CtrlK
BlogDocsLog inGet started
Tessl Logo

react-native-brownfield-migration

Implements an accepted incremental brownfield migration from native iOS or Android to React Native or Expo using @callstack/react-native-brownfield. Use after the brownfield path has been selected, when setting up the integration, packaging XCFramework or AAR artifacts, or adding React Native surfaces to native hosts.

69

Quality

85%

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

71%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 index/router skill with clear sequencing, validation checkpoints, and excellent progressive disclosure, slightly weakened by duplicated navigation tables and the absence of executable commands in the body itself.

Suggestions

Collapse the 'Quick Reference' and 'Problem -> Skill Mapping' tables into a single routing table to remove the duplicated file listings and recover token budget.

Trim the 'When to Apply' section, which restates trigger conditions already covered by the frontmatter description.

Add an explicit fix-and-retry feedback loop (e.g. 'If packaging validation fails, fix the build and re-run before host integration') to lift workflow_clarity from good to exemplary.

DimensionReasoningScore

Conciseness

The body is mostly lean and assumes Claude's competence (no React Native primer), but the 'Quick Reference' and 'Problem -> Skill Mapping' tables duplicate the same reference-file routing, and 'When to Apply' restates trigger conditions already in the description.

4 / 5

Actionability

The body provides concrete routing logic (path-selection gate inspecting package.json/app.json) and explicit guardrails, but delegates all executable commands and code to reference files, so the SKILL.md itself offers high-level direction rather than copy-paste steps.

3 / 5

Workflow Clarity

A clear 5-step migration sequence is present with validation checkpoints ('Validate each packaging command before moving to host integration', 'validate startup/runtime' via agent-device), though explicit error-recovery feedback loops (fix-and-retry) are not spelled out.

4 / 5

Progressive Disclosure

SKILL.md is a well-organized overview pointing via two navigation tables and reference-style links to 10 real one-level-deep reference files in ./references/, all of which exist, giving easy navigation.

5 / 5

Total

16

/

20

Passed

Description

100%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 is concise, concrete, and fully answers both what the skill does and when to use it, with domain-natural trigger terms and a clearly bounded niche tied to a specific package.

DimensionReasoningScore

Specificity

Names multiple concrete actions including 'setting up the integration', 'packaging XCFramework or AAR artifacts', and 'adding React Native surfaces to native hosts', with specific artifact types giving comprehensive coverage.

5 / 5

Completeness

Explicitly states the 'what' ('Implements an accepted incremental brownfield migration... using @callstack/react-native-brownfield') and the 'when' ('Use after the brownfield path has been selected, when setting up the integration...') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Covers the natural domain vocabulary a user would say — 'brownfield migration', 'native iOS or Android', 'React Native or Expo', plus artifact file types 'XCFramework' and 'AAR'.

5 / 5

Distinctiveness Conflict Risk

Narrow niche pinned to a specific package and explicit post-selection sequencing ('Use after the brownfield path has been selected'), minimizing overlap with the related assess-migration skill.

5 / 5

Total

20

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 3 suspicious

Warning

Total

15

/

16

Passed

Repository
callstackincubator/agent-skills
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.