AC registration-scanner
Scans email accounts (Gmail, iCloud, Outlook, Yahoo, AOL, GMX, Web.de, Fastmail, Proton, T-Online and more) for registration, welcome and confirmation emails to build a chronological list of all services the user has ever signed up for. Triggers on phrases like "where am I registered", "scan my email for registrations", "show me all my accounts", "welche dienste habe ich", "wo bin ich registriert", "liste mes inscriptions", "encuentra mis registros".
As a process C 57/100 · Has gaps — weak spots: result and completion, inputs and preconditions, consistency
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- 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: 8. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when")
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. 4 mutating operations with no state check
- 40Consistency. Frontmatter name (registration-scanner) differs from the folder (email-registration-scanner)
- 60Tools and files. Uses tools (python) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 100Steps. 13 steps
- 100Failures and branches. 2 branches, has a failure section
- 100Execution cost. Instruction body is 1185 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 7 example trigger phrases
- +3Description length 454: enough signal without eating the budget
- +4Structure: 14 headings
- +3Step-by-step instructions: 13 items
- +4Has examples (2 code blocks)
- +4Reference files are cited in the instructions (2 of 2)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.