CtrlK
BlogDocsLog inGet started
Tessl Logo

agent-spec-mobile-react-native

Agent skill for spec-mobile-react-native - invoke with $agent-spec-mobile-react-native

51

1.16x
Quality

25%

Does it follow best practices?

Impact

99%

1.16x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/agent-spec-mobile-react-native/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

50%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body pairs a concrete JSX example with organized sections, but it is padded by a large inline agent-spec YAML block and general-knowledge guidance, and it lacks a real multi-step workflow with validation checkpoints.

Suggestions

Move the large inline agent-spec YAML config out of the body or trim it heavily; it duplicates trigger/capability info and consumes tokens without instructing Claude.

Replace general-knowledge bullets ('Use functional components with hooks', 'Test on both iOS and Android') with project-specific conventions Claude could not infer.

Add a concrete multi-step workflow with validation checkpoints (e.g., build -> run on iOS simulator -> run on Android emulator -> verify) instead of a loose responsibilities list.

DimensionReasoningScore

Conciseness

The markdown portion is reasonably lean and includes a useful code example, but the ~140-line embedded YAML agent-spec block and general-knowledge bullets ('Use functional components with hooks', 'Test on both iOS and Android') add tokens Claude doesn't need, fitting 'mostly efficient but could be tightened' rather than the lean level 3.

2 / 3

Actionability

One complete, copy-paste JSX component example provides concrete guidance, but most surrounding direction ('Handle platform differences appropriately', 'Optimize images and assets') is abstract and incomplete, matching level 2 rather than the fully-executable level 3.

2 / 3

Workflow Clarity

A numbered responsibilities list and best-practices bullets give loose structure, but there is no sequenced multi-step workflow and no validation checkpoints, which fits 'sequence present but checkpoints missing' rather than the explicit-validation level 3.

2 / 3

Progressive Disclosure

Sections are organized (responsibilities, best practices, patterns, platform notes) with no broken nested references, but the large inline YAML config is content that arguably belongs in a separate file and there are no signaled external references, matching level 2 rather than the well-split level 3.

2 / 3

Total

8

/

12

Passed

Description

0%

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 a templated invocation label rather than a capability statement: it names no concrete actions, includes no natural trigger terms, and provides no 'when to use' guidance, making it indistinguishable from sibling spec-mobile skills.

Suggestions

Rewrite the description to state concrete actions, e.g. 'Scaffold React Native screens, implement React Navigation, and integrate native modules for iOS and Android'.

Add an explicit 'Use when...' trigger clause with natural user terms such as 'React Native app', 'mobile app', 'iOS/Android screen', or 'Expo'.

Replace the generic 'Agent skill for X - invoke with $X' phrasing with capability language that distinguishes this skill from spec-mobile-ios and spec-mobile-android.

DimensionReasoningScore

Specificity

The description ('Agent skill for spec-mobile-react-native - invoke with $agent-spec-mobile-react-native') names the skill and its invocation syntax but states zero concrete actions, matching the 'vague or no actions' anchor rather than level 2 which requires named actions.

1 / 3

Completeness

It conveys only a label for what the skill is and nothing about what it does, with no 'Use when...' trigger guidance; the missing explicit trigger clause and absent substantive 'what' keep it at level 1 rather than level 2.

1 / 3

Trigger Term Quality

The only terms are the technical identifier 'spec-mobile-react-native' and the invocation syntax '$agent-spec-mobile-react-native'; no natural user phrasing like 'React Native app' or 'mobile app' appears, so it sits at level 1 rather than level 2 which needs some relevant keywords.

1 / 3

Distinctiveness Conflict Risk

The templated 'Agent skill for X - invoke with $X' form is identical across sibling spec skills (e.g. spec-mobile-ios, spec-mobile-android referenced in the body), so it would conflict and fail to distinguish, matching the level 1 anchor rather than the somewhat-specific level 2.

1 / 3

Total

4

/

12

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
ruvnet/claude-flow
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.