SKILLEMALL.ai
GitHub ↗ RU Sign in

BC author-webpage-content

Generates and fills the localized HTML body of an existing webpage in a PAC CLI-downloaded non-SPA Power Pages site from a resolved page-content specification. Use whenever a caller has resolved the existing webpage metadata and asks to compose, replace, append, or modify the exact localized `.webpage.copy.html` file with Design Studio-compatible sections, columns, flex containers, text, images, buttons, videos, iframes, Generative AI Search components, basic forms, lists, multistep forms, or spacers. This skill owns only HTML generation and the supplied target file; the coordinator's webpage reference workflow owns discovery, records, metadata, languages, routes, templates, navigation, and companion-file creation. Do not use for React, Angular, Vue, or Astro SPA sites.

The skillemall take

Generates HTML for localized Power Pages—fills ready-made `.webpage.copy.html` with sections, columns, text, images, buttons, forms, and search components. Promises Design Studio compatibility and works with PAC CLI-downloaded non-SPA sites.

Tests gave it a B grade with 92 quality and 95 safety score. One medium finding, no critical issues. The skill maps 15 files but process score sits at 63, suggesting coverage gaps. Models untested, sandbox never ran. The description cuts off mid-sentence on coordinator responsibilities, leaving unclear where this skill's authority ends.

Install it if you're already in Power Pages and need HTML generation for an existing template. Beginners may find it too narrow—requires pre-resolved metadata and routes.

microsoft/power-platform-skills Agent Skills author: microsoft 15 files body ≈ 2 792 tokens Open the sourcegithub.com↗ analyzed 9 d ago

Generates and fills the localized HTML body of an existing webpage in a PAC CLI-downloaded non-SPA Power Pages site from a resolved page-content specification.

As a process C 63/100 · Has gaps — weak spots: result and completion, inputs and preconditions, failures and branches

GeneratorData and analyticsMedia and videotype and topics are labelled automatically from the skill text
Runs in: Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) OpenClaw Goose OpenCode
JSON
Technical rating
B
94/100
safety, quality, tests
Safety 60%
95
Quality 40%
92
Run on models
none yet
Process rating
C
63/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
Failures and branches w 10
0
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Broad scope medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The skill asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.

For the author

Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.

How to improve

    For the model run — optional
    • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
    • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

    Guard findings · 1

    ✓ No critical or high findings

    Medium and low: 1
    • medium Broad scope meta-broad-allowed-tools SKILL.md:1
      Broad tool permissions pre-approved: Bash
      allowed-tools: Read Write Edit Grep Glob Bash TaskCreate TaskUpdate TaskList

    Files scanned: 15. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    ✓ No remarks against the Agent Skills spec

    Process rating: all ten parameters 63/100

    • 0Result and completion. Does not say what the result is
    • 0Inputs and preconditions. Does not say what the process needs to start
    • 0Failures and branches. Linear process with no failure handling
    • 0Progress reporting. Says nothing while it works
    • 100Tools and files. Tools declared in frontmatter
    • 100Steps. 52 steps
    • 100When it triggers. States when to use and when not to
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 2792 tokens
    • 100Running it twice. Mutating operations check current state
    • low 11 top-level sections: this looks like several domains in one skill

    Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

    Quality signals

    • +5Description has no quoted example phrases that should trigger the skill
    • +3Output format is not stated: the model decides each time
    • +1No license
    • +2Single-language instructions
    • +4Description says when NOT to use the skill
    • +3Description length 780: enough signal without eating the budget
    • +4Structure: 13 headings
    • +3Step-by-step instructions: 52 items
    • +4Has examples (3 code blocks)
    • +4Reference files are cited in the instructions (14 of 14)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 92.