菜单
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.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
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.
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.
Refactor code safely by analyzing blast radius and dependencies before making changes. Covers renaming, moving, extracting, and restructuring code with verification at each step. Use when refactoring, renaming symbols, extracting functions, moving files, or restructuring code.
| name | debug-performance |
| description | 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. |
| compatibility | Requires tokenlean CLI tools (npm i -g tokenlean) and git |
Find and fix performance bottlenecks by measuring, not guessing.
Measure → Identify → Analyze → Optimize → Confirm
Establish a baseline before touching anything:
tl-run "<benchmark or timed command>" # Capture current performance numbers
tl-complexity <file> # High complexity correlates with slow paths
tl-hotspots # Frequently-changed files accumulate debt
Find the actual bottleneck:
tl-flow <function> <file> # Full call chain of the slow operation
tl-deps <file> # Expensive imports or heavy initialization?
tl-symbols <file> # Map structure without reading everything
Understand why it's slow:
tl-snippet <function> <file> # Read only the functions on the hot path
tl-related <file> # Files contributing to the same bottleneck
tl-scope <function> <file> # Variable lifetimes and data flow
Apply the fix based on the bottleneck type:
# Algorithmic change
tl-flow <function> <file> # Verify new path is simpler
# Caching opportunity
tl-impact <file> # How many callers benefit?
# Reducing I/O
tl-deps <file> # Identify unnecessary imports
# Parallelization
tl-flow <function> <file> # Confirm no shared state
tl-run "<same benchmark>" # Measure improvement — no numbers, no claim
"It's slow" → Do you have a measurement?
├─ Yes (specific operation) → tl-flow on that operation
│ → tl-snippet on each function in chain
│ → Find the O(n^2) or blocking I/O
├─ Vague ("app is slow") → tl-hotspots + tl-complexity
│ → Profile top 3 complex files
│ → tl-flow on entry points to find hot paths
└─ Memory issue → tl-deps on entry point
→ Look for large imports, circular refs
→ tl-guard for circular deps