Name: application-performance-performance-optimization
Rating: 57.599999999999994 (1 reviews)
Author: boisenoise

Blog Docs Log in Get started

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

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

65%

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

The skill is highly actionable with concrete, tool-specific subagent prompts and a clear phased sequence, but it is held back by a padded narrative intro, missing validation feedback loops, and a monolithic inline structure with no progressive disclosure.

Suggestions

Remove the 'Extended thinking' narrative paragraph and the redundant opening line; let the phased structure convey the strategy without philosophy.

Add explicit validation checkpoints or feedback loops after optimization phases (e.g. 're-baseline and compare against Phase 1 metrics; if no improvement, revisit the bottleneck'), especially before load testing and rollout.

Move the detailed per-phase prompts, Configuration Options, and Success Criteria into one-level-deep reference files (e.g. PHASES.md, CONFIG.md) and keep SKILL.md a concise overview with signaled links.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with concrete tool and metric specifics, but the opening 'Extended thinking' narrative paragraph and the redundant intro line pad the skill with philosophy Claude already infers, keeping it off the lean score-3 anchor.	2 / 3
Actionability	Each of the 13 steps supplies a copy-paste-ready subagent prompt with specific tools (DataDog, New Relic, k6, Gatling, Redis, CloudFlare, OpenTelemetry) and concrete metrics, matching the fully-executable, specific-examples anchor.	3 / 3
Workflow Clarity	The five phases and 13 numbered steps are clearly sequenced with context/output fields, but there are no explicit per-step validation checkpoints or 'validate -> fix -> retry' feedback loops for the destructive/batch operations (production load testing, rollouts), which caps clarity at 2 per the rubric.	2 / 3
Progressive Disclosure	The content is organized into clear phases, but everything (all 13 detailed prompts, configuration, success criteria) is inline in a ~150-line SKILL.md with no bundle files or one-level-deep references, so content that should be split out is not.	2 / 3
	Total	9 / 12 Passed

Description

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 is well-formed with both a clear capability statement and an explicit 'Use when' trigger, but its action vocabulary and trigger terms are somewhat high-level and could overlap with narrower performance skills.

Suggestions

Add concrete user-facing trigger terms a person would actually say, such as 'the app is slow', 'high latency', or 'reduce response times', alongside the technical phrasing.

Sharpen specificity by listing discrete actions (e.g. 'profile bottlenecks, add caching, tune queries, optimize bundle size') instead of broad areas like 'observability' and 'backend/frontend tuning'.

Narrow the scope framing to reduce conflict risk, e.g. specify 'coordinating across backend, frontend, and infrastructure' only when no single-layer performance skill applies.

Dimension	Reasoning	Score
Specificity	The description names the domain ('application performance') and several actions ('profiling, observability, and backend/frontend tuning'), but these are high-level activity areas rather than the kind of discrete concrete verbs (e.g. 'extract text', 'fill forms') that define a score-3 anchor.	2 / 3
Completeness	It clearly answers both 'what' ('Optimize end-to-end application performance with profiling, observability, and backend/frontend tuning') and 'when' via an explicit 'Use when coordinating performance optimization across the stack' trigger clause, satisfying the highest anchor.	3 / 3
Trigger Term Quality	It includes relevant terms like 'performance optimization' and 'profiling' and an explicit 'Use when' trigger, but it misses the colloquial variations a user would actually say (e.g. 'the app is slow', 'latency', 'reduce response times'), so coverage is partial.	2 / 3
Distinctiveness Conflict Risk	Full-stack performance optimization is a recognizable niche, but the broad framing ('performance optimization across the stack') could overlap with narrower single-layer performance skills (database, frontend, CDN), so it is only somewhat distinctive.	2 / 3
	Total	9 / 12 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
Commit: f36337d

Reviewed: 2 days 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.