AC claw-mail
Multi-account email management skill for IMAP/SMTP. Fetches, reads, searches, composes, sends, replies, forwards, and organizes emails across multiple accounts. Features IMAP Outbox for reliable delivery, secure credential storage via 1Password and macOS Keychain, TLS 1.2+ with hardened ciphers, OAuth2 authentication, IMAP IDLE push monitoring, connection pooling, S/MIME signing, calendar invitations, mail merge, conversation threading, webhook rule actions, and configurable dated-folder archival.
As a process C 61/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
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 · 3
✓ No critical or high findings
Medium and low: 3
-
low Exfiltration
exfil-webhook-urlreferences/REFERENCE.md:727Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)webhook_url: "https://hooks.slack.com/services/..."
placeholder -
low Secrets in code
secret-password-literalscripts/lib/smime.py:74Hard-coded password / key literal (may be an example)pwd = self…ode() if self…ord else None
A further 1 matches are quotations in this security skill's documentation and are not counted as findings.
Files scanned: 38. 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 61/100
- 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
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 17 mutating operations with no state check
- 100Tools and files. Tools declared in frontmatter
- 100Steps. 12 steps
- 100Failures and branches. 2 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2557 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 502: enough signal without eating the budget
- +4Structure: 22 headings
- +3Step-by-step instructions: 12 items
- +4Has examples (12 code blocks)
- +4Reference files are cited in the instructions (3 of 3)
- +3All 18 scripts are documented
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 80.