AB imap-client
Read, search, and download email over IMAP from the command line using the `myl` CLI client. Use this skill whenever the user wants to interact with their mailbox from a terminal — checking the inbox, listing or searching messages, reading a specific email, opening HTML or raw source, or saving attachments. Trigger on any of these cues even when `myl` is not named explicitly — "check my email", "look in my inbox", "search my mail for X", "find the email from Y", "download the attachment", "is there an email about Z", "read the latest message", "show me unread", "connect to my IMAP server", "imap.gmail.com", "imap.yandex.com", "imap.yandex.ru", "imap.mail.ru", "imap.fastmail.com", "Yandex Mail", "Mail.ru", "Gmail IMAP", "проверить почту", "новые письма", "найти письмо", and similar. Also trigger when the user asks to script or automate any of the above. Do not trigger for outgoing mail (sending, SMTP, drafting) — `myl` is read-only — or for desktop/GUI mail clients.
As a process B 68/100 · Nearly there — weak spots: inputs and preconditions, running it twice, progress reporting
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.
Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.
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 · 2
✓ No critical or high findings
Medium and low: 2
-
medium Dangerous commands
cmd-shell-rcreferences/installation.md:73Writes to a shell startup fileecho 'export PATH="$HOME/.local/bin:$PATH"' >> ~/.bashrc
-
medium Dangerous commands
cmd-shell-rcreferences/troubleshooting.md:29Writes to a shell startup fileecho 'export PATH="$HOME/.local/bin:$PATH"' >> ~/.bashrc && source ~/.bashrc
Files scanned: 10. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- 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
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 2 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
- 100Steps. 8 steps
- 100Failures and branches. 2 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1845 tokens
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)
- +3Description length 979: 120–800 characters recommended
- +2Single-language instructions
- +5Description quotes 20 example trigger phrases
- +4Structure: 13 headings
- +3Step-by-step instructions: 8 items
- +3Output format is stated explicitly
- +4Has examples (2 code blocks)
- +4Reference files are cited in the instructions (5 of 5)
- +3All 2 scripts are documented
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 96.