Name: application-performance-performance-optimization
Rating: 62.4 (1 reviews)
Author: boisenoise

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

74%

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/antigravity-application-performance-performance-optimization/SKILL.md

Quality

Content

65%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 content is highly actionable with concrete subagent prompts and tools throughout, but it is hurt by an unnecessary philosophy paragraph, missing inter-phase validation checkpoints for risky operations, and a monolithic structure that inlines content which could be split into reference files.

Suggestions

Remove or sharply trim the "[Extended thinking: ...]" paragraph; it restates workflow rationale Claude can already infer.

Add explicit validation checkpoints between phases (e.g., verify baselines before optimizing, validate load-test results before rolling out) to support the destructive/batch nature of the work.

Move the detailed per-phase prompts, Configuration Options, and Success Criteria into reference files referenced one level deep from SKILL.md to improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with templated Prompt/Context/Output per phase, but the lengthy "[Extended thinking: ...]" paragraph explains workflow philosophy that Claude could infer, and several sections could be tightened.	3 / 5
Actionability	Each of the 13 phases specifies a concrete subagent_type plus a copy-paste-ready prompt naming exact tools (DataDog, New Relic, k6, Gatling, OpenTelemetry) and concrete metrics, giving fully executable guidance.	5 / 5
Workflow Clarity	A clear 5-phase / 13-step sequence is present with per-step Context linking to prior outputs, but explicit validation checkpoints between phases are absent; for batch/destructive-adjacent work (load testing, prod rollouts) this caps workflow clarity at 3 per the rubric's feedback-loop guidance.	3 / 5
Progressive Disclosure	Section headers and phases provide structure, but all 13 detailed sub-prompts and reference-style content are inlined into a single monolithic SKILL.md with no one-level-deep reference files, and no bundle files are provided to offload the bulk.	3 / 5
	Total	14 / 20 Passed

Description

83%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 strong, clearly stating both the capability and an explicit use-when trigger with concrete techniques named. It would benefit from broader trigger-term synonyms (latency, throughput, slow) to improve retrieval.

Suggestions

Add natural trigger synonyms like "latency", "throughput", "slow", or "speed up" to broaden the trigger-term coverage.

Consider listing one or two more concrete actions (e.g., load testing, capacity planning) to push specificity toward comprehensive coverage.

Dimension	Reasoning	Score
Specificity	"Optimize end-to-end application performance with profiling, observability, and backend/frontend tuning" lists several concrete techniques (profiling, observability, backend/frontend tuning), but they remain at a fairly high level rather than enumerating a comprehensive set of actions.	4 / 5
Completeness	It explicitly states what the skill does ("Optimize end-to-end application performance with profiling, observability, and backend/frontend tuning") and when to use it ("Use when coordinating performance optimization across the stack"), answering both what and when concretely.	5 / 5
Trigger Term Quality	"coordinating performance optimization across the stack" includes natural phrasing users would say, but misses common synonyms and variations such as "slow", "latency", "throughput", or "speed up".	4 / 5
Distinctiveness Conflict Risk	"performance optimization across the stack" carves out a fairly distinct cross-stack niche, with only minor overlap risk against single-domain (frontend-only or backend-only) performance skills.	4 / 5
	Total	17 / 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: boisenoise/skills-collections
Path: skills/antigravity-application-performance-performance-optimization/SKILL.md
Commit: 652629d

Reviewed: ~12 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.