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, making it easy for Claude to know when to select this skill. However, it is weak on explaining what the skill actually does — it reads more like a trigger list than a capability description. Adding concrete actions (e.g., 'scaffolds project structure, configures routing, sets up build pipeline') would significantly improve it.
Suggestions
Add specific capability descriptions: what does the skill produce? E.g., 'Scaffolds a Power Pages code site with project structure, routing configuration, and build setup using React, Angular, Vue, or Astro.'
Restructure to lead with capabilities first, then follow with 'Use when...' clause, rather than starting with trigger phrases.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description mentions creating a Power Pages code site (SPA) using specific frameworks (React, Angular, Vue, Astro), which names the domain and some actions, but it doesn't list multiple concrete actions beyond 'create/scaffold'. It lacks detail on what the skill actually does (e.g., generates project structure, configures routing, sets up build tools). | 2 / 3 |
Completeness | The 'when' is very well covered with explicit trigger phrases, but the 'what' is weak — it only says 'create a new Power Pages code site' without describing what concrete outputs or steps the skill performs. The description is almost entirely trigger-focused with minimal capability explanation. | 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 the term 'SPA'. These are phrases users would naturally say. | 3 / 3 |
Distinctiveness Conflict Risk | The description is highly distinctive with 'Power Pages code site (SPA)' as a clear niche. The combination of Power Pages + specific frameworks makes it very unlikely to conflict with generic web development or other site-building skills. | 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 highly actionable and well-structured workflow skill with excellent sequencing, validation gates, and concrete executable guidance. However, it is severely over-long and verbose — explaining many concepts Claude already knows (basic git, npm, CSS variables, accessibility fixes) and repeating instructions across phases. The monolithic structure with all phases inline rather than split into referenced sub-documents further inflates the token cost.
Suggestions
Reduce verbosity by removing explanations of concepts Claude already knows (git commands, what CSS variables are, common accessibility fixes, how npm install works) — just provide the specific commands and patterns unique to this workflow.
Extract detailed phase instructions (especially Phases 5 and 6) into separate reference files and link to them from the main skill, keeping only summaries and key gates inline.
Remove or drastically shorten the Example Workflow section at the end — it largely restates what the phases already describe and adds ~60 lines of redundant content.
Consolidate repeated instructions (e.g., 'do NOT take screenshots — only use browser_snapshot' appears 4+ times; Playwright verification steps are repeated in multiple phases) into a single reference in the Important Notes section.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | This skill is extremely verbose at ~500+ lines. It over-explains many concepts Claude already understands (git commands, what CSS variables are, how to use npm install, what alt text is). Tables explaining common accessibility fixes, lengthy phase descriptions with repeated gate conditions, and extensive example workflows all contribute to significant token waste. Much of this could be condensed to 40-50% of its current size. | 1 / 3 |
Actionability | The skill provides highly specific, executable commands (git init, npm install, npm run dev), exact file paths with template variables, concrete Playwright verification steps, specific axe-core audit commands with flags, and detailed tables mapping violations to fixes. Code blocks are copy-paste ready with proper variable substitution patterns. | 3 / 3 |
Workflow Clarity | The 8-phase workflow is meticulously sequenced with explicit GATE conditions that must be met before proceeding (e.g., Phase 2 gate requires 6 specific conditions). Validation checkpoints are built into every phase — Playwright verification after changes, axe-core re-runs after fixes, git commits for rollback capability. Error recovery is addressed (git revert, re-verify loops). | 3 / 3 |
Progressive Disclosure | The skill references external files well (design-aesthetics.md, framework-conventions.md, skill-tracking-reference.md, template asset directories), but the main SKILL.md itself is monolithic — all 8 phases with full detail are inline rather than being split into separate reference files. The example workflow at the end duplicates information already covered in the phases. Content like the accessibility fix table and detailed git instructions could be in separate references. | 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 (605 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 | |
1132a35
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.