create-component
Creates complete AEM components with dialog, HTL template, Sling Model, unit tests, and clientlibs. Supports extending Core Components and project components. When a Figma design URL is provided, fetches the design via Figma MCP (get_design_context) and translates it into pixel-perfect HTL, CSS, and JS. Follows Adobe Experience League best practices for AEM Cloud Service and 6.5. Use this skill whenever the user mentions creating, building, generating, or scaffolding an AEM component, or mentions component types like teaser, card, hero, banner, accordion, tabs, carousel, list, navigation, breadcrumb, or any custom AEM component. Also trigger when the user wants to extend a Core Component, create a component dialog, add a Sling Model, or convert a Figma design into an AEM component.
94
92%
Does it follow best practices?
Impact
Pending
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 clearly defines its scope, lists concrete capabilities, and provides comprehensive trigger guidance. It covers the AEM component development domain thoroughly with specific component types, technologies, and use cases. The explicit 'Use this skill whenever...' clause with natural trigger terms makes it highly effective for skill selection.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: creates dialog, HTL template, Sling Model, unit tests, clientlibs, supports extending Core Components, fetches Figma designs via MCP, translates to HTL/CSS/JS. Very comprehensive and concrete. | 3 / 3 |
Completeness | Clearly answers both 'what' (creates complete AEM components with dialog, HTL, Sling Model, tests, clientlibs; converts Figma designs) and 'when' with an explicit 'Use this skill whenever...' clause listing specific trigger scenarios. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'AEM component', 'teaser', 'card', 'hero', 'banner', 'accordion', 'tabs', 'carousel', 'Core Component', 'Sling Model', 'component dialog', 'Figma design', 'scaffolding'. These are terms AEM developers naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche targeting AEM (Adobe Experience Manager) component development specifically. The combination of AEM-specific terminology (HTL, Sling Model, Core Components, clientlibs, AEM Cloud Service) makes it very unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
85%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-structured, highly actionable AEM component creation skill with excellent progressive disclosure and clear workflow sequencing. Its main weakness is some redundancy in the configuration gate check section, where the same 'do not explore the codebase' instruction is repeated in multiple forms. Overall, it demonstrates strong domain expertise and provides concrete, executable guidance throughout.
Suggestions
Consolidate the configuration gate check — the 'do not explore' instruction appears in the gate check section, the 'Why you should not explore' subsection, and again in Step 0.2. Merge these into a single concise block to save ~15-20 lines.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly long (~300+ lines) with some redundancy — the configuration gate check is explained multiple times (sections 'Configuration Gate Check', 'Why you should not explore', and Step 0 repeat the same points). Some explanatory rationale (e.g., 'these sources may be outdated or inconsistent') could be trimmed. However, most content is domain-specific AEM knowledge Claude wouldn't inherently know, so the verbosity is partially justified. | 2 / 3 |
Actionability | The skill provides concrete file paths, exact XML resource types, executable Java code snippets (delegation pattern), specific MCP tool call syntax, field type mapping tables, and precise naming conventions. The guidance is highly specific and copy-paste ready for AEM component creation. | 3 / 3 |
Workflow Clarity | The workflow is clearly sequenced (Steps 0-4) with a numbered table overview, explicit validation checkpoints (configuration gate check before proceeding, dialog specification confirmation before creating, dependency verification for servlets), and clear decision tables for branching logic (extension tiers, dynamic content requirements). Error recovery is addressed (stop and display message if unconfigured). | 3 / 3 |
Progressive Disclosure | The skill is structured as an overview with clear, well-signaled one-level-deep references to specific reference files (references/dialog-patterns.md, references/htl-patterns.md, etc.). The reference table at the bottom provides excellent navigation. Each step indicates exactly which reference to load and why, following an on-demand loading pattern that keeps the main skill lean. | 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.
- Repository
- adobe/skills
- Commit
5bb2150
- 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.