insights to plan modifications or understand code flow

Use cases

Good for
  • Understanding a new deep learning codebase before making modifications
  • Reviewing model architecture and training pipeline structure
  • Identifying where to insert monitoring or custom logic
  • Detecting potential implementation issues or anti-patterns
  • Documenting repository structure for team reference
Who it's for
  • ML researchers reviewing unfamiliar codebases
  • Engineers auditing deep learning implementations
  • Teams onboarding to new research projects
  • Code reviewers assessing model architecture
  • Anyone needing repository analysis without execution risk

analyze-project FAQ

Can this skill modify code or run the model?

No. This is a read-only skill that performs static analysis only. It does not patch code, execute commands, or run heavy jobs.

What output does this skill produce?

It generates three files: SUMMARY.md (repository overview), RISKS.md (flagged patterns and concerns), and status.json (analysis metadata).

When should I not use this skill?

Do not use it for debugging tracebacks, environment setup, speculative code adaptation, broad refactoring, or automatic bug fixing.

Does it identify confirmed bugs?

No. It marks suspicious patterns as heuristics and conservative suggestions, not confirmed bugs.

Can it help me understand where to insert custom logic?

Yes. It maps config relationships and insertion points, making it useful for planning modifications before implementation.

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 ../../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.md
  • analysis_outputs/RISKS.md
  • analysis_outputs/status.json

Notes

Use references/analysis-policy.md and the shared references/research-pitfall-checklist.md.