Purpose
Produce ready-to-send deadline reminders and status updates for active ad campaigns — calibrated to the recipient's role, how much time is left, and the channel — so production coordinators keep strategists and creative producers moving without rewriting messages or striking the wrong tone. Eliminates the daily drain of composing "just checking in" nudges while ensuring every message carries a clear ask, a hard date, and an escalation path.
When to Use
Invoke this skill when the user asks to:
- Draft a deadline reminder for an asset, script, cut, or approval that's coming due
- Send a status update to an account strategist on campaign progress
- Nudge a creative producer who is at risk of missing a delivery date
- Escalate a slipping deadline when a first reminder went unanswered
- Write a milestone kickoff or "we're on track" confirmation message
- Prepare a batch of reminders across multiple campaigns or recipients at once
Inputs Required
Before starting, collect:
- Campaign name: The active campaign or client the messages relate to
- Milestone and hard date: What's due and the exact deadline (date/time, timezone if relevant)
- Recipient role: Account strategist, creative producer, or both
- Current status: On track / at risk / already late — and what specifically is outstanding
- Urgency tier: How far out the deadline is (comfortable, tightening, imminent, overdue)
- Delivery channel: Email, Slack/Teams, or project-tool comment
- Prior contact: Whether this is a first touch or a follow-up to an unanswered message
If urgency tier is missing, infer it from the milestone date relative to today. If channel is missing, default to email plus a shorter Slack variant.
Instructions
Step 1: Set the Urgency Tier
Map the deadline distance to a tier that governs tone and directness:
- Comfortable (5+ business days out): Informational, low-pressure — "heads up, here's what's coming"
- Tightening (2–4 business days out): Confirming — "checking we're still on for [date], flag anything now"
- Imminent (same day or next day): Direct — clear single ask, explicit time, easy to answer in one line
- Overdue (past deadline): Escalation — states the miss factually, names the downstream impact, requests an immediate ETA
Step 2: Calibrate by Recipient Role
Adjust framing to what each role cares about:
- Account strategist: Cares about client-facing risk and timeline commitments. Lead with campaign status and any risk to what the client was promised. Keep asks about decisions and approvals.
- Creative producer: Cares about production load and clarity of deliverable. Lead with the specific asset and what "done" looks like. Keep asks about delivery of work product.
- Both / group message: Lead with the milestone, then split the ask — one line for the strategist (approval/decision), one for the producer (delivery).
Step 3: Build Each Message on the Same Skeleton
Every message uses this structure so recipients can act fast:
- Subject line / opener: Campaign + milestone + timeframe (e.g., "[Campaign] — final cut due Thursday EOD")
- Status line: One sentence on where things stand
- The ask: The single clearest action needed, with the hard date/time
- Why it matters: One line on the downstream dependency (only if it adds pressure that's warranted)
- Easy out: A one-tap way to respond ("Reply 👍 if on track, or flag the blocker")
Step 4: Generate the Message Set
Produce, for the primary scenario provided:
- Primary reminder: Full message in the requested channel, matched to tier and role
- Channel variant: If email is primary, a tightened Slack/Teams version (2–4 lines); if Slack is primary, an email version with a subject line
- Escalation variant: The next message to send if this one goes unanswered — one tier hotter, with a clear ETA request and, where appropriate, a note that the strategist/producer's manager or the client timeline is now in play
- On-track confirmation: A short positive-close message for when the recipient replies that they're fine — closes the loop and logs the commitment
Step 5: Apply Tone Guardrails
- Never guilt-trip or use passive-aggressive phrasing ("as I mentioned twice…")
- Name dates as dates, not "ASAP" or "soon"
- One ask per message — bundle nothing extra
- Escalations stay factual, not personal — reference the deadline and the dependency, not the person
Output Format
- Structure: Grouped by message type, each labeled with its tier, role, and channel
- Length: 500–800 words total across the message set
- Format: Ready-to-send message blocks (subject line where applicable, then body), not prose commentary
- Sections: Primary reminder → Channel variant → Escalation variant → On-track confirmation
- Tone: Warm, direct, and time-anchored — the tone of a coordinator people like working with because messages are short and unmistakably clear
Quality Checklist
Before delivering output, verify:
- [ ] Every message states the hard date/time explicitly — no "ASAP" or "soon"
- [ ] Each message contains exactly one primary ask
- [ ] The escalation variant is one tier hotter than the primary and requests a specific ETA
- [ ] Role calibration is visible — strategist messages lead with client risk, producer messages lead with the specific deliverable
- [ ] Channel variants match length norms (Slack 2–4 lines; email includes a subject line)
- [ ] No guilt-trip, passive-aggressive, or blame phrasing in any message
Notes
- The on-track confirmation is the most-skipped and most-valuable message — closing the loop turns a nudge into a logged commitment the coordinator can point to later
- For batch requests across multiple campaigns, generate one full set per campaign rather than merging recipients — merged deadline messages dilute the single ask
- When status is "at risk," resist softening the ask; the clearest, kindest message names the risk early enough to fix it
How to use this skill
This file is a Claude Code skill in Anthropic's standard format — markdown with YAML frontmatter at the top.
Installing in Claude Code:
~/.claude/skills/<folder-name>/SKILL.md— auto-loads in every session anywhere on your machine (recommended for skills you'll use across multiple projects)<your-project>/.claude/skills/<folder-name>/SKILL.md— auto-loads only when working in that project (recommended for project-specific skills)
Restart Claude Code or open a new session to register.
Using in Claude.ai, ChatGPT, Gemini, or other AI tools:
- Drag this file into a new chat, or copy and paste its contents
- Send your task or request as your next message — the AI will apply the skill where it fits
For Claude Code skill details: https://docs.anthropic.com/en/docs/claude-code/skills