You want to understand a deep learning codebase before making any changes. This skill helps you explore the project structure safely. It reads model designs, training scripts, and configuration files. It flags anything that looks odd or risky. You get a clear map of the repository without running any code.
This is a read-only analysis tool for researchers and developers. It helps you inspect entry points for training and inference. You can review how different parts of the code connect. The skill highlights suspicious patterns as heuristics, not confirmed bugs.
Use this skill when you need a careful overview of a deep learning project. It is designed for safe exploration without modifying files or running heavy jobs. You get summary reports and risk assessments to guide your next steps.
Global
mkdir -p ~/.claude/skills/analyze-projectProject
mkdir -p .claude/skills/analyze-projectSource Repository
Lark Baselarksuite/cli
Simplify your Lark Base data with tables, fields, records, and views
Lark Wikilarksuite/cli
Manage your Lark Wiki spaces, members, and documents with simple commands
Grillingmattpocock/skills
Test your plan thoroughly with clear step-by-step interview questions
Ai Research Reproductionlllllllama/rigorpilot-skills
Faithful reproduction of deep learning research with auditable steps and minimal changes
Repo Intake And Planlllllllama/rigorpilot-skills
Scan a repo, find commands, and get a simple reproduction plan
Minimal Run And Auditlllllllama/rigorpilot-skills
Capture evidence from deep learning runs and create standardized audit reports
Obsidian Vaultmattpocock/skills
Search create and organize notes with wikilinks and index notes easily
Paper Context Resolverlllllllama/ai-paper-reproduction-skill
Resolve deep learning paper reproduction gaps with precise primary source evidence