Name: application-performance-performance-optimization
Rating: 70.6 (1 reviews)
Author: administrakt0r

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.

1.71x

Quality

58%

Does it follow best practices?

Impact

89%

1.71x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/application-performance-performance-optimization/SKILL.md

The canonical home for this skill is application-performance-performance-optimization in rmyndharis/antigravity-skills

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 lays out a thorough, well-sequenced 5-phase optimization workflow with concrete subagent dispatch instructions, but it is padded with an unnecessary Extended thinking preamble and lacks the validation/feedback checkpoints that batch and production-affecting operations require.

Suggestions

Remove or sharply condense the Extended thinking block at the top; Claude already understands workflow orchestration and does not need the process narrated.

Add explicit validation/rollback checkpoints between phases (e.g., 'Confirm baselines captured before Phase 2', 'Validate load test results against success criteria before proceeding', 'Verify rollback plan executed if metrics regress') to lift workflow_clarity past the destructive/batch cap.

Move the long per-step subagent prompts into one-level-deep reference files (e.g., references/phase1-profiling.md) and keep SKILL.md as an overview with signaled links, improving progressive disclosure and token efficiency.

Dimension	Reasoning	Score
Conciseness	The Extended thinking block narrates what the workflow does ('orchestrates a comprehensive performance optimization process...'), and each of the 13 step prompts is padded with background Claude already knows, making it noticeably verbose with several unnecessary explanatory sections, matching the score-2 anchor; not a 3 because the padding is pervasive rather than occasional.	2 / 5
Actionability	Each step gives a concrete Task-tool invocation with a specific subagent_type and a detailed prompt, providing mostly executable guidance with only minor gaps (placeholders like $ARGUMENTS and {context_from_phase_1}), matching the score-4 anchor; not a 5 because the prompts are parameterized templates rather than copy-paste-ready commands.	4 / 5
Workflow Clarity	Five phases and 13 sequenced steps each carry explicit Context and Output, but the workflow involves batch/destructive-adjacent operations (production load testing, infrastructure changes) with no inter-phase validation checkpoints or fix-retry feedback loops, so per the rubric cap workflow_clarity is held at 3.	3 / 5
Progressive Disclosure	The file is a single monolithic document with no external references (no references/, scripts/, or assets/ bundle files exist) and the 13 detailed subagent prompts are all inlined where separate reference files would aid navigation; it has clear section structure but content that could be split is inline, matching the score-3 anchor; not a 4 because nothing is offloaded to separate files.	3 / 5
	Total	12 / 20 Passed

Description

67%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 clearly states both what the skill does and when to use it, with concrete capability terms. It is held back from the top band by a generic 'when' trigger and limited keyword variation rather than comprehensive natural trigger phrases.

Suggestions

Expand the 'Use when...' clause with concrete natural trigger phrases users would actually say, e.g., 'latency is too high', 'slow database queries', 'page load times', 'throughput bottlenecks', or 'capacity planning'.

Add a few capability synonyms to the 'what' clause (e.g., 'reduce latency', 'improve throughput', 'cut infrastructure cost') to broaden natural keyword coverage.

Tighten distinctiveness by scoping the niche, e.g., 'across backend, frontend, and infrastructure' in the description itself rather than only in the 'when' clause.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete actions — 'profiling, observability, and backend/frontend tuning' — covering multiple specific actions with only minor gaps, matching the score-4 anchor.	4 / 5
Completeness	Both 'what' (optimize end-to-end performance with profiling, observability, backend/frontend tuning) and 'when' (Use when coordinating performance optimization across the stack) are present, but the 'when' could be more explicit/specific, matching the score-4 anchor; not a 5 because the trigger clause is generic.	4 / 5
Trigger Term Quality	Contains one natural trigger phrase ('Use when coordinating performance optimization across the stack') but lacks common variations or synonyms users would say (e.g., latency, throughput, slow queries, scaling), fitting the score-3 anchor; not a 4 because keyword coverage is thin.	3 / 5
Distinctiveness Conflict Risk	'End-to-end application performance' with explicit stack-wide coordination is a clear niche that is mostly distinct from narrower skills, with only minor overlap risk against related performance skills, matching the score-4 anchor; not a 5 because 'performance optimization' is broad enough to risk some overlap.	4 / 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: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: plugins/AI-Agents-Safe-Coding-Skills-claude/skills/application-performance-performance-optimization/SKILL.md
Commit: 6c06908

Reviewed: ~11 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.