CtrlK
BlogDocsLog inGet started
Tessl Logo

flow

Use when you need to run Flow type checking, or when seeing Flow type errors in React code.

72

1.72x
Quality

56%

Does it follow best practices?

Impact

100%

1.72x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./.claude/skills/flow/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Discovery

40%

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 provides a reasonable 'when to use' clause with some relevant trigger terms like 'Flow type checking' and 'React code', but it severely lacks specificity about what the skill actually does. It reads more like a trigger condition than a full skill description, missing concrete actions and capabilities that would help Claude confidently select this skill.

Suggestions

Add specific capabilities the skill provides, e.g., 'Runs Flow type checker, diagnoses and fixes Flow type errors, configures .flowconfig, adds type annotations to React components.'

Expand trigger terms to include common variations like '.flowconfig', '@flow pragma', 'flow-typed', 'static type checking', and specific file extensions.

Restructure to clearly separate 'what' from 'when': start with concrete actions, then follow with 'Use when...' clause.

DimensionReasoningScore

Specificity

The description says 'run Flow type checking' which is a single vague action, and 'seeing Flow type errors' which describes a condition rather than a concrete capability. It doesn't list specific actions like 'configure Flow, fix type annotations, resolve type mismatches, add type definitions'.

1 / 3

Completeness

It has a 'Use when...' clause which addresses the 'when' question reasonably well, but the 'what does this do' part is very weak — it only implies running type checking without describing what the skill actually does or what capabilities it provides.

2 / 3

Trigger Term Quality

Includes relevant keywords like 'Flow', 'type checking', 'type errors', and 'React code' which users might naturally mention. However, it misses variations like 'flow-typed', '.flowconfig', 'type annotations', '@flow', or 'static typing'.

2 / 3

Distinctiveness Conflict Risk

The mention of 'Flow' specifically distinguishes it from TypeScript or general type-checking skills, but 'React code' is broad and could overlap with many React-related skills. The description could be more precise about its niche.

2 / 3

Total

7

/

12

Passed

Implementation

72%

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

This is a concise, well-structured skill that efficiently communicates how to run Flow type checking. Its main weakness is the lack of a feedback loop (run → find errors → fix → re-run) and the absence of concrete example output showing what type errors look like and how to address them.

Suggestions

Add a brief feedback loop to the workflow: after step 2, include 'Fix reported errors and re-run until clean' to make the iterative process explicit.

Add a short example showing sample Flow error output and the corresponding fix to improve actionability.

DimensionReasoningScore

Conciseness

The content is lean and efficient. It assumes Claude knows what Flow is, doesn't explain type checking concepts, and every section earns its place with actionable information.

3 / 3

Actionability

Provides the concrete command (`yarn flow $ARGUMENTS`) and a useful renderer table, but lacks example output of type errors or a concrete example of fixing a common error. The guidance is specific but not fully copy-paste demonstrable.

2 / 3

Workflow Clarity

The three steps are clear and sequenced, but there's no validation/feedback loop for handling errors—e.g., what to do when type errors are found, how to iterate on fixes, or when to re-run. For a type-checking workflow, a fix-and-recheck loop would be expected.

2 / 3

Progressive Disclosure

For a simple, single-purpose skill under 50 lines with no need for external references, the content is well-organized into clear sections (Renderers table, Instructions, Common Mistakes) that are easy to scan.

3 / 3

Total

10

/

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.

Validation11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository
facebook/react
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.