mcpField
A
analyze-project

analyze-project

github.com/lllllllamaTesting & quality486340.0k installsUpdated 5w ago
Repository

About analyze-project

analyze-project is a read-mostly skill for understanding a deep learning repository before changing it. It maps model structure, training and inference entrypoints, and config relationships, and offers conservative suggestions about insertion points or suspicious patterns. It is aimed at researchers and engineers who want analysis without heavy execution, and it labels suspicious findings as heuristics rather than confirmed bugs.

Key features

  1. 01Read-mostly repository structure analysis
  2. 02Maps model structure and entrypoints
  3. 03Maps relationships between config files
  4. 04Conservative insertion point suggestions
  5. 05Flags suspicious patterns as heuristics

Use cases

  1. 01Understanding an unfamiliar deep learning codebase before editing
  2. 02Locating training and inference entrypoints
  3. 03Reviewing implementation patterns without heavy execution

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/lllllllama/rigorpilot-skills --skill analyze-project

After installing, type/analyze-projectin Claude Code to confirm it loaded.

Bundled files

References and scripts installed along with SKILL.md.

agents/
openai.yaml
references/
analysis-policy.md
scripts/
analyze_project.py

Details

From the project README

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

Notes

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

Comments

Markdown supported