argent-react-native-app-workflow

Step-by-step workflows for developing or debugging React Native apps on iOS simulator or Android emulator. Use when starting the app, debugging Metro, fixing builds, diagnosing runtime errors, or running tests.

Quality

88%

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

88%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 highly actionable, well-sequenced workflow skill with strong validation checkpoints and feedback loops. The main improvements are trimming the duplicated Quick Reference table and extracting the dense §3.6 stale-code gotchas into a reference file.

Suggestions

Trim or cross-link the 'Quick Reference: Tools & Commands' table, since most entries duplicate commands already shown in §1–§4, to recover token budget.

Move the detailed §3.6 EAS/gradle stale-code gotchas into a references/ file (e.g. ANDROID_RELEASE_CACHE.md) and keep a short symptom/pointer inline, improving both conciseness and progressive_disclosure.

Add a one-line 'Validation' callout in §3.4 confirming how to verify a reload took effect (e.g. expected 'Writing bundle output' log), making the rebuild-vs-reload feedback loop fully explicit.

Dimension	Reasoning	Score
Conciseness	Mostly lean commands, tables, and checklists that assume Claude's RN competence; the only padding is the 'Quick Reference' table which duplicates commands already given in the numbered sections.	4 / 5
Actionability	Abundant copy-paste-ready commands and tool invocations ('bun mobile start', 'npx react-native run-ios', 'adb -s <serial> reverse tcp:8081 tcp:8081', 'lsof -i :PORT') with parameterized placeholders covering the common cases.	5 / 5
Workflow Clarity	Clear numbered sequences (1.1–1.3, 3.1), explicit validation ('Verify Metro is ready' via debugger-status), feedback loops (build-fail order-of-operations, 'STOP and ask the user after 2-3 failed attempts'), and multiple agent checklists.	5 / 5
Progressive Disclosure	Well-organized into numbered sections with a Quick Reference and Related Skills table, and delegates detail to peer skills one level deep; however §3.6's lengthy project-specific gotchas are inlined rather than split into a reference file, and no bundle files exist.	4 / 5
	Total	18 / 20 Passed

Description

88%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 states both what the skill does and when to use it, with concrete trigger phrases and a well-scoped platform niche. It could add a few synonyms (e.g. 'bundling', 'build failures') to push trigger coverage to the top anchor.

Suggestions

Add synonyms for broader trigger matching, e.g. 'bundling', 'build failures', or 'JS bundle' alongside 'debugging Metro' and 'fixing builds'.

Consider noting the relationship to peer skills (e.g. 'for full Metro CDP debugging see argent-metro-debugger') to reduce overlap ambiguity at trigger time.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'starting the app, debugging Metro, fixing builds, diagnosing runtime errors, or running tests' — scoped to 'iOS simulator or Android emulator', giving comprehensive coverage of the RN app workflow.	5 / 5
Completeness	Explicitly states what ('Step-by-step workflows for developing or debugging React Native apps on iOS simulator or Android emulator') and when ('Use when starting the app, debugging Metro, fixing builds, diagnosing runtime errors, or running tests') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Good natural-term coverage ('starting the app', 'debugging Metro', 'fixing builds', 'runtime errors', 'running tests', 'iOS simulator', 'Android emulator') but lacks synonyms/extensions, so it stops short of the comprehensive-synonym anchor.	4 / 5
Distinctiveness Conflict Risk	Clear RN-on-simulator/emulator niche with distinct triggers, but minor overlap risk with closely related peer skills (argent-metro-debugger, argent-ios-simulator-setup) that handle sub-tasks.	4 / 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-react-native-app-workflow/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.