Name: application-performance-performance-optimization
Rating: 45.6 (1 reviews)
Author: rmyndharis

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

46%

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

35%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 well-structured into a coherent multi-phase optimization workflow, but it is verbose and lacks executable, copy-paste-ready guidance. It also keeps all detail in a single file with no bundle references and no explicit validation checkpoints between phases.

Suggestions

Remove the bracketed 'Extended thinking' paragraph and trim the repeated 'Context/Output' lines to essential deltas only, retaining the phase structure.

Add concrete, executable artifacts: example k6/Gatling load-test scripts, APM config snippets, or index-creation SQL, so steps are copy-paste ready.

Insert explicit validation checkpoints between phases (e.g., 'Before Phase 2: confirm baseline metrics captured and bottlenecks ranked') and move the per-phase prompt detail into reference files referenced one level deep.

Dimension	Reasoning	Score
Conciseness	The body is noticeably verbose: the bracketed 'Extended thinking' paragraph restates the workflow at length and each of the 13 phases repeats a near-identical 'Context/Output' scaffolding, padding that competes with context without adding new information.	2 / 5
Actionability	Guidance is high-level: it names subagent_types and lists topics to ask for in prose prompts, but there is no executable code, commands, or copy-paste-ready instructions, leaving the actual execution steps implicit.	2 / 5
Workflow Clarity	Phases 1-5 are clearly sequenced and steps are numbered, and there is a Safety section on gradual rollouts, but the phased workflow lacks explicit validation checkpoints (e.g., compare against baseline before proceeding) despite load testing and rollback being batch/destructive-adjacent operations.	3 / 5
Progressive Disclosure	It is organized into clear phases and sections, but everything is inlined in one monolithic SKILL.md with no external reference files (references/scripts/assets are absent), so content that could be split out stays inline and there are no one-level-deep references to navigate.	3 / 5
	Total	10 / 20 Passed

Description

58%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 competent: third-person, includes an explicit 'Use when' clause, and names the optimization domain. It is capped by generic action categories, limited natural trigger phrases, and overlap risk with more specialized performance skills.

Suggestions

Replace generic action categories with concrete actions (e.g., 'profile hot paths, add missing indexes, split frontend bundles, set Core Web Vitals budgets') to lift specificity.

Add natural user phrasings and synonyms to the trigger clause (e.g., 'Use when the user asks to speed up an app, reduce latency, improve load times, or hit performance/SLA targets').

Sharpen the niche to distinguish it from single-layer skills (e.g., 'Use when coordinating optimization across multiple stack layers, not for isolated single-component fixes').

Dimension	Reasoning	Score
Specificity	It names the domain (performance optimization) and concrete action areas ('profiling, observability, and backend/frontend tuning'), but the actions are generic categories rather than the multiple specific concrete actions (e.g., flame graphs, indexing, code splitting) that would warrant a 4.	3 / 5
Completeness	It has a clear 'what' ('Optimize end-to-end application performance with profiling, observability, and backend/frontend tuning') and an explicit 'Use when' trigger clause ('Use when coordinating performance optimization across the stack'), though the 'when' could be more specific about concrete scenarios.	4 / 5
Trigger Term Quality	It includes relevant terms like 'performance optimization', 'profiling', 'observability', and 'backend/frontend tuning', but lacks natural user phrases ('speed up my app', 'reduce latency', 'improve load times') and synonym variations, so keyword coverage is incomplete.	3 / 5
Distinctiveness Conflict Risk	'End-to-end application performance optimization' is somewhat specific but overlaps with narrower skills like database optimization, frontend performance, or observability skills, so the niche is not clearly distinct and conflict risk remains.	3 / 5
	Total	13 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: rmyndharis/antigravity-skills
Path: skills/application-performance-performance-optimization/SKILL.md
Commit: 3eff4af

Reviewed: 1 day 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.