argent-metro-debugger

Debug a React Native app via Metro CDP using argent debugger tools. Use when connecting to Metro, inspecting React components, reading console logs, or evaluating JavaScript in the app runtime.

Quality

83%

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

78%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, mostly lean skill body with concrete commands and good progressive disclosure via real one-level-deep reference files. The main improvement would be tightening a couple of prose sections and adding one fully worked inspection example with an in-body validation loop.

Suggestions

Add a short end-to-end worked example for the inspect-element workflow (e.g. connect → inspect-element at (x,y) → read source fragment) to lift actionability to fully copy-paste ready.

Inline a brief 'validate via debugger-status before re-running the failing tool' checkpoint into the Golden Rules so the recovery feedback loop does not depend solely on the failure-scenarios reference.

Trim the adb-reverse paragraph and the log-registry prose to the essential steps to reduce remaining verbosity.

Dimension	Reasoning	Score
Conciseness	Lean and efficient — it assumes Claude knows what Metro, CDP, and React are, and uses dense tool tables — but the adb-reverse explanation and the log-registry prose could be tightened further.	4 / 5
Actionability	Concrete, executable guidance throughout (e.g. 'adb -s <serial> reverse tcp:8081 tcp:8081', 'grep -m 50', 'tail -N'), with documented tool returns; a full end-to-end worked example is the main missing piece.	4 / 5
Workflow Clarity	The log-registry workflow is numbered and the Golden Rules give a clear recovery sequence with 'debugger-status first' as a checkpoint, but the explicit validate-then-proceed loop for inspection is delegated to the failure-scenarios reference rather than stated in-body.	4 / 5
Progressive Disclosure	SKILL.md is a well-organized overview with clearly signaled one-level-deep references ('See references/source-maps.md', 'references/failure-scenarios.md', and the cross-skill workflow), and the Quick Reference table makes navigation easy.	5 / 5
	Total	17 / 20 Passed

Description

87%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 description that clearly answers what the skill does and when to use it, with concrete capabilities and distinct, low-conflict triggers. The only gap is that network inspection and the React profiler capabilities are not surfaced in the trigger list.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — 'connecting to Metro, inspecting React components, reading console logs, or evaluating JavaScript' — but omits network inspection and the React profiler, so coverage is not fully comprehensive.	4 / 5
Completeness	Explicitly states both the 'what' ('Debug a React Native app via Metro CDP using argent debugger tools') and the 'when' ('Use when connecting to Metro, inspecting React components, reading console logs, or evaluating JavaScript') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Natural trigger phrases like 'connecting to Metro', 'inspecting React components', 'reading console logs' align with what a user debugging RN would say, though common synonyms like 'RN', 'breakpoint', or 'debugger' are absent.	4 / 5
Distinctiveness Conflict Risk	The narrow niche ('Metro CDP', 'argent debugger tools', 'React Native app') gives clear, distinct triggers with minimal risk of firing for an unrelated skill.	5 / 5
	Total	18 / 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-metro-debugger/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.