argent-react-native-optimization

Optimizes a React Native app by profiling first to find real bottlenecks, then sweeping for mechanical issues. Entry-point for all performance work. Use when the app feels slow, user asks to optimize, fix re-renders, reduce jank, or improve startup. Delegates to argent-react-native-profiler for measurement.

Quality

81%

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

Quality

Content

81%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.

A well-structured, actionable optimization playbook with strong validation feedback loops and clean progressive disclosure of detail into reference files. The main gaps are mild redundancy between the Pipeline and App-wide sections and one orphan reference file that is never linked from the body.

Suggestions

Link references/fix-reference.md from the body (e.g., in the Phase 3 Fix step or Rules) so every bundle file is reachable from the overview.

Either fold the 'App-wide optimization' section's distinct parallelization guidance into the Pipeline phases or shorten it to only the delta, removing the four-phase re-listing.

Inline the actual ESLint invocation command in Phase 1 (or cite the exact command from lint-rules.md) so the lint step is executable without opening the reference.

Dimension	Reasoning	Score
Conciseness	The body is lean and Claude-targeted with no concept teaching, but the 'App-wide optimization' section re-lists the same four phases already defined in the Pipeline, a minor redundant over-explanation that keeps it just below the 5 anchor.	4 / 5
Actionability	Highly concrete tool and skill invocations throughout (react-profiler-start/stop/analyze, react-profiler-fiber-tree, debugger-evaluate, debugger-log-registry, argent-create-flow) cover the cases, but the Phase 1 ESLint command is deferred to the reference rather than given inline, a minor gap versus fully copy-paste-ready.	4 / 5
Workflow Clarity	A clearly sequenced four-phase pipeline with a copy-in TODO checklist, explicit validation checkpoints (re-measure honestly, revert if no net benefit, Phase 4 verify no regressions, debugger-log-registry error check), and feedback loops matches the 5 anchor despite this being a batch/destructive optimization skill.	5 / 5
Progressive Disclosure	Good structure with one-level-deep, clearly signaled markdown links to lint-rules.md and semantic-checklist.md, but references/fix-reference.md is an orphan bundle file with no inbound link from the overview, a minor navigation gap that holds it at 4 rather than 5.	4 / 5
	Total	17 / 20 Passed

Description

82%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.

A strong, third-person description that explicitly covers both capability and concrete usage triggers within a distinct RN-performance niche. Its only weakness is specificity: it states two high-level strategies rather than enumerating several concrete optimization actions.

Suggestions

Add one or two concrete action verbs beyond 'profiling' and 'sweeping' (e.g., 'memoizes hot components, flattens lists, defers heavy work') to lift specificity toward the 4-5 anchors.

Consider adding a couple more colloquial trigger synonyms ('laggy', 'frame drops', 'freezes') to push trigger term coverage toward comprehensive.

The 'Entry-point for all performance work' phrase is broad; tightening it to 'Entry-point for React Native performance work' would further reduce any overlap risk with general perf skills.

Dimension	Reasoning	Score
Specificity	Names the React Native performance domain and two meta-actions ('profiling first to find real bottlenecks, then sweeping for mechanical issues') plus delegation, but does not enumerate several specific concrete actions as the 4 anchor requires; it is domain + 1-2 actions rather than comprehensive.	3 / 5
Completeness	Clearly answers both 'what' (optimize via profile-then-sweep, entry-point for performance work) and 'when' (explicit 'Use when...' clause with concrete trigger phrases), matching the 5 anchor almost exactly.	5 / 5
Trigger Term Quality	Five natural trigger phrases a user would actually say ('app feels slow', 'optimize', 'fix re-renders', 'reduce jank', 'improve startup') give good coverage, but synonyms like 'laggy', 'freeze', or 'frame drops' are missing so it falls just short of the comprehensive 5 anchor.	4 / 5
Distinctiveness Conflict Risk	Clear React Native performance niche with distinct triggers and an explicit delegation boundary ('Delegates to argent-react-native-profiler for measurement') that distinguishes it from the profiler skill, giving minimal conflict risk.	5 / 5
	Total	17 / 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: Uniswap/interface
Path: .agents/skills/argent-react-native-optimization/SKILL.md
Commit: da6d36f

Reviewed: 13 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.