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

26%

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

36%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.

The body is a generic React Native role description rather than a skill: it relies on knowledge Claude already has, offers one boilerplate example instead of project-specific guidance, and defines no executable workflow. The duplicated YAML config block between frontmatter and body further confuses the file's structure.

Suggestions

Replace the generic best-practice bullets with concrete, project-specific guidance (e.g. the project's navigation setup, state-management choice, exact commands to run/build/test like 'npx react-native run-ios --reset-cache').

Define an actual workflow with sequence and validation, e.g. 1. implement screen, 2. verify types with tsc, 3. run on both platforms via the project's test command, 4. only then report done.

Fix the file structure: remove the duplicated YAML frontmatter/config block so there is a single frontmatter block, and move the hooks/trigger config into clearly-signaled reference files if it is genuinely needed.

DimensionReasoningScore

Conciseness

The body spends much of its budget on concepts Claude already knows ('Use functional components with hooks', 'Test on both iOS and Android') and a 57-line boilerplate component example, with several padded/generic bullet sections that could be cut entirely.

2 / 5

Actionability

The single JSX component example is complete and executable, but the surrounding guidance is high-level hints ('Implement proper navigation (React Navigation)', 'Optimize images and assets') with no commands, configs, or concrete steps for the common cases.

3 / 5

Workflow Clarity

The numbered 'Key responsibilities' is a duty list rather than a sequenced process; there is no ordered workflow for building, running, or validating a change (e.g. no run/test/verify loop), leaving many gaps and no checkpoints.

2 / 5

Progressive Disclosure

The body has headed sections and is reasonably short with no bundle files, but the file is structurally malformed: a ~140-line duplicate YAML config block (triggers, capabilities, hooks) sits between the real frontmatter and the body, so overall organization is mediocre.

3 / 5

Total

10

/

20

Passed

Description

16%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 fails at its core job: it does not say what the skill does or when to use it. It reads as a machine-generated placeholder ('invoke with $agent-spec-mobile-react-native') rather than a capability description with natural trigger terms.

Suggestions

State concrete capabilities in third person, e.g. 'Develops React Native components and screens, implements React Navigation routing, integrates native modules for iOS and Android, and optimizes FlatList/image performance.'

Add an explicit 'when' clause with natural trigger terms: 'Use when the user mentions React Native, Expo, mobile apps, iOS or Android screens, or native module integration.'

Remove the invocation syntax ('$agent-spec-mobile-react-native') from the description — it consumes the character budget without helping trigger matching or telling Claude what the skill does.

DimensionReasoningScore

Specificity

The description ('Agent skill for spec-mobile-react-native - invoke with $agent-spec-mobile-react-native') names no concrete actions or capabilities; it only identifies the skill by slug and says how to invoke it, matching the 'pure abstract language, no concrete actions' anchor.

1 / 5

Completeness

There is only a vague 'what' ('Agent skill for spec-mobile-react-native' says nothing about what the skill does) and no 'when'/Use-when clause at all, matching the 'vague what and no when' anchor rather than anchor 3 which requires a clear what.

2 / 5

Trigger Term Quality

The only trigger term is the technical slug '$agent-spec-mobile-react-native'; natural phrases users would say ('react native', 'mobile app', 'iOS', 'Android', 'expo') are entirely absent, matching the 'no natural keywords; only technical jargon' anchor.

1 / 5

Distinctiveness Conflict Risk

The slug narrows the domain to React Native mobile development, which is somewhat specific, but the description provides no distinguishing trigger phrasing and could overlap with sibling mobile agents like spec-mobile-ios or spec-mobile-android.

3 / 5

Total

7

/

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
ruvnet/ruflo
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.