AC gmail-filter-architect
Design, verify and import a complete Gmail filter system: a small emoji label taxonomy, urgent mail starred, bills/finance/infra/codes labelled, marketing and social auto-archived, forwarded accounts tagged by source. Built from a 90-day sender census of your own mailbox, every rule is checked against your real mail for misfires before import, and every archiving rule carries a shared protection group so bills, codes and security alerts are never hidden. Use for: cleaning up Gmail filters, bills landing in promotions, important mail getting archived, 'set up the best Gmail filters', labelling mail forwarded from other accounts. 中文:整理 Gmail 过滤器、账单被当营销收走、重要邮件看不到、转发来的邮件标记来源账号、要一套最好的过滤规则。
Design, verify and import a complete Gmail filter system: a small emoji label taxonomy, urgent mail starred, bills/finance/infra/codes labelled, marketing and…
As a process C 64/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice
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: 6. 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 64/100
- 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. 23 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 100Tools and files. No external tools needed
- 100Steps. 25 steps
- 100Failures and branches. 2 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1963 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low The response is described with custom markup (3 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)
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +3Description length 693: enough signal without eating the budget
- +4Structure: 10 headings
- +3Step-by-step instructions: 25 items
- +4Has examples (1 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.