CtrlK
BlogDocsLog inGet started
Tessl Logo

ui-development

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.

73

Quality

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Advisory

Suggest reviewing before use

SKILL.md
Quality
Evals
Security

Quality

Content

85%

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

A well-structured, highly actionable reference skill with executable commands, decision tables, validation checkpoints, and clean progressive disclosure to verified reference files. Its only weakness is moderate redundancy of critical warnings repeated across inline sections and the Common Pitfalls list.

Suggestions

Consolidate the repeated vite.config.js, manifest path/entrypoint, and run-from-app-root warnings into Common Pitfalls only, leaving brief inline pointers, to reduce redundancy and token cost.

Add a single numbered end-to-end checklist (scaffold → install/build → cd to app root → validate → deploy backend → foundry ui run) so the full workflow is visible in one place rather than distributed across sections.

Trim the ALL-CAPS 'SYSTEM INJECTION' preamble to essential directives only; the role statement and bold directives partially restate guidance already covered in later sections.

DimensionReasoningScore

Conciseness

Mostly efficient and high-signal — concrete code/tables with no basic-concept explanation — but several critical warnings are restated across sections (vite.config.js, manifest path/entrypoint, run-from-app-root appear both inline and in Common Pitfalls), so it could be tightened; not level 3 because of that redundancy, not level 1 because it assumes Claude's competence and avoids padding.

2 / 3

Actionability

Provides fully executable, copy-paste-ready CLI commands (e.g. "foundry ui pages create --name ... --from-template React --homepage --no-prompt") and complete code snippets with concrete values, matching the level-3 anchor.

3 / 3

Workflow Clarity

Sequences are clear (scaffold → build → deploy backend before `foundry ui run`) with explicit validation steps ("foundry apps run validates manifest on startup", "foundry apps validate") and error-recovery feedback (revert vite.config.js on path errors, cd back to app root), meeting the level-3 validation/checkpoint bar; not level 2 because checkpoints and recovery loops are explicit.

3 / 3

Progressive Disclosure

Keeps quick-start material inline and pushes detail to one-level-deep, well-signaled reference files (all seven referenced references/*.md files exist), with a Reading Guide table mapping tasks to files; matches the level-3 clear-overview-with-signaled-references anchor rather than the monolithic level-1 or loosely-organized level-2.

3 / 3

Total

11

/

12

Passed

Description

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.

A highly specific, third-person description that clearly states capabilities and provides explicit positive and negative triggers, covering natural user phrasings and CLI commands. It cleanly satisfies the what-and-when requirement with minimal padding.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — "Build UI pages and extensions", "add a Shoelace component", "call an API from the UI" — tied to specific frameworks (React/Vue, Shoelace, Foundry-JS), matching the level-3 anchor rather than the domain-only level 2.

3 / 3

Completeness

Explicitly answers both what (build Falcon Foundry UI pages/extensions with React/Vue + Shoelace + Foundry-JS) and when (a literal "TRIGGER when..." clause with multiple conditions), satisfying the level-3 what-AND-when requirement; not level 2 because the when is explicit, not implied.

3 / 3

Trigger Term Quality

Covers natural phrases users would say ("create a UI page", "build a UI extension", "add a Shoelace component") plus CLI invocations ("foundry ui pages create", "foundry ui run"), giving broad coverage of common variations beyond the level-2 single-keyword anchor.

3 / 3

Distinctiveness Conflict Risk

Occupies a clear niche (Falcon Foundry UI) with distinct triggers and explicit negative guidance ("DO NOT TRIGGER for backend functions, workflow YAML, or collection schemas"), making overlap with other skills unlikely; well above the generic level-1/2 anchors.

3 / 3

Total

12

/

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.

Validation13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

relative_links

Relative link issues: 2 suspicious

Warning

Total

13

/

16

Passed

Repository
CrowdStrike/foundry-skills
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.