AB inbox-triage
Runs a full inbox triage using the knowledge base created by the 'inbox-setup' skill. Light-intake by design (most invocations skip questions and run with KB-default preferences); asks at most 2 grill-me override questions when invocation is outside normal cadence or includes category-skip intent. Searches recent emails, classifies them via the user's taxonomy, researches new senders, generates recommendations, drafts replies (NEVER sends), delivers a report in the user's preferred format, and updates the knowledge base with learnings. Designed to run on a recurring schedule (1-3x daily) or on demand. Use when the user wants their inbox processed, in any variation (e.g., 'triage my inbox', 'inbox triage', 'check my email', 'run email triage', 'process my inbox', 'what's new in my email', 'handle my email', 'email triage'). Requires the inbox-setup skill to have been run first.
Runs a full inbox triage using the knowledge base created by the 'inbox-setup' skill.
As a process B 70/100 · Nearly there — weak spots: result and completion
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: 7. 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 70/100
- 0Result and completion. Does not say what the result is
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 85Steps. 92 steps, 1 vague phrases
- 100Failures and branches. 3 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3248 tokens
- 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 20 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (4 tags): a typed call is more reliable
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)
- +3Description length 889: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +4Structure: 23 headings
- +3Step-by-step instructions: 92 items
- +4Has examples (1 code blocks)
- +4Reference files are cited in the instructions (3 of 3)
- +3All 3 scripts are documented
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 89.