AC mailbutler
Narrative-aware inbox triage that reads real mail through an approved mailbox adapter, surfaces only what deserves the owner's attention, recommends reply or read actions, and maintains an evidence-backed local narrative. Use when asked to triage an inbox, identify what needs attention today, catch up across accounts, prepare a reply draft, or review what was handled quietly. Triage is read-only; drafts and sends require separate explicit per-message approval.
Narrative-aware inbox triage that reads real mail through an approved mailbox adapter, surfaces only what deserves the owner's attention, recommends reply or…
As a process C 53/100 · 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 · 1
✓ No critical or high findings
Medium and low: 1
-
low Concealment
en-hide-from-userreferences/security-contract.md:32Instruction to hide actions from the user (negated — the text forbids it)Mailbox contents may be processed only through services the owner has already approved. If the configured agent runtime uses a remote model, disclose that fact according to the runtime's policy. Do no
negated
Files scanned: 9. 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 53/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 11 mutating operations with no state check
- 40Consistency. Frontmatter name (mailbutler) differs from the folder (mailbutler-agent-skill)
- 50When it triggers. No condition that starts the skill
- 55Failures and branches. 1 branches
- 85Steps. 27 steps, 1 vague phrases
- 100Tools and files. No external tools needed
- 100Execution cost. Instruction body is 1641 tokens
- 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
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +3Description length 464: enough signal without eating the budget
- +4Structure: 12 headings
- +3Step-by-step instructions: 27 items
- +4Has examples (6 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
- +3All 1 scripts are documented
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 92.