Intelligence · Claude Code skill

Campaign Intelligence skill and the Yalc Framework

The Friday morning agent that tells you what your LinkedIn campaigns actually did this week. Variant-aware, narrative-first, no dashboards.

Yalc Fit Score
9/10
License
MIT (Yalc)
Cadence
Weekly (Fri 11:00 CET)
Output
Slack + Notion
Last reviewed
2026-04-29
Trigger phrases

Say this to fire the Campaign Intelligence skill

Any of these natural language phrases activates the skill inside Claude Code.

campaign report
how are campaigns doing
variant results
campaign intelligence
compare variants
which angle is winning
campaign performance
weekly campaign report
What it does

Campaign Intelligence, plainly

The Campaign Intelligence skill runs every Friday at 11:00 CET. It pulls the week's data from the Unipile Campaigns DB and Variants DB, computes per-variant performance, identifies the winning angle, surfaces under-performers, and writes a narrative digest to Slack and a structured page to Notion.

Where Looker Studio dashboards make you go look at numbers, this skill brings the answers to you. The narrative format means the team gets aligned on the week's takeaways without a meeting. For Earleads agencies running 3 to 10 LinkedIn campaigns simultaneously, this is the weekly attention focus.

Where it slots in

Position in the GTM operating system

Intake
Enrich
Score
Route
Draft
Send
Listen

The Campaign Intelligence skill sits at the **listen** node for active LinkedIn campaigns. It reads the previous week's variant-level data, computes performance, and produces a narrative interpretation pushed to Slack.

The cadence (every Friday at 11:00 CET) is intentional. Friday mid-morning is when operators have time to act on the week's data before the weekend. Slower cadence (monthly) misses the chance to kill underperforming variants early. Faster cadence (daily) is noise.

The Yalc Framework

Running the Campaign Intelligence skill end to end

Workflow position

The weekly campaign analysis. Yalc runs this on schedule via launchd. Output is a Slack post plus a Notion summary. No dashboards required.

Required inputs

  • → Unipile Campaigns DB data source ID
  • → Campaign Variants DB data source ID
  • → Slack channel ID for posting
  • → [object Object]

Outputs

  • → Slack narrative digest (3 to 5 paragraphs, plain language)
  • → Notion summary page with variant-level numbers
  • → Per-campaign verdict (continue, kill, double down)
  • → Suggested action items for the operator (kill weakest variant, scale top, etc.)

Chaining recommendations

Upstream7 days of unipile-campaign sends + replies → campaign-intelligence (analysis)
DownstreamOperator action on Friday afternoon (kill, scale, draft new variants)

Anti patterns to avoid

Don't ignore the Friday digest. The cadence only works if the operator actually reviews on Friday. Push the Slack post to a channel you actually check.
Don't run this skill on campaigns under 50 sends per variant. Variance dominates signal at low volume. Wait until each variant has 50+ sends before drawing conclusions.
Don't optimize to vanity metrics (open rate, accept rate alone). The skill weights reply quality (intent classification) above acceptance.
Operator take

Pros, cons, who it's for

Pros

  • Weekly cadence catches underperformers before they waste another week
  • Variant-level reporting (not just campaign-level) surfaces winning angles
  • Narrative format reads in 2 minutes, faster than any dashboard
  • Slack + Notion output covers async (Notion) and sync (Slack) attention
  • Suggested actions, not just data

Cons

  • Requires at least 50 sends per variant for meaningful analysis. Quiet weeks produce thin reports.
  • Single-language (English). Voice in non-English campaigns less calibrated.
  • Doesn't handle complex multi-touch attribution (LinkedIn → email → call). Single channel only.
  • Relies on accurate intent classification of replies; bad classification = bad recommendations.

Who it's for

  • Operators running 3+ LinkedIn campaigns concurrently
  • Agencies managing campaign performance for multiple clients
  • Founders who want to know what's working without opening dashboards
Dependencies

What this skill expects to find

Other skills

MCP servers

Environment variables

Schedule via launchd plist `com.earleads.campaign-intelligence`. Runs every Friday at 11:00 CET. Reads the per-account Slack channel ID from the Yalc workspace config. Falls back to the default ops channel if no per-account override exists.

Related

The Campaign Intelligence ecosystem inside Yalc

Alternatives

Skills that overlap

FAQ

Frequently asked

Why Friday at 11:00?

Friday mid-morning gives operators time to act on the week's takeaways. Earlier in the week and the previous Friday's data isn't a full week. Later and the weekend swallows the urgency.

How does the skill identify winning angles?

It groups variants by hypothesis (the angle each variant tests), computes weighted reply quality per variant, and flags the top-scoring as winners. Bottom 25 percent get flagged for kill.

Does it suggest new variants?

Implicitly. The narrative often says "the curiosity angle is dead, try a value-first angle next". Explicit variant drafting happens in unipile-campaign with this report as input.

How does the skill handle campaigns paused mid-week?

Paused campaigns are noted but not analyzed for performance. Resumed campaigns count from the resumption date.

Can the skill compare to prior weeks?

Yes. It reads the prior week's report from Notion and produces delta analysis (acceptance rate change, reply quality shift, new variants introduced).

What's "reply quality" measured by?

A Claude classification of each reply into positive intent, objection, not-now, not-interested, out-of-office, automated. Positive intent and meaningful objections count as quality; auto-replies and not-now don't.

Get the Campaign Intelligence skill

Clone the Yalc skill set, drop in your env, run from your next Claude Code session.

gh repo clone Othmane-Khadri/YALC-the-GTM-operating-system && cp -r YALC-the-GTM-operating-system/.claude/skills/campaign-intelligence ./.claude/skills/