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.
45
47%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/antigravity-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 establishes a clear domain (full-stack performance optimization) and includes an explicit 'Use when' clause, which is good. However, it relies on high-level category terms rather than listing concrete actions, and it lacks the natural trigger terms users would actually use when experiencing performance issues (e.g., 'slow,' 'latency,' 'bottleneck'). The broad scope creates some risk of overlap with more specialized performance skills.
Suggestions
Add concrete actions to improve specificity, e.g., 'Profile CPU and memory usage, analyze database query performance, reduce frontend bundle size, set up distributed tracing, identify bottlenecks.'
Include natural user trigger terms that describe symptoms, e.g., 'Use when the user mentions slow response times, high latency, bottlenecks, memory leaks, load time issues, or needs caching strategies.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (performance optimization) and mentions some areas like 'profiling, observability, and backend/frontend tuning,' but these are still fairly high-level categories rather than concrete actions. It doesn't list specific actions like 'profile CPU usage,' 'reduce bundle size,' or 'set up distributed tracing.' | 2 / 3 |
Completeness | Explicitly 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'). The 'Use when' clause is present and provides explicit trigger guidance. | 3 / 3 |
Trigger Term Quality | Includes some relevant terms like 'performance,' 'profiling,' 'observability,' and 'tuning,' but misses many natural user terms such as 'slow,' 'latency,' 'load time,' 'bottleneck,' 'memory leak,' 'caching,' 'response time,' or 'metrics.' Users often describe symptoms rather than solutions. | 2 / 3 |
Distinctiveness Conflict Risk | The scope is broad ('across the stack') which could overlap with more specific frontend performance skills, backend optimization skills, or database tuning skills. The phrase 'coordinating...across the stack' helps differentiate it as a cross-cutting concern, but terms like 'profiling' and 'tuning' could still conflict with more targeted skills. | 2 / 3 |
Total | 9 / 12 Passed |
Implementation
27%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is an overly verbose orchestration template that spells out 13 detailed prompt templates inline, resulting in a massive token footprint with limited executable value. While the phased structure and context-passing between steps show good workflow design intent, the lack of concrete code examples, missing feedback loops, and monolithic organization significantly reduce its effectiveness. The content would benefit greatly from aggressive condensation and splitting into referenced sub-files.
Suggestions
Condense the 13 steps into a concise checklist with key parameters, moving detailed prompt templates into separate phase-specific reference files (e.g., PHASE1_PROFILING.md, PHASE2_BACKEND.md).
Add explicit validation gates between phases (e.g., 'Do not proceed to Phase 2 unless baseline metrics are established and documented') and feedback loops for when optimizations cause regressions.
Replace verbose prompt templates with concrete, executable examples—actual CLI commands for profiling tools, sample k6 load test scripts, or real configuration snippets for monitoring setup.
Remove the extended thinking block and explanatory text about well-known concepts (Core Web Vitals definitions, what CDNs do) to respect Claude's existing knowledge.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose with extensive prompt templates that Claude doesn't need spelled out in full. The extended thinking block, detailed tool prompts for each of 13 steps, and explanations of well-known concepts (what Core Web Vitals are, what CDNs do) waste significant token budget. Much of this could be condensed to a structured checklist with key parameters. | 1 / 3 |
Actionability | Provides structured steps with specific tool invocations and named subagent types, which gives some concrete guidance. However, the actual instructions are prompt templates rather than executable code or commands—there are no real code snippets, CLI commands, or configuration examples that could be directly used. The guidance remains at the level of 'tell another agent to do X.' | 2 / 3 |
Workflow Clarity | The 5-phase, 13-step sequence is clearly laid out with logical progression and context passing between steps. However, validation checkpoints are weak—step 10 (load testing) comes late, and there are no explicit feedback loops for when optimizations fail or degrade performance. The safety section mentions rollback plans but doesn't integrate them into the workflow steps. Missing explicit validation gates between phases caps this at 2. | 2 / 3 |
Progressive Disclosure | The entire skill is a monolithic wall of text with no references to external files and no bundle files to support it. All 13 detailed steps with full prompt templates are inlined, making this extremely long. Content like configuration options, success criteria, and individual phase details could easily be split into separate reference files. | 1 / 3 |
Total | 6 / 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
- boisenoise/skills-collections
- Commit
e41e34a
- 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.