Name: application-performance-performance-optimization
Rating: 52.8 (1 reviews)
Author: sickn33

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.

Quality

60%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/application-performance-performance-optimization/SKILL.md

Quality

Content

50%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The skill is well-structured and provides concrete subagent invocations, but it is over-long and padded with concepts Claude already knows, lacks validation checkpoints between phases, and inlines everything instead of using reference files.

Suggestions

Trim the verbose Prompt paragraphs and remove the Extended thinking rationale block; trust Claude's knowledge of profiling, caching, and Core Web Vitals.

Add explicit validation gates between phases (e.g., 'Confirm baseline captured before optimizing'; 'Validate load-test improvement before moving to monitoring') with retry-on-failure loops.

Move per-phase prompt templates and the configuration/success-criteria detail into reference files referenced one level deep, keeping SKILL.md a concise overview.

Dimension	Reasoning	Score
Conciseness	The body is heavily padded — 13 phases each with a verbose 'Prompt:' paragraph re-explaining performance concepts Claude already knows, plus an Extended thinking block that restates the obvious workflow rationale, making it noticeably verbose rather than lean.	2 / 5
Actionability	Each phase gives a concrete Task tool invocation with a specific subagent_type and a ready-to-use prompt, so the guidance is largely executable; minor gaps are that prompts embed placeholders like {context_from_phase_1} that are not wired up.	4 / 5
Workflow Clarity	Steps are clearly sequenced across five phases with a Context/Output chain, but this is a batch/rollout operation with no explicit validation checkpoints or feedback loops between phases — the guideline caps such destructive/batch skills at 3.	3 / 5
Progressive Disclosure	It is organized into clear sections, but all 13 phases are inlined into a single monolithic SKILL.md with no reference files; bulk detail that should be split out (per-phase prompts, config) is inline, and no bundle files exist to offload it.	3 / 5
	Total	12 / 20 Passed

Description

71%Weight 40%Scale 1-5

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 is solid: it states concrete capabilities and includes an explicit 'Use when' trigger clause. Its main weakness is breadth — 'end-to-end performance across the stack' risks overlap with narrower single-domain skills.

Suggestions

Tighten the 'when' clause with concrete triggering situations (e.g., 'when the user reports slow page loads, high latency, or poor throughput and the bottleneck spans multiple layers').

Add common user-facing trigger terms like 'latency', 'slow app', 'throughput', or 'page load times' to better match natural phrasing.

Dimension	Reasoning	Score
Specificity	Names concrete actions — 'profiling, observability, and backend/frontend tuning' — but stays high-level rather than listing specific optimization techniques, leaving minor coverage gaps.	4 / 5
Completeness	Clearly states 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'), though the trigger clause is somewhat general rather than listing concrete triggering situations.	4 / 5
Trigger Term Quality	Includes natural phrases like 'Optimize ... application performance', 'profiling, observability', and 'Use when coordinating performance optimization', but lacks common synonyms like 'latency', 'slow app', or 'throughput' that users would say.	4 / 5
Distinctiveness Conflict Risk	'End-to-end application performance' spans backend, frontend, database, and infra, giving it a broad scope that could overlap with dedicated database, frontend, or observability skills depending on how those are defined.	3 / 5
	Total	15 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: sickn33/antigravity-awesome-skills
Path: skills/application-performance-performance-optimization/SKILL.md
Commit: 1f67c44

Reviewed: about 16 hours ago

Table of Contents

Discovery Implementation Validation

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.