メニュー
Improve performance in Codex by measuring baseline behavior, isolating hot paths, implementing focused optimizations, and confirming wins with before/after numbers.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Add new functionality by understanding existing patterns and dependencies before writing code. Locates where the feature belongs, studies conventions, implements following precedent, then verifies integration. Use when asked to add a feature, flag, endpoint, component, or module.
Thorough code review using token-efficient context gathering. Analyzes PRs, diffs, or staged changes by checking blast radius, complexity, and dependencies before reviewing the actual code. Use when asked to review a PR, review changes, or do a code review.
Systematically investigate and fix bugs using token-efficient context gathering. Reproduces the issue first, localizes with blame and history, traces the call path, then verifies the fix. Use when asked to fix a bug, investigate an error, or debug unexpected behavior.
Diagnose and fix performance issues by measuring before optimizing. Establishes baselines, identifies bottlenecks through call graphs and complexity analysis, then confirms improvements with numbers. Use when asked to optimize, speed up, reduce memory usage, or fix slowness.
Efficiently explore and understand an unfamiliar codebase using token-lean context gathering. Maps project structure, identifies key files, and builds understanding progressively without reading everything. Use when onboarding to a new project, asked to understand a codebase, or starting work in unfamiliar code.
Migrate frameworks, APIs, or language versions incrementally with verification at each step. Surveys the migration surface, batches work by dependency order, and commits after each verified batch. Use when asked to migrate between frameworks, upgrade major versions, or adapt to new API versions.
| name | debug-performance |
| description | Improve performance in Codex by measuring baseline behavior, isolating hot paths, implementing focused optimizations, and confirming wins with before/after numbers. |
| compatibility | Codex CLI with terminal access, git (tokenlean CLI optional) |
Measure first. Optimize second.
Measure -> Isolate -> Analyze -> Optimize -> Confirm
time <command>
Capture baseline metrics (latency, throughput, memory) before edits.
rg -n "<slow operation symbol>" src
rg -n "for |while |map\(|filter\(|reduce\(" <suspect-file>
Prioritize hot paths and repeated work.
Inspect only relevant functions/loops/I/O:
sed -n '1,260p' <suspect-file>
Check for:
time <same command>
npm test
Report before/after numbers. No numbers means no verified gain.