application-performance-performance-optimization
Optimize end-to-end application performance with profiling, observability, and backend/frontend tuning. Use when coordinating performance optimization across the stack.
56
Quality
51%
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 ./.agent/skills/application-performance-performance-optimization/SKILL.mdQuality
Discovery
67%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 has good structure with explicit 'what' and 'when' clauses, earning full marks for completeness. However, it relies on somewhat abstract terminology (profiling, observability, tuning) rather than concrete actions, and lacks the natural trigger terms users would actually say when experiencing performance issues. The scope is broad enough that it could conflict with more specialized performance skills.
Suggestions
Add concrete actions like 'analyze flame graphs, identify memory leaks, reduce bundle sizes, optimize database queries, implement caching strategies'
Include natural user trigger terms in the 'Use when' clause such as 'slow', 'latency', 'bottleneck', 'speed up', 'load time', or 'memory issues'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (performance optimization) and mentions some actions (profiling, observability, backend/frontend tuning), but these are high-level categories rather than concrete specific actions like 'analyze flame graphs' or 'reduce bundle size'. | 2 / 3 |
Completeness | Clearly answers both what ('Optimize end-to-end application performance with profiling, observability, and backend/frontend tuning') and when ('Use when coordinating performance optimization across the stack') with an explicit trigger clause. | 3 / 3 |
Trigger Term Quality | Includes some relevant terms like 'performance optimization', 'profiling', 'observability', but misses common natural variations users might say like 'slow app', 'latency', 'bottleneck', 'speed up', 'load time', or 'memory leak'. | 2 / 3 |
Distinctiveness Conflict Risk | The 'across the stack' and 'end-to-end' framing provides some distinction, but 'performance optimization' is broad enough to potentially conflict with more specialized skills for frontend-only or backend-only optimization. | 2 / 3 |
Total | 9 / 12 Passed |
Implementation
35%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill serves as a high-level orchestration document that delegates to sub-skills, but lacks actionable content in the main file itself. The instructions are too abstract to be immediately useful, and the structure is confusing with a 'Phase 1' header that doesn't align with the 13 sub-skills listed. The extended thinking block wastes tokens on philosophical explanation rather than practical guidance.
Suggestions
Replace abstract instructions with concrete first steps: specific profiling commands, tool names, or example metrics to collect before delegating to sub-skills
Add a clear mapping between the 4 instruction steps and the 13 sub-skills (e.g., 'Step 1 uses sub-skills 1-3, Step 2 uses sub-skills 4-9')
Remove the extended thinking block entirely - it explains concepts Claude already understands and adds no actionable value
Add validation checkpoints between phases with specific criteria (e.g., 'Proceed to optimization only when baseline p95 latency is measured and documented')
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The extended thinking block adds unnecessary verbosity explaining the workflow philosophy. The 'Use this skill when' and 'Do not use this skill when' sections are reasonable but could be tighter. The instructions themselves are appropriately brief. | 2 / 3 |
Actionability | The skill provides only abstract guidance ('Confirm performance goals', 'Establish baselines', 'Execute phased optimizations') with no concrete commands, code examples, or specific tools. It describes what to do conceptually but not how to actually do it. | 1 / 3 |
Workflow Clarity | There's a 4-step instruction sequence and a mention of phased approach, but no validation checkpoints, no feedback loops for error recovery, and no concrete criteria for moving between phases. The safety section mentions rollback plans but doesn't specify how to implement them. | 2 / 3 |
Progressive Disclosure | The skill appropriately links to 13 sub-skills for detailed content, which is good progressive disclosure. However, the organization is confusing - 'Phase 1' header appears but phases 2-4 are not shown, and the sub-skills list doesn't clearly map to the phases mentioned in instructions. | 2 / 3 |
Total | 7 / 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
- Dokhacgiakhoa/antigravity-ide
- Commit
3395991
- 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.