agentleFS
Othmane-KhadriOthmane-Khadri/YALC-the-GTM-operating-system/.claude/skills/track-campaigns/SKILL.md

track-campaigns

Skill298 starsChanged 6 months agoMITView on GitHub

Poll Unipile / Instantly for the status of running campaigns, advance sequence steps that are due, and sync results to Notion. Run this on a cadence (cron / launchd) or manually after staging a campaign. Use when the user says 'track campaigns', 'advance the sequences', 'check campaign progress', 'poll for replies', or 'sync replies to Notion'. Side-effecting — calls Unipile/Instantly, writes to SQLite + Notion.

  • Reads credentials

The file

Files
SKILL.md

Track Campaigns

I'll wrap campaign:track. Run the polling cycle, advance any sequence steps that are due, and surface the per-campaign status delta.

When This Skill Applies

  • "track campaigns"
  • "advance the sequences"
  • "check campaign progress"
  • "poll for replies"
  • "sync campaign status to Notion"

NOT this skill (use launch-linkedin-campaign instead):

  • "launch a campaign" — that's the create+stage flow.

NOT this skill (use answer-linkedin-comments instead):

  • "reply to LinkedIn comments" — that's per-thread engagement, not campaign-level tracking.

Workflow

Step 0 — No input needed (or ask for --campaign-id <id> if user wants a single campaign)

Step 1 — Shell out

cd ~/Desktop/gtm-os && set -a && source .env.local && set +a && \
  npx tsx src/cli/index.ts campaign:track

Optional: --campaign-id <id> to scope to one campaign.

Step 2 — Parse output

CLI emits per-campaign status delta: messages sent, replies detected, sequence steps advanced, errors.

Step 3 — Render

Step 4 — Offer follow-ups

"Want me to (a) personalize follow-ups for hot replies via personalize-message, (b) generate the weekly campaign report via campaign:report?"

Notes

  • Best run on cron: every 15 min during business hours.
  • Replies appear in Notion within ~2 min of posting (Unipile webhook latency).
  • The CLI is idempotent — running it twice in quick succession is safe (advances nothing if no time has elapsed).

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.