From polymath-engineering
Orient quickly in an unfamiliar codebase area; produce a one-page map of structure, entry points, and the most likely place a change should land.
How this skill is triggered — by the user, by Claude, or both
Slash command
/polymath-engineering:read-codeThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
> Orient in an unfamiliar codebase area before changing anything. Output is a concise map, not a tour.
Orient in an unfamiliar codebase area before changing anything. Output is a concise map, not a tour.
feature-dev if the area is unfamiliar.README.md, package.json, Cargo.toml, pyproject.toml, etc.) to identify the language and build system.main, app, route table, CLI dispatch), trace one user-facing flow end-to-end.Codebase map: <area>
Entry points:
- <file>:<line> — <function/route>
Flow:
- <step 1>
- <step 2>
- <step 3>
Likely change site:
- <file>:<line> — <reason>
Alternative change sites:
- <file>:<line> — <reason>
- <file>:<line> — <reason>
Open questions:
- <thing you couldn't determine from reading>
Provides behavioral guidelines to reduce common LLM coding mistakes, focusing on simplicity, surgical changes, assumption surfacing, and verifiable success criteria.
Searches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.
Creates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.
npx claudepluginhub mohammadbafkar/polymath --plugin polymath-engineering