From perf
Maps code paths, entrypoints, and likely hot files before profiling. Outputs candidate files and symbols with evidence for performance scenarios.
How this skill is triggered — by the user, by Claude, or both
Slash command
/perf:code-pathsThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Identify likely implementation paths for a performance scenario.
Identify likely implementation paths for a performance scenario.
Follow docs/perf-requirements.md as the canonical contract.
keywords: <comma-separated list>
paths:
- file: <path>
symbols: [<symbol1>, <symbol2>]
evidence: <short reason>
npx claudepluginhub composio-community/awesome-claude-plugins --plugin perf2plugins reuse this skill
First indexed Feb 4, 2026
Profiles application performance across Node.js, Python, and Java stacks by analyzing CPU, memory, and execution hotspots to identify optimization targets.
Maps unfamiliar codebases in phases: structure, entry points, data flow, patterns, landmines. Use before coding in new, inherited, or revisited projects.
Runs a 7-phase codebase analysis using typegraph-mcp tools, producing a detailed architectural report. Useful when onboarding to an unfamiliar codebase or before making significant changes.