m10-performance
CRITICAL: Use for performance optimization. Triggers: performance, optimization, benchmark, profiling, flamegraph, criterion, slow, fast, allocation, cache, SIMD, make it faster, 性能优化, 基准测试
82
78%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/m10-performance/SKILL.mdQuality
Discovery
72%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
The description excels at trigger term coverage with natural phrases like 'make it faster' and technical terms like 'flamegraph' and 'criterion', making it highly discoverable. However, it lacks specificity about what concrete actions the skill performs - it reads more like a keyword list than a capability description. The format is unconventional but functional for skill selection.
Suggestions
Add concrete actions describing what the skill does, e.g., 'Profiles code execution, identifies bottlenecks, optimizes hot paths, and implements caching strategies.'
Restructure to follow the pattern: '[What it does]. Use when [triggers]' rather than leading with 'CRITICAL: Use for' which doesn't describe capabilities.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (performance optimization) and lists related concepts (benchmark, profiling, flamegraph, criterion, SIMD, cache, allocation) but doesn't describe concrete actions like 'profile code', 'analyze bottlenecks', or 'optimize hot paths'. | 2 / 3 |
Completeness | The 'when' is addressed via 'Triggers:' list and 'Use for performance optimization', but the 'what' is weak - it doesn't explain what actions the skill actually performs beyond the general domain of performance optimization. | 2 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'performance', 'slow', 'fast', 'make it faster', 'optimization', 'benchmark', 'profiling', plus technical terms like 'flamegraph', 'criterion', 'SIMD', and even Chinese translations '性能优化', '基准测试'. | 3 / 3 |
Distinctiveness Conflict Risk | Clear niche focused specifically on performance optimization with distinct triggers like 'flamegraph', 'criterion', 'SIMD', 'profiling' that are unlikely to conflict with other skills. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-crafted design-level skill that excels at conciseness and organization. It effectively uses tables to compress decision guidance and provides clear workflows for optimization thinking. The main weakness is the lack of complete, executable code examples - the techniques are named but not fully demonstrated.
Suggestions
Add one complete, executable benchmark example using criterion to demonstrate the profiling workflow
Include a concrete before/after code snippet showing a common optimization (e.g., pre-allocation reducing allocations)
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely lean and efficient. Uses tables extensively to compress information, avoids explaining basic concepts Claude knows, and every section delivers actionable value without padding. | 3 / 3 |
Actionability | Provides concrete tool names and techniques with specific syntax examples (e.g., `Vec::with_capacity(n)`, `Cow<T>`), but lacks complete executable code examples. The guidance is specific but more reference-style than copy-paste ready. | 2 / 3 |
Workflow Clarity | Clear decision workflow with explicit priority ordering (1-5 optimization priority), decision tables mapping goals to implementations, and a structured 'before optimizing' checklist. The trace up/down navigation provides clear sequencing for the optimization process. | 3 / 3 |
Progressive Disclosure | Well-organized with clear sections, appropriate use of tables for quick reference, and explicit cross-references to related skills (m01-ownership, m07-concurrency, domain-*). Content is appropriately structured for a design-level skill. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- actionbook/rust-skills
- Commit
1f4becd
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.