This skill should be used when the user asks to "deploy to power pages", "upload site", "publish site", "deploy site", "push to power pages", "upload code site", or wants to deploy/upload an existing Power Pages code site to a Power Pages environment using PAC CLI.
85
83%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
89%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 completeness, providing explicit guidance on when to use the skill with multiple natural language variations. Its main weakness is that it focuses heavily on trigger conditions while providing limited detail about the specific concrete actions the skill performs (e.g., authentication steps, file packaging, environment configuration). The description also uses passive/imperative voice rather than third person, though this is a minor issue.
Suggestions
Add more specific concrete actions the skill performs, e.g., 'Authenticates to a Power Pages environment, packages site content, and uploads/deploys using PAC CLI commands' to improve specificity.
Rephrase to third person voice: 'Deploys an existing Power Pages code site to a Power Pages environment using PAC CLI' instead of starting with 'This skill should be used when...'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description mentions deploying/uploading a Power Pages code site using PAC CLI, which names the domain and a key action, but it doesn't list multiple specific concrete actions beyond deploy/upload variations. It lacks detail on what the skill actually does step-by-step. | 2 / 3 |
Completeness | The description explicitly answers both 'when' (with a clear list of trigger phrases) and 'what' (deploy/upload an existing Power Pages code site to a Power Pages environment using PAC CLI). The 'Use when' guidance is effectively provided via the opening clause. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms: 'deploy to power pages', 'upload site', 'publish site', 'deploy site', 'push to power pages', 'upload code site', 'PAC CLI'. These are phrases users would naturally say when needing this functionality. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche: Power Pages deployment via PAC CLI. The specific technology stack (Power Pages, PAC CLI) and action (deploy/upload code site) make it very unlikely to conflict with other skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
77%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 deployment skill with excellent workflow clarity and explicit validation/decision points at every phase. Its main weakness is length — the document is comprehensive but could benefit from extracting some sections (troubleshooting, blocked JS handling) into separate reference files to improve progressive disclosure and reduce token consumption. The actionability is exemplary with specific commands, error handling paths, and user interaction patterns clearly defined.
Suggestions
Extract the 'Troubleshooting: HTML Blocked Attachment Error' section and Phase 6 (Handle Blocked JavaScript) into a separate troubleshooting reference file, linking to it from the main skill.
Tighten Phase 6.1's explanation — Claude doesn't need the security rationale explained; just state the fix needed and ask permission.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is quite lengthy (~350+ lines) and includes some verbosity in explanations (e.g., Phase 6.1's explanation of why JS is blocked), but most content is necessary given the complexity of the multi-phase deployment workflow. Some sections like the AskUserQuestion tables add structural overhead that could be tightened. | 2 / 3 |
Actionability | Every phase includes specific, executable PowerShell commands, exact CLI flags, and concrete decision trees. Commands are copy-paste ready with clear placeholders, and error handling paths are explicitly defined with specific actions to take. | 3 / 3 |
Workflow Clarity | The 6-phase workflow is clearly sequenced with explicit validation checkpoints (verify CLI → verify auth → confirm environment → deploy → verify → handle errors). Feedback loops are present throughout: build failures trigger fix-and-retry, upload failures route to specific troubleshooting paths, and the HTML error troubleshooting includes a clear fix-and-retry loop. | 3 / 3 |
Progressive Disclosure | The skill is a monolithic document with all content inline rather than splitting detailed troubleshooting or reference material into separate files. It does reference external skills (/activate-site, /audit-permissions) and one external reference file (skill-tracking-reference.md), but the main document is very long and could benefit from extracting the troubleshooting section and Phase 6 into separate references. | 2 / 3 |
Total | 10 / 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.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
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 | 9 / 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.