Creates a new Power Pages code site (SPA) using React, Angular, Vue, or Astro. Guides through the full process from initial concept to deployed site: requirements discovery, scaffolding, component planning, design, implementation, validation, and deployment. Use when the user wants to create, build, or scaffold a new Power Pages website or portal.
65
81%
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 a strong skill description that clearly communicates what the skill does, which frameworks it supports, the full workflow it covers, and when it should be triggered. It uses third person voice correctly, includes natural trigger terms, and has an explicit 'Use when' clause with relevant keywords. The description is concise yet comprehensive, making it easy for Claude to select appropriately from a large skill set.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: creating a new Power Pages code site (SPA), using specific frameworks (React, Angular, Vue, Astro), and enumerates the full process steps (requirements discovery, scaffolding, component planning, design, implementation, validation, deployment). | 3 / 3 |
Completeness | Clearly answers both 'what' (creates a new Power Pages code site using specific frameworks, guiding through the full process) and 'when' (explicit 'Use when the user wants to create, build, or scaffold a new Power Pages website or portal'). | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would say: 'Power Pages', 'create', 'build', 'scaffold', 'website', 'portal', 'SPA', 'React', 'Angular', 'Vue', 'Astro'. These cover common variations of how users would phrase requests for this task. | 3 / 3 |
Distinctiveness Conflict Risk | The combination of 'Power Pages' with 'code site (SPA)' and specific framework names creates a very distinct niche. This is unlikely to conflict with general web development skills or other CMS-related skills due to the Power Pages specificity. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
62%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is exceptionally well-structured with clear phases, explicit gates, and highly actionable instructions — it would be very effective at guiding Claude through the full site creation workflow. However, it is severely over-long, with extensive repetition (scaffold-status protocol explained 4+ times), unnecessary explanations of basic concepts (git commands, npm install), and inline content that should be in reference files. The token cost is very high relative to the unique information conveyed.
Suggestions
Extract the Live Preview Status Protocol, accessibility violation fix table, and example workflow into separate reference files to reduce the main SKILL.md by ~40%.
Remove explanations of basic operations Claude already knows (e.g., how git init/add/commit work, what npm install does, how to open files in a browser) — just provide the commands.
Consolidate scaffold-status.json update instructions into a single rule ('update before every AskUserQuestion and before each Phase 5 step') instead of repeating the full JSON shape and instructions in Phases 2, 3, 4, and 5.
Remove the Example Workflow section at the end — it restates the phases without adding new information and consumes ~80 lines of context.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~600+ lines. Extensively explains concepts Claude already knows (how to run git commands, how to use npm, what accessibility violations look like, how to open files in a browser). Many sections repeat instructions (e.g., the scaffold-status.json protocol is explained in detail in its own section, then re-explained in Phase 3, Phase 4, and Phase 5). The example workflow at the end largely restates the phases already described. | 1 / 3 |
Actionability | Highly actionable with specific commands, exact file paths, concrete JSON schemas, specific tool names (mcp__plugin_power-pages_playwright__browser_navigate), exact bash commands, and detailed tables mapping violations to fixes. Every phase has clear, executable steps. | 3 / 3 |
Workflow Clarity | Excellent workflow clarity with 8 clearly sequenced phases, explicit GATE conditions (Phase 2 and Phase 5 have detailed prerequisite checklists), feedback loops (Phase 6: fix → re-verify → repeat until passing), git revert instructions for error recovery, and clear validation checkpoints throughout. | 3 / 3 |
Progressive Disclosure | References external files appropriately (design-aesthetics.md, framework-conventions.md, skill-tracking-reference.md, asset templates), but the main SKILL.md itself is monolithic — the Live Preview Status Protocol, the full example workflow, and detailed accessibility fix tables could all be in separate reference files. The inline content is overwhelming despite having a reasonable reference structure. | 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 |
|---|---|---|
skill_md_line_count | SKILL.md is long (719 lines); consider splitting into references/ and linking | Warning |
allowed_tools_field | 'allowed-tools' contains unusual tool name(s) | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 8 / 11 Passed | |
b4c46e9
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.