Deploys an existing Power Pages code site to a Power Pages environment using PAC CLI. Handles tooling verification, authentication, environment confirmation, building, and uploading. Use when the user wants to deploy, upload, or publish their code site.
66
81%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
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 identifies the specific technology (Power Pages, PAC CLI), lists concrete actions in the deployment pipeline, and provides explicit trigger guidance with natural user terms. It is concise, well-structured, and highly distinguishable from other skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: tooling verification, authentication, environment confirmation, building, and uploading. Also specifies the tool (PAC CLI) and the target (Power Pages environment). | 3 / 3 |
Completeness | Clearly answers both 'what' (deploys Power Pages code site using PAC CLI, handles tooling verification, authentication, environment confirmation, building, uploading) and 'when' (explicit 'Use when the user wants to deploy, upload, or publish their code site'). | 3 / 3 |
Trigger Term Quality | Includes natural trigger terms users would say: 'deploy', 'upload', 'publish', 'code site', 'Power Pages'. These cover the common variations of how a user would phrase a deployment request. | 3 / 3 |
Distinctiveness Conflict Risk | Highly specific niche: Power Pages deployment via PAC CLI. The combination of 'Power Pages', 'PAC CLI', and 'code site' makes it very unlikely to conflict with other skills. | 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 excels at actionability and workflow clarity, providing a comprehensive, well-sequenced deployment guide with executable commands, clear decision points, and robust error handling paths. However, it is significantly over-verbose — the content could be reduced by 40-50% without losing any actionable information, as it repeats guidance patterns, over-explains straightforward concepts, and includes formatting overhead that doesn't add value. The monolithic structure would benefit from splitting troubleshooting and Phase 6 into separate reference files.
Suggestions
Reduce verbosity by removing repeated phrases like 'present the error to the user and help troubleshoot', consolidating the AskUserQuestion tables into a more compact format, and eliminating explanations of obvious concepts (e.g., how semicolon-separated lists work).
Extract the Troubleshooting section and Phase 6 (Handle Blocked JavaScript) into separate reference files, keeping only a brief summary and link in the main SKILL.md to improve progressive disclosure.
Remove the Progress Tracking table at the end since it duplicates the phase structure already described in the body — or consolidate it into a single compact reference at the top.
Condense the AskUserQuestion specifications — Claude can format user prompts appropriately without full table schemas for each interaction point.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~400+ lines, with significant redundancy. It over-explains concepts Claude can infer (e.g., what blocked attachments are, how semicolon-separated lists work), repeats instructions across phases (e.g., 'present the error to the user and help troubleshoot' appears multiple times), and includes extensive AskUserQuestion table formatting that could be condensed. The progress tracking table at the end largely duplicates the phase structure already described. | 1 / 3 |
Actionability | The skill provides fully executable commands at every step (pac help, pac auth who, pac pages upload-code-site, npm run build, etc.), specific error handling paths, concrete bash commands with proper argument placeholders, and clear decision trees for each outcome. Every phase has copy-paste ready commands. | 3 / 3 |
Workflow Clarity | The workflow is exceptionally well-sequenced across 6 phases with explicit validation checkpoints (verify PAC CLI → verify auth → confirm environment → deploy → verify → handle errors). Each phase has clear success/failure branching, feedback loops for retries (e.g., retry upload after unblocking JS, re-validate after installation), and the troubleshooting section addresses a specific misleading error with a concrete fix-and-retry loop. | 3 / 3 |
Progressive Disclosure | The skill references external files (skill-tracking-reference.md, scripts like check-activation-status.js, clear-site-cache.js) and other skills (/activate-site, /audit-permissions), which is good. However, the main SKILL.md itself is monolithic — the troubleshooting section, the detailed Phase 6 blocked JavaScript handling, and the extensive AskUserQuestion tables could be split into separate reference files. The content that is inline is overwhelming for a single file. | 2 / 3 |
Total | 9 / 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 | |
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.