AC intune-graph
Manage Microsoft Intune and Entra ID device management via the Microsoft Graph API. Use this skill whenever the user mentions Intune, MDM, managed devices, device compliance, device sync/reboot/lock/wipe/retire, Autopilot, enrollment, compliance or configuration policies, Settings Catalog, Conditional Access, app deployment/assignment, App Protection (MAM), Endpoint Security (BitLocker, Defender, Firewall, ASR), Windows Update rings, Apple DEP/ADE/VPP/APNS, Android Enterprise, Intune audit logs, or asks anything like "zeig mir alle Geräte", "ist Gerät X compliant", "sync den Laptop von …", "wipe device", "create a compliance policy" — even if they don't say "Graph API" explicitly.
As a process C 57/100 · Has gaps — weak spots: result and completion, inputs and preconditions, consistency
How to improve
- 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 · 0
✓ No critical or high findings
Files scanned: 16. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "homepage"
Process rating: all ten parameters 57/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 8 mutating operations with no state check
- 40Consistency. Frontmatter name (intune-graph) differs from the folder (openclaw-intune-skill)
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 100Steps. 22 steps
- 100Failures and branches. 2 branches, has a failure section
- 100Execution cost. Instruction body is 1615 tokens
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
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)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 6 example trigger phrases
- +3Description length 689: enough signal without eating the budget
- +4Structure: 6 headings
- +3Step-by-step instructions: 22 items
- +4Has examples (1 code blocks)
- +4Reference files are cited in the instructions (9 of 9)
- +3All 2 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 95.