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
47%
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/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 has good structural completeness with an explicit 'Use when' clause and identifies the domain clearly. However, it relies on broad category terms rather than listing specific concrete actions, and it lacks the natural trigger terms users would actually use when experiencing performance issues (e.g., 'slow page load,' 'high latency,' 'memory leak'). The description would benefit from more specificity in both capabilities and trigger vocabulary.
Suggestions
Add specific concrete actions such as 'analyze flame graphs, set up distributed tracing, optimize database queries, reduce bundle size, configure caching strategies' instead of broad categories like 'profiling' and 'tuning.'
Include natural user trigger terms like 'slow,' 'latency,' 'bottleneck,' 'load time,' 'memory leak,' 'CPU usage,' 'response time' that users would actually say when they have performance problems.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (performance optimization) and mentions some areas like 'profiling, observability, and backend/frontend tuning,' but these are broad categories rather than concrete specific actions like 'run flame graphs,' 'set up distributed tracing,' or 'optimize database queries.' | 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 'Use when' clause. | 3 / 3 |
Trigger Term Quality | Includes some relevant keywords like 'performance,' 'profiling,' 'observability,' and 'tuning,' but misses many natural user terms such as 'slow,' 'latency,' 'bottleneck,' 'load time,' 'memory leak,' 'CPU usage,' 'caching,' 'APM,' or 'metrics.' | 2 / 3 |
Distinctiveness Conflict Risk | The scope is somewhat specific to cross-stack performance optimization, but terms like 'profiling' and 'observability' could overlap with dedicated monitoring/observability skills or individual backend/frontend optimization skills. The phrase 'across the stack' helps differentiate but the boundaries remain fuzzy. | 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 ambitious end-to-end performance optimization workflow but suffers from extreme verbosity—the full prompt templates for each subagent are spelled out with redundant detail that Claude already knows. The workflow has reasonable phasing but lacks explicit validation checkpoints and feedback loops between phases. The entire content is monolithic with no progressive disclosure or supporting files, making it a heavy context-window burden.
Suggestions
Extract the 13 detailed subagent prompt templates into a separate reference file (e.g., PROMPTS.md) and keep SKILL.md as a concise overview of the phases with brief descriptions of each step.
Remove explanations of well-known concepts (Core Web Vitals definitions, what APM tools do, what code splitting is) and reduce each step to its essential instruction—the subagent type, key objective, and expected output format.
Add explicit validation checkpoints between phases, e.g., 'Verify baseline metrics are captured and reviewed before proceeding to Phase 2' and 'Confirm load test environment is non-production before executing Phase 4.'
Split configuration options and success criteria into a separate CONFIG.md or REFERENCE.md file to reduce the main skill's token footprint.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose with extensive prompt templates that Claude doesn't need spelled out in full. The extended thinking block, lengthy subagent prompts, and exhaustive tool/technology listings bloat the content significantly. Much of this (e.g., explaining what Core Web Vitals are, listing APM tools) is knowledge Claude already has. | 1 / 3 |
Actionability | The skill provides structured steps with specific tool invocations and subagent types, which gives some concrete guidance. However, there is no executable code—everything is prompt templates with placeholders like {context_from_phase_1} and $ARGUMENTS, making it more of a process description than copy-paste-ready instructions. | 2 / 3 |
Workflow Clarity | The phased structure (Profiling → Backend → Frontend → Load Testing → Monitoring) provides a clear sequence, and there is some validation in Phase 4. However, there are no explicit validation checkpoints between phases (e.g., 'verify baseline metrics are captured before proceeding'), no feedback loops for error recovery, and the load testing phase lacks safeguards like 'confirm non-production environment before executing.' | 2 / 3 |
Progressive Disclosure | This is a monolithic wall of text with 13 detailed steps all inline, no references to supporting files, and no bundle files to offload detail into. The configuration options, success criteria, and per-phase details could all be split into separate reference documents. Everything is crammed into one long document with no navigation aids. | 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
431bfad
- 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.