Build UI pages and extensions for Falcon Foundry apps using React or Vue with the Shoelace design system and Foundry-JS. TRIGGER when user asks to "create a UI page", "build a UI extension", "add a Shoelace component", "call an API from the UI", runs `foundry ui pages create` or `foundry ui run`, or needs help with Vite config, Foundry-JS, or Falcon console theming. DO NOT TRIGGER for backend functions, workflow YAML, or collection schemas.
69
86%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
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 covers all dimensions thoroughly. It provides specific capabilities, rich natural trigger terms including CLI commands, explicit 'when to use' and 'when not to use' guidance, and clear boundaries that distinguish it from related backend/workflow skills. The inclusion of negative triggers is a particularly strong practice for reducing conflict risk.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: building UI pages, building extensions, using React or Vue, Shoelace design system, Foundry-JS, Vite config, Falcon console theming, and calling APIs from the UI. | 3 / 3 |
Completeness | Clearly answers both 'what' (build UI pages and extensions for Falcon Foundry apps using React/Vue with Shoelace and Foundry-JS) and 'when' (explicit TRIGGER clause with multiple scenarios, plus a DO NOT TRIGGER clause for disambiguation). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would say: 'create a UI page', 'build a UI extension', 'add a Shoelace component', 'call an API from the UI', specific CLI commands like 'foundry ui pages create' and 'foundry ui run', plus technology names like Vite, Foundry-JS, and Falcon console theming. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche (Falcon Foundry UI development) and explicit negative triggers ('DO NOT TRIGGER for backend functions, workflow YAML, or collection schemas') that actively prevent conflicts with related backend or workflow skills. | 3 / 3 |
Total | 12 / 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 strong, highly actionable skill with excellent progressive disclosure and concrete, executable guidance for Foundry UI development. Its main weaknesses are moderate redundancy (repeated warnings about vite.config.js and manifest paths appear in multiple sections) and the lack of an explicit end-to-end workflow with validation checkpoints for the full create-build-test-deploy cycle. The content is well-structured and would serve Claude effectively in most UI development scenarios.
Suggestions
Consolidate the repeated warnings about vite.config.js and manifest.yml path/entrypoint into a single prominent section, and reference it from Common Pitfalls rather than restating the full details.
Add an explicit end-to-end numbered workflow (e.g., 'Creating and Deploying a UI Page') with validation checkpoints like 'run foundry apps validate' and 'verify in dev mode before deploying'.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient with good code examples and tables, but has notable redundancy — the warnings about not modifying vite.config.js and manifest.yml path/entrypoint are repeated multiple times (in dedicated sections AND again in Common Pitfalls). The 'SYSTEM INJECTION' header is unnecessary theater. Some pitfalls could be condensed. | 2 / 3 |
Actionability | Excellent actionability throughout — CLI commands are copy-paste ready with all required flags explained, code examples are executable JavaScript/TypeScript with real API calls, and the socket table provides exact technical IDs needed for commands. Every section gives concrete, specific guidance. | 3 / 3 |
Workflow Clarity | The skill covers individual steps well (scaffolding, building, running dev servers) and includes important sequencing notes (cd back to root, deploy backend before UI run). However, there's no end-to-end numbered workflow for creating and deploying a complete UI page or extension, and no explicit validation checkpoints (e.g., 'run foundry apps validate' after build, verify in browser before deploy). | 2 / 3 |
Progressive Disclosure | Excellent progressive disclosure with a clear Reading Guide table mapping tasks to reference files, well-signaled inline references throughout (e.g., 'see references/shoelace-reference.md'), and external GitHub repos for real-world examples. The main SKILL.md serves as a comprehensive overview without burying the reader in details that belong in reference files. | 3 / 3 |
Total | 10 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
metadata_version | 'metadata.version' is missing | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 9 / 11 Passed | |
631c815
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.