BF deliverability-qa
Use when the user asks to "run a deliverability pre-flight before I send", "check my SPF/DKIM/DMARC/BIMI", "why am I landing in spam / promotions", or "score my sender reputation and list hygiene"; runs the ONE-TIME pre-send SEND S1 authentication pre-flight and builds the SEND S (Sender-integrity / Deliverability) evidence read — DNS + DMARC-RUA auth, domain/IP reputation, inbox placement, content/link/render, and point-in-time bounce/complaint hygiene — using Pass/Partial/Fail/Unknown/N/A states and scoring only at complete applicable coverage. Not for the recurring hygiene trend — use list-hygiene-monitor; not for final EQS or veto verdicts — use email-quality-auditor; not for segments/suppression lists — use list-segment-builder. 邮件送达率预检/SPF DKIM DMARC认证/发件域声誉
Use when the user asks to "run a deliverability pre-flight before I send", "check my SPF/DKIM/DMARC/BIMI", "why am I landing in spam / promotions", or "score…
As a process F 51/100 · Will not run — References files that are not bundled: ../list-hygiene-monitor/SKILL.md, ../../deliver/email-quality-auditor/SKILL.md, ../../../protocol/consent-registry/SKILL.md
How to improve
- For Hermes the description must be one sentence under 60 characters; move the conditions to a "When to Use" section.
- The text references files that are not there: add them or drop the references.
- 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: 0. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-long-hermesdescription is 774 chars; the Hermes authoring standard requires ≤ 60 (one sentence, ending with a period) - warning
missing-refreference to a missing file: ../list-hygiene-monitor/SKILL.md - warning
missing-refreference to a missing file: ../../deliver/email-quality-auditor/SKILL.md - warning
missing-refreference to a missing file: ../../../protocol/consent-registry/SKILL.md - warning
missing-refreference to a missing file: ../../../references/skill-contract.md - warning
missing-refreference to a missing file: ../../../CONNECTORS.md - warning
missing-refreference to a missing file: ../../../scripts/connectors/README.md - warning
missing-refreference to a missing file: ../../../SECURITY.md - warning
missing-refreference to a missing file: ../../../references/send-benchmark.md - warning
missing-refreference to a missing file: references/deliverability-checklist.md - warning
missing-refreference to a missing file: ../list-segment-builder/SKILL.md - note
frontmatter-keyunknown frontmatter key "slug" - note
frontmatter-keyunknown frontmatter key "displayName" - note
frontmatter-keyunknown frontmatter key "summary" - note
frontmatter-keyunknown frontmatter key "homepage"
Process rating: all ten parameters 51/100
- 0Tools and files. 10 referenced file(s) missing: ../list-hygiene-monitor/SKILL.md, ../../deliver/email-quality-auditor/SKILL.md, ../../../protocol/consent-registry/SKILL.md
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 27 mutating operations with no state check
- 40Result and completion. Does not say what the result is
- 60Failures and branches. 2 branches
- 60Consistency. The Hermes dialect needs category and tags
- 100Steps. 26 steps
- 100When it triggers. States when to use and when not to
- 100Execution cost. Instruction body is 3060 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
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +5Description quotes 4 example trigger phrases
- +4Description says when NOT to use the skill
- +3Description length 774: enough signal without eating the budget
- +4Structure: 9 headings
- +3Step-by-step instructions: 26 items
- +4Has examples (3 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 73.