agentleFS
victordelrosalvictordelrosal/chairman/.claude/skills/campaign/SKILL.md

campaign

Skill0 starsChanged 8 months agoMITView on GitHub

Campaign performance review. Pulls engagement and conversion data, assesses what is working, recommends keep/kill/adjust for each active campaign. Thursday routine. Octopus colors: Yellow (analytics) + Green (adjustment) + Purple (decision framing).

9 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 8 edited versions we read keep these.

  • 3

    Distinctive

    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. Very specific:

    Read departments/marketing/knowledge/ for active campaigns and historical data

    line 14
  2. Distinctive:

    Use real data from knowledge base.

    line 55
  3. Distinctive:

    If no marketing department exists, adapt to whatever campaigns the business runs.

    line 56
  4. Distinctive:

    If $ARGUMENTS provided, focus on that specific campaign.

    line 57

“Common” is measured: kept by at least 6 in 10 of the 8 edited versions of this file we could read. “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: Campaign Performance Review

Octopus Colors: Yellow (Researcher) + Green (Marketer) + Purple (Manager)

Process

  1. Read departments/marketing/knowledge/ for active campaigns and historical data
  2. Pull performance data (Yellow):
    • Engagement: views, clicks, shares, comments per channel
    • Conversion: leads generated, signups, purchases attributed
    • Cost: spend per channel, cost per acquisition
    • Comparison: this period vs. previous period
  3. Assess (Green):
    • What is working: which channels, content types, messages resonate
    • What is not: underperformers, declining trends, wasted spend
    • Adjustment ideas: new angles, channel shifts, audience changes
  4. Frame decisions (Purple):
    • For each campaign: keep, kill, or adjust
    • Support each recommendation with data
  5. Present to Chairman

Output Format

# Campaign Review: [Date]

## Active Campaigns

### [Campaign Name]
**Status:** [performing/underperforming/new]
**Metrics:** [key numbers]
**Trend:** [improving/stable/declining]
**Recommendation:** [KEEP / KILL / ADJUST]
**Rationale:** [one sentence with data]
**If adjusting:** [specific change proposed]

## Summary
- Performing: [count] campaigns
- Kill: [count] - saves [estimated amount/effort]
- Adjust: [count] - changes proposed above

## Approval
[ ] Approve all recommendations
[ ] Adjust (specify below)

Rules

  • Use real data from knowledge base. Do not invent metrics.
  • If no marketing department exists, adapt to whatever campaigns the business runs.
  • If $ARGUMENTS provided, focus on that specific campaign.
  • Save to .chairman/reports/campaign-YYYY-MM-DD.md

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.