flow
Use when you need to run Flow type checking, or when seeing Flow type errors in React code.
82
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
Discovery
62%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 has strong trigger terms and distinctiveness due to Flow being a specific technology, but lacks specificity about what concrete actions the skill performs. It tells Claude when to use it but not what it actually does beyond 'run type checking'.
Suggestions
Add specific capabilities: what does the skill do? (e.g., 'Runs Flow type checker, diagnoses type errors, suggests fixes for Flow annotations')
Expand the 'what' portion to list concrete actions like 'configure Flow, interpret error messages, add type annotations, fix type mismatches'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description only mentions 'run Flow type checking' without listing concrete actions. It doesn't specify what the skill actually does beyond triggering type checking - no mention of fixing errors, configuring Flow, or specific capabilities. | 1 / 3 |
Completeness | Has a 'Use when...' clause addressing when to use it, but the 'what does this do' portion is weak - it only implies running type checking without explaining what actions or capabilities the skill provides. | 2 / 3 |
Trigger Term Quality | Contains good natural keywords users would say: 'Flow type checking', 'Flow type errors', 'React code'. These are terms developers would naturally use when encountering Flow-related issues. | 3 / 3 |
Distinctiveness Conflict Risk | Flow is a specific type system distinct from TypeScript or other type checkers. The combination of 'Flow' + 'React' creates a clear niche that's unlikely to conflict with other skills. | 3 / 3 |
Total | 9 / 12 Passed |
Implementation
87%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-crafted, concise skill that efficiently teaches Flow type checking with specific commands and a helpful renderer reference table. The main weakness is the lack of a feedback loop for handling and verifying error fixes, which would strengthen the workflow for iterative type error resolution.
Suggestions
Add a brief feedback loop step after reporting errors, e.g., 'Fix errors and re-run `yarn flow $ARGUMENTS` until clean'
Consider adding an example of typical Flow error output to help with error interpretation
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient, presenting only essential information without explaining what Flow is or how type checking works. Every section earns its place with actionable content. | 3 / 3 |
Actionability | Provides specific, executable commands (`yarn flow $ARGUMENTS`, `yarn flow-ci`) with clear defaults and a practical renderer selection table. Instructions are copy-paste ready. | 3 / 3 |
Workflow Clarity | Steps are listed clearly but lack validation checkpoints. For a type-checking workflow, there's no guidance on what to do when errors are found or how to verify fixes were successful. | 2 / 3 |
Progressive Disclosure | For a simple, single-purpose skill under 50 lines, the content is well-organized with clear sections (Renderers table, Instructions, Common Mistakes) and doesn't require external references. | 3 / 3 |
Total | 11 / 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.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- 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.