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

campaign-dashboard

Skill298 starsChanged 6 months agoMITView on GitHub

This skill should be used when the user says 'campaign status', 'show me campaigns', 'visualize campaigns', 'what's the state of campaigns', 'campaign dashboard', 'open campaign view', 'how are outreach campaigns doing visually', 'show campaign pipeline', 'show me the leads for [campaign]', or any variant indicating they want a visual browser-based campaign dashboard.

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 3 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If the user mentioned a specific campaign name:

    line 49
  2. Distinctive:

    After opening the dashboard, tell the user:

    line 68
  3. Very specific:

    Default: 3847. If port is in use, pass --port <number> to the CLI command.

    line 82
  4. Distinctive:

    No external APIs needed — reads directly from local DB

    line 87

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Campaign Dashboard Skill

Opens the GTM-OS campaign visualization dashboard in the browser — Heyreach/Lemlist-style cards grid with per-lead timelines and variant comparison.

When This Skill Applies

  • "campaign status" / "campaign dashboard"
  • "show me campaigns" / "visualize campaigns"
  • "what's the state of campaigns"
  • "open campaign view" / "campaign pipeline"
  • "show me the leads for [campaign name]"
  • "how are outreach campaigns doing" (when visual context is implied)

NOT this skill (use campaign-intelligence instead):

  • "campaign report" / "weekly campaign report" → generates a Notion text report
  • "compare variants" / "which angle is winning" → text analysis

What This Skill Does

  1. Starts the GTM-OS server (if not already running)
  2. Opens the campaign dashboard at http://localhost:3847/campaigns
  3. Shows campaign cards with live metrics from SQLite
  4. Drill into any campaign for per-lead timeline + variant A/B comparison

What This Skill Does NOT

  • Generate Notion reports (that's campaign-intelligence)
  • Modify campaigns, leads, or variants
  • Send any LinkedIn messages

Workflow

Step 1: Start the GTM-OS Dashboard

npx tsx src/cli/index.ts campaign:dashboard

This starts the Hono.js server on port 3847 and opens /campaigns in the browser.

Step 2: If User Wants a Specific Campaign

If the user mentioned a specific campaign name:

  1. Query the campaign ID:
npx tsx -e "
import { db } from './src/lib/db/index.ts';
import { campaigns } from './src/lib/db/schema.ts';
const rows = await db.select({ id: campaigns.id, title: campaigns.title }).from(campaigns);
console.log(JSON.stringify(rows, null, 2));
"
  1. Open the specific campaign detail page:
open "http://localhost:3847/campaigns/{campaignId}"

Step 3: Report Back

After opening the dashboard, tell the user:

  • The URL that was opened
  • A quick summary of what they'll see (number of campaigns, active count, total leads)
  • Remind them they can filter by status and search leads in the UI

Dashboard Pages

URLWhat it shows
/campaignsAll campaigns as cards with metrics, funnel progress bars, status filters
/campaigns/:idSingle campaign: variant comparison cards + per-lead horizontal timeline

Port

Default: 3847. If port is in use, pass --port <number> to the CLI command.

Dependencies

  • SQLite database with campaign data (gtm-os.db)
  • No external APIs needed — reads directly from local DB

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.