CtrlK
BlogDocsLog inGet started
Tessl Logo

argent-react-native-profiler

Profile a React Native Hermes app to measure re-render and CPU performance using argent profiler tools. Use when optimizing for performance, measuring before/after a fix, spotting slow components, diagnosing re-renders, checking CPU hotspots, or producing a ranked issue report.

76

Quality

93%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

92%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, highly actionable profiling workflow with clear sequencing, validation checkpoints, and proper offloading of detailed tool reference material to a bundled file. Minor conciseness tightening possible around repeated post-fix emphasis.

DimensionReasoningScore

Conciseness

Mostly efficient and assumes Claude's competence without explaining basic React Native concepts, but the repeated "always re-profile / report honestly" emphasis across multiple sections could be tightened.

4 / 5

Actionability

Fully executable guidance with exact tool names, modes, and parameters (e.g. `profiler-cpu-query` mode=`component_cpu` component_name=`AppNavigator`) plus concrete JSON payloads in the referenced file covering common cases.

5 / 5

Workflow Clarity

Clear 8-step sequence with explicit validation checkpoints (fiber_renders_captured:0 warning, buildMode/strictMode checks) and a re-profile feedback loop for error recovery after fixes.

5 / 5

Progressive Disclosure

Body keeps the workflow overview while per-tool JSON examples are appropriately split into the one-level-deep, clearly signaled references/diagnostic-tools.md, which exists as a real file.

5 / 5

Total

19

/

20

Passed

Description

95%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, well-scoped description that clearly states capabilities and provides rich, natural trigger phrases in proper third-person voice. Only minor specificity gaps around the query/drill-down toolset.

DimensionReasoningScore

Specificity

Lists several concrete actions ("measure re-render and CPU performance", "producing a ranked issue report") tied to the React Native Hermes domain, with only minor gaps in coverage of the drill-down query capabilities.

4 / 5

Completeness

Explicitly answers both what ("Profile a React Native Hermes app to measure re-render and CPU performance") and when ("Use when optimizing for performance...") with concrete trigger phrases in third person.

5 / 5

Trigger Term Quality

Comprehensive natural trigger phrases users would actually say: "optimizing for performance", "spotting slow components", "diagnosing re-renders", "checking CPU hotspots", "measuring before/after a fix".

5 / 5

Distinctiveness Conflict Risk

Clear niche scoped to React Native Hermes profiling via argent profiler tools, with distinct triggers that minimize overlap with the sibling optimization skill.

5 / 5

Total

19

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
Uniswap/interface
Reviewed

Table of Contents

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.