BF ensure-pipelines-host
Ensures the tenant has a usable Power Platform Pipelines host environment before any pipeline operation runs. Detects host state via the same resolution order as the Power Apps UI (org-db setting → BAP env metadata → default-custom-host setting); if any existing host (Platform or Custom) is found, uses it. If no host is bound to the source env, provisions a new **Platform Host** (recommended, idempotent) or a **Custom Host** via the BAP env-create API with the `D365_ProjectHost` template, or guides the user through PPAC install / `New custom host` (manual fallbacks). Polls lifecycle operations, verifies the host responds to Pipelines API calls, writes a host-check artifact other ALM skills consume. Use when asked to: "set up pipelines host", "ensure pipelines host", "no pipelines host", "install pipelines", "create pipelines host", "provision platform host", "provision custom host". Also invoked transparently by /power-pages:setup-pipeline when its host discovery step finds nothing.
Ensures the tenant has a usable Power Platform Pipelines host environment before any pipeline operation runs.
As a process F 57/100 · Will not run — References files that are not bundled: scripts/lib/alm-thresholds.js, references/cicd-pipeline-patterns.md, scripts/lib/powerpages-hook-utils.js
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
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.
Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- The text references files that are not there: add them or drop the references.
- 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-toolsSKILL.md:1Broad tool permissions pre-approved: Bashallowed-tools: Read Write Edit Bash Glob Grep TaskCreate TaskUpdate TaskList AskUserQuestion mcp__plugin_power-pages_microsoft-learn__microsoft_docs_search mcp__plugin_power-pages_microsoft-learn__mic
Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 22221 tokens (recommended < 5000); move details to references/ - warning
missing-refreference to a missing file: scripts/lib/alm-thresholds.js - warning
missing-refreference to a missing file: references/cicd-pipeline-patterns.md - warning
missing-refreference to a missing file: scripts/lib/powerpages-hook-utils.js - note
edit-residuethe text marks something as outdated (lines 740): check that old rules are not kept next to new ones — the full check reads the text for contradictions
Process rating: all ten parameters 57/100
- 0Tools and files. 3 referenced file(s) missing: scripts/lib/alm-thresholds.js, references/cicd-pipeline-patterns.md, scripts/lib/powerpages-hook-utils.js
- 0Result and completion. Does not say what the result is
- 10Execution cost. Instruction body is 22221 tokens: crowds the task out of the window
- 50When it triggers. No condition that starts the skill
- 100Steps. 181 steps
- 100Inputs and preconditions. Inputs and preconditions are listed
- 100Failures and branches. 5 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 16 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 997: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -215 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +5Description quotes 7 example trigger phrases
- +4Structure: 40 headings
- +3Step-by-step instructions: 181 items
- +4Has examples (20 code blocks)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 65.