This skill should be used when the user asks to "create a power pages site", "build a code site", "scaffold a website", "create a portal", "make a new site", or wants to create a new Power Pages code site (SPA) using React, Angular, Vue, or Astro.
71
67%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/power-pages/skills/create-site/SKILL.mdQuality
Discovery
72%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
The description excels at trigger term coverage and distinctiveness, providing numerous natural phrases users would say and clearly scoping to Power Pages SPA sites. However, it is weak on describing what the skill actually does — it focuses almost entirely on when to use it without explaining the concrete actions or outputs (e.g., scaffolding project structure, generating configuration files, setting up routing).
Suggestions
Add concrete capability descriptions before the trigger clause, e.g., 'Scaffolds a new Power Pages code site (SPA) with project structure, routing configuration, and framework-specific templates for React, Angular, Vue, or Astro.'
Reframe to lead with 'what it does' followed by 'Use when...' to clearly separate capabilities from trigger conditions, improving completeness.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description mentions creating a Power Pages code site (SPA) using specific frameworks (React, Angular, Vue, Astro), but it doesn't list concrete actions beyond 'create/build/scaffold'. It names the domain and some context but lacks detail on what specific steps or outputs the skill produces. | 2 / 3 |
Completeness | The 'when' is very well covered with explicit trigger phrases, but the 'what' is weak — it only says it creates a Power Pages code site without describing what that entails (e.g., generating project structure, configuring routing, setting up templates). The 'what does this do' portion is underdeveloped. | 2 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms: 'create a power pages site', 'build a code site', 'scaffold a website', 'create a portal', 'make a new site', plus framework names (React, Angular, Vue, Astro) and 'SPA'. These are phrases users would naturally say. | 3 / 3 |
Distinctiveness Conflict Risk | The description is clearly scoped to Power Pages code sites (SPA) with specific framework mentions, making it highly distinctive. It's unlikely to conflict with general web development or other site-building skills due to the 'Power Pages' qualifier. | 3 / 3 |
Total | 10 / 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 is a comprehensive, highly actionable skill with excellent workflow clarity including explicit gates, validation loops, and error recovery. However, it is extremely verbose — repeating instructions multiple times, over-explaining concepts Claude already understands, and inlining massive amounts of detail that could be split into reference files. The token cost is very high relative to the unique information conveyed.
Suggestions
Reduce repetition: instructions like 'do NOT take screenshots — only use browser_snapshot' and 'the scaffold is completely replaced' appear 4-5 times each. State once in Core Principles and reference that section.
Extract Phase 5 (Implementation) and Phase 6 (Accessibility) into separate reference files (e.g., implementation-guide.md, accessibility-guide.md) with 2-3 line summaries in the main SKILL.md, reducing the monolithic structure.
Remove explanatory text Claude doesn't need — e.g., 'Its only purpose is to get the dev server running quickly so the user has something to look at while you plan and build' and similar rationale sentences throughout. Focus on instructions, not justifications.
Consolidate the example workflow section — it largely restates what the phases already describe and adds ~60 lines of redundant content.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~500+ lines. Extensively explains workflow mechanics, progress tracking, and process details that Claude can infer. Repeats instructions across phases (e.g., 'do NOT take screenshots' appears 5+ times, Playwright verification instructions repeated in nearly every phase). The scaffold explanation is stated multiple times. Much of this could be condensed to a fraction of the size. | 1 / 3 |
Actionability | Highly actionable with specific commands (npm install, git init, axe-audit.js invocations), concrete file paths, exact tool names (mcp__plugin_power-pages_playwright__browser_navigate), specific URL patterns for Unsplash, detailed tables for CSS variables, and copy-paste ready PowerShell commands. Every phase has clear, executable steps. | 3 / 3 |
Workflow Clarity | Excellent multi-step workflow with 8 clearly sequenced phases, explicit GATE conditions between phases (e.g., Phase 2 gate with 6 checkpoints, Phase 5 gate, Phase 6 gate), validation/verification loops (axe-core run → fix → re-run), git revert instructions for error recovery, and clear feedback loops throughout. | 3 / 3 |
Progressive Disclosure | References external files appropriately (framework-conventions.md, design-aesthetics.md, skill-tracking-reference.md, asset directories), but the SKILL.md itself is monolithic — all 8 phases with full detail are inline rather than split into separate reference files. The component planning, accessibility verification, and implementation phases could each be their own reference documents with summaries in the main file. | 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 (603 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 | |
66a61c6
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.