AB officeclaw
Connect to personal Microsoft accounts via Microsoft Graph API to manage email, calendar events, and tasks. Use this skill when the user needs to read/write Outlook mail, manage calendar appointments, or handle Microsoft To Do tasks.
As a process B 68/100 · Nearly there — weak spots: inputs and preconditions, running it twice
IntegrationOutlookPersonal productivityInfrastructuretype and topics are labelled automatically from the skill text
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
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 · 0
✓ No critical or high findings
Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 5270 tokens (recommended < 5000); move details to references/ - note
frontmatter-keyunknown frontmatter key "homepage"
Process rating: all ten parameters 68/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 34 mutating operations with no state check
- 60Tools and files. Uses tools (bash, web, python) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 70Execution cost. Instruction body is 5270 tokens
- 100Steps. 62 steps
- 100Failures and branches. 3 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 10 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
- +4Description does not say when NOT to use the skill (false activations)
- +2Single-language instructions
- +3Description length 233: enough signal without eating the budget
- +4Structure: 23 headings
- +3Step-by-step instructions: 62 items
- +3Output format is stated explicitly
- +4Has examples (13 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 77.
External checks
ClawHub: clean
OfficeClaw is a clearly disclosed Microsoft Graph integration, with meaningful account-access risks that are mostly scoped by user-controlled permissions and safety gates.
LLM: benign (medium) · VirusTotal: · 6 Sept 2026