activate-site
Activates and provisions a Power Pages website in a Power Platform environment via the Power Platform REST API. Use when the user wants to activate, provision, turn on, or enable a Power Pages website or portal.
68
83%
Does it follow best practices?
Impact
—
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.
This is a well-crafted skill description that clearly identifies its niche (Power Pages website activation) and provides explicit trigger guidance with multiple natural keyword variations. Its main weakness is that the capability description is somewhat narrow — it describes a single action (activate/provision) rather than multiple distinct operations — but this may accurately reflect the skill's scope.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names the domain (Power Pages website) and the primary action (activates and provisions), and mentions the mechanism (Power Platform REST API), but it describes essentially one action rather than listing multiple distinct concrete actions. | 2 / 3 |
Completeness | Clearly answers both 'what' (activates and provisions a Power Pages website via the Power Platform REST API) and 'when' (explicit 'Use when...' clause listing multiple trigger scenarios). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms: 'activate', 'provision', 'turn on', 'enable', 'Power Pages website', 'portal', and 'Power Platform'. These are the terms a user would naturally use when requesting this task. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — the combination of Power Pages, Power Platform REST API, and website activation/provisioning creates a very specific niche that is 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 skill with excellent workflow clarity — clear phases, explicit validation gates, comprehensive error handling with feedback loops, and concrete executable commands throughout. Its main weakness is length: the document is verbose for a single SKILL.md, with inline content (error tables, ALM marker writes, cloud domain mappings) that could be extracted to supporting files. The phase output summaries also add redundancy without adding clarity.
Suggestions
Extract the cloud-to-domain mapping table and the Phase 4.2 error handling matrix into a reference file to reduce the main skill's token footprint.
Remove the 'Output' summary blocks at the end of each phase — they restate what the actions already describe and add ~30 lines of redundancy.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is quite long (~300+ lines) with some redundancy — output summaries at the end of each phase repeat what was already stated, and some explanations (e.g., what Azure CLI login does, cloud URL domain tables) could be tightened. However, given the complexity of the multi-phase workflow, most content earns its place. The gate comments and ALM plan refresh explanations are verbose. | 2 / 3 |
Actionability | Every step provides concrete, executable commands with exact flags and arguments. The error handling table in Phase 4.2 maps specific status codes to specific actions. Scripts are called with full argument syntax, and the marker file write includes actual executable Node.js code. Decision points are explicit and copy-paste ready. | 3 / 3 |
Workflow Clarity | The 5-phase workflow is clearly sequenced with explicit validation checkpoints: Phase 1.4 checks activation status before proceeding, Phase 3 requires explicit user confirmation before mutation, Phase 4.2 has a comprehensive error-handling table with feedback loops (e.g., subdomain conflict loops back to Phase 2.2). The Key Decision Points section at the end reinforces critical branching logic. | 3 / 3 |
Progressive Disclosure | The skill is a monolithic document with all content inline rather than split across files. The cloud URL domain table, error handling matrix, and ALM plan refresh details could be extracted to reference files. Some references exist (skill-tracking-reference.md, scripts) but the main body carries substantial detail that could benefit from separation. For a skill of this complexity, more layering would help. | 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 | |
- Repository
- microsoft/power-platform-skills
- Commit
b4c46e9
- Reviewed
Table of Contents
Is this your skill?
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.