Design JSON Schema collections and CRUD patterns for Falcon Foundry apps. TRIGGER when user asks to "create a collection", "define a JSON schema", "store data in Foundry", runs `foundry collections create`, or needs help with indexable fields, FQL queries, or collection access patterns. DO NOT TRIGGER for workflow YAML, function handlers, or UI components — use the appropriate sub-skill.
83
82%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
100%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 is an excellent skill description that clearly defines its scope, provides rich trigger terms, and explicitly delineates boundaries with related skills. The DO NOT TRIGGER clause is a strong addition that minimizes conflict risk. The description is concise yet comprehensive, covering what the skill does, when to use it, and when not to use it.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: designing JSON Schema collections, CRUD patterns, indexable fields, FQL queries, and collection access patterns. Also specifies the platform context (Falcon Foundry apps). | 3 / 3 |
Completeness | Clearly answers both 'what' (design JSON Schema collections and CRUD patterns for Falcon Foundry apps) and 'when' (explicit TRIGGER clause with multiple scenarios). Also includes a DO NOT TRIGGER clause to reduce false positives, which adds further clarity. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms: 'create a collection', 'define a JSON schema', 'store data in Foundry', 'foundry collections create', 'indexable fields', 'FQL queries', 'collection access patterns'. These are terms users would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche (Falcon Foundry collections/JSON Schema). The explicit DO NOT TRIGGER clause for workflow YAML, function handlers, and UI components actively prevents conflicts with sibling skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong, highly actionable skill with excellent concrete examples covering CLI scaffolding, JSON Schema patterns, CRUD operations in both TypeScript and Python, and FQL query syntax. Its main weaknesses are length (could split detailed CRUD implementations into referenced files) and the lack of explicit validation/verification steps in the collection creation and data operation workflows. The content is well-organized with tables and clear sections but would benefit from trimming some redundancy and adding validation checkpoints.
Suggestions
Add explicit validation steps after collection creation (e.g., verify schema was copied correctly, test a sample PUT/GET cycle) to improve workflow clarity for this data-store operation.
Move the full TypeScript CRUD class and/or the full Python CRUD examples into referenced files (e.g., references/typescript-crud.md, references/python-crud.md) to reduce the main skill's length and improve progressive disclosure.
Remove minor redundancies — e.g., the 'Common Pitfalls' section repeats constraints about draft 7, collection naming, and max 10 indexes that are already stated in earlier sections.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient with good use of tables and code blocks, but it's quite long (~250 lines) and includes some explanatory text that Claude wouldn't need (e.g., explaining what NoSQL document stores are, explaining what upsert means). The 'Common Pitfalls' section partially repeats constraints already stated earlier. However, most content earns its place with platform-specific details Claude wouldn't know. | 2 / 3 |
Actionability | Excellent actionability with fully executable CLI commands, complete TypeScript and Python code examples for CRUD operations, concrete JSON Schema examples with both indexing patterns, specific API endpoints, FQL query syntax with examples, and manifest YAML configuration. Everything is copy-paste ready. | 3 / 3 |
Workflow Clarity | The CLI scaffolding section provides a clear sequence (write schema to /tmp, run create command, edit project copy), but there's no explicit validation step after schema creation or collection setup. The CRUD operations are well-documented but lack error recovery patterns — e.g., what to do if schema validation fails, or how to verify a collection was created correctly. For a skill involving data store operations, the absence of validation checkpoints is notable. | 2 / 3 |
Progressive Disclosure | The skill references external files (references/advanced-patterns.md, use-cases/collections.md, python-patterns.md) which is good progressive disclosure, but the main body is quite long with inline content that could be split out (e.g., the full TypeScript CRUD class, the full Python examples). The Reading Guide and Use Cases sections at the bottom provide navigation, but the bulk of the content is monolithic. No bundle files were provided to verify referenced paths exist. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
72%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 8 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
metadata_version | 'metadata.version' is missing | Warning |
metadata_field | 'metadata' should map string keys to string values | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 8 / 11 Passed | |
e7fa026
Table of Contents
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.