api-schema-inferrer
This skill should be used when the user asks to "infer schemas", "generate schemas from examples", "add schemas", "bootstrap schemas", or mentions inferring, generating, or adding schemas to OpenAPI/OAS specifications that have examples but missing schema definitions.
68
83%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
89%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This description excels at trigger term coverage and completeness, clearly specifying when the skill should be activated with multiple natural phrasings. Its main weakness is that it focuses heavily on trigger conditions rather than describing the concrete actions the skill performs (e.g., analyzing example payloads, generating JSON Schema objects, inserting them into the spec). The description reads more like a trigger specification than a capability description.
Suggestions
Add concrete action descriptions of what the skill does, e.g., 'Analyzes example request/response payloads in OpenAPI specs to generate JSON Schema definitions, then inserts them into the appropriate schema components.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names the domain (OpenAPI/OAS specifications) and mentions actions like 'infer schemas', 'generate schemas from examples', 'add schemas', 'bootstrap schemas', but doesn't list concrete specific actions beyond these trigger phrases. It describes the scenario (specs with examples but missing schema definitions) but doesn't detail what the skill actually does step-by-step. | 2 / 3 |
Completeness | The description explicitly answers both 'what' (inferring/generating schemas for OpenAPI specs that have examples but missing schema definitions) and 'when' (when the user asks to infer, generate, add, or bootstrap schemas). The 'Use when' guidance is clearly embedded throughout the description. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms: 'infer schemas', 'generate schemas from examples', 'add schemas', 'bootstrap schemas', 'OpenAPI', 'OAS specifications', 'examples but missing schema definitions'. These are terms users would naturally use when needing this functionality. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche: schema inference specifically for OpenAPI/OAS specifications with examples but missing schemas. The combination of 'schema inference' + 'OpenAPI' + 'from examples' creates a very specific trigger profile unlikely to conflict with other skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid, actionable skill with clear workflow steps and excellent concrete examples. Its main weakness is moderate verbosity—some sections like 'When to Use', 'Using with Claude', and 'What It Does' add tokens without proportional value, as they either duplicate information shown in the example or explain things Claude can infer. The workflow is well-structured with appropriate validation checkpoints.
Suggestions
Remove the 'Using with Claude' section entirely—Claude doesn't need example prompts to know when to use the skill.
Condense or remove the 'When to Use This Skill' section since the skill description and the content itself make the use case obvious.
Consider moving the large before/after YAML example to a separate reference file to keep the main skill leaner.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient but includes some unnecessary content. The 'When to Use This Skill' section largely duplicates the description, the 'Using with Claude' section with example prompts is unnecessary padding, and the 'What It Does' bullet list partially repeats information already demonstrated in the example. The example before/after block is long but justified for clarity. | 2 / 3 |
Actionability | Provides fully executable commands with exact script paths, concrete before/after YAML examples showing expected output, and clear post-inference steps. The dry-run and apply commands are copy-paste ready, and the prerequisite installation command is explicit. | 3 / 3 |
Workflow Clarity | The workflow is clearly sequenced: preview with dry-run first, then apply changes (which auto-creates backups). The post-inference steps provide a clear checklist including validation via the api-spec-validator skill. The dry-run step serves as a validation checkpoint before destructive changes, and the backup creation is explicitly noted. | 3 / 3 |
Progressive Disclosure | The skill references related skills (api-spec-validator, api-doc-generator) and the script path, but all content is inline in a single file. The lengthy before/after YAML example could be in a separate file. No bundle files are provided, so we can't verify referenced paths. The structure is reasonable but the document is on the long side for a single file. | 2 / 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.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- mulesoft/mulesoft-dx
- Commit
32e2b58
- 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.