reply-email — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited reply-email (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Draft email replies that sound like the user, not like AI.
/reply-email [message-id] or /reply-email + paste email text
/reply-email confirm [message-id] — 1-line confirmation/reply-email schedule [message-id] — propose dates + calendar link/reply-email followup [message-id] — gentle follow-upWhen user says "draft all" or during morning triage:
# Fetch the full message
gws gmail users messages get --params '{"userId":"me","id":"MESSAGE_ID","format":"full"}' --format jsonRead these files before drafting (every time):
skills/reply-email/email-voice-guide.md — real examples of how you writeskills/reply-email/learned-replies.md — corrections from past sessionsshared/communication-style.md — writing rulesEvery email draft MUST include the signature from skills/reply-email/signature.html.
The signature has two parts:
CDN-hosted images (always use these URLs):
https://elc-decks.pages.dev/assets/img/marian-signature.pnghttps://elc-decks.pages.dev/assets/img/elc26-signature-banner.pngWhen creating drafts via gmail_create_draft, use contentType: "text/html" and append the full signature HTML (photo + text + banner) after the body. Wrap the body text in <p> tags so line breaks render correctly.
Plain-text fallback (when HTML is not possible):
--
Marian Kamenistak
Founder @ ELC
[email protected]
+420 736 519 879
engineeringleaders.io | elc-conference.io
LinkedIn · Instagram · LumaRead the draft out loud. Does it sound like a real person typing fast between calls? Or does it sound like AI being polite? If the latter, cut half the words.
Default: create a Gmail draft, NOT send.
# Build base64url-encoded RFC 2822 email
RAW=$(python3 -c "
import base64, email.message
msg = email.message.EmailMessage()
msg['To'] = 'RECIPIENT_EMAIL'
msg['Subject'] = 'Re: ORIGINAL_SUBJECT'
msg['In-Reply-To'] = 'ORIGINAL_MESSAGE_ID_HEADER'
msg['References'] = 'ORIGINAL_REFERENCES_HEADER'
msg.set_content('''REPLY_BODY_HERE''')
print(base64.urlsafe_b64encode(msg.as_bytes()).decode())
")
gws gmail users drafts create \
--params '{"userId":"me"}' \
--json "{\"message\":{\"threadId\":\"THREAD_ID\",\"raw\":\"$RAW\"}}"Only send directly if user says "send it":
gws gmail +reply --message-id MESSAGE_ID --body "REPLY_TEXT"Configure these label IDs after creating them in Gmail (see INSTALL.md step 2b):
AI_READY_LABEL_ID=Label_XXX
INFO_LABEL_ID=Label_XXX
OPS_LABEL_ID=Label_XXX
HIGH_LABEL_ID=Label_XXX
BILLING_LABEL_ID=Label_XXXTo find your label IDs:
gws gmail users labels list --params '{"userId":"me"}' --format jsonWhen user gives feedback → incorporate, redraft, log correction.
drafts-log.mdlearned-replies.md### [YYYY-MM-DD HH:MM] [Thread ID] [Recipient]
**Subject:** Re: [subject]
**Draft ID:** [gmail draft id]
**Our draft:**
> [exact text]
**Status:** pending | sent-as-is | sent-with-edits | discarded~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.