agentleFS
athina-aiathina-ai/goose-skills/skills/marketing/plan-campaign-goal-chain/SKILL.md

plan-campaign-goal-chain

Skill1.3k starsChanged 23 days agoMITView on GitHub

Checks whether a stated goal is reachable on a given budget: fills an economics box with a source on every number, subtracts the baseline, works out the implied cost per customer against history or labelled base rates, and flags when the goal needs renegotiating. Use alone when you already have the goal (metric, number, date), budget, order value, margin and baseline; otherwise run plan-campaign.

1 other project uses a version of this.

Trending

Quiet since March.thin dataabout the whole repository

Dec 2025: 0 mentionsJan 2026: 0 mentionsFeb 2026: 0 mentionsMar 2026: 1 mentionApr 2026: 0 mentionsMay 2026: 0 mentionsJun 2026: 0 mentionsJul 2026: 0 mentionsAug 2026: 0 mentionsSep 2026: 0 mentionsOct 2026: 0 mentionsNov 2026: 0 mentions
Dec 2025Jun 2026Nov 2026
Mentions a month of the athina-ai/goose-skills repository that our weekly crawl found: only 1 in all, so this is a hint, not a trend. There is no adoption data for this file yet.

Most recently taken up by

Who's talking about athina-ai/goose-skills

The biggest 1 of 1 mention linking to the repository that our crawl found. Each line is their own headline.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 3 are distinctive, and 0 are 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.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Run conservative / expected / optimistic using the low / middle / high end of each assumption.

    line 23
  2. Distinctive:

    Check the forecast against stock (days of cover, inbound) or capacity (open slots).

    line 24
  3. Distinctive:

    If the expected scenario misses: write the renegotiation case (gap in numbers.

    line 25

≈ “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

Goal chain and economics (atom)

Load: ../plan-campaign/references/unit-economics.md, ../plan-campaign/references/company-types.md (the brand's type).

Inputs: the goal (metric, number, date) as the marketer stated it; budget; AOV / ARPA / first-job value; margin or contribution inputs; repeat behaviour if shown; baseline for the same period (marketer or past reports); conversion rates from the brand's history (learnings, past performance reads) or labelled base rates; stock or capacity.

Do — part 1 (step 2):

  1. Fill the economics box. Every line gets a source: own history · marketer · base rate (rule of thumb) · assumption. Unknown margin → a labelled assumption with "confirm margin" first in What we couldn't check (asked only when the plan turns on it).
  2. Baseline → incremental target (never credit the campaign for the baseline); implied CAC = budget ÷ incremental target vs history or labelled base rates; stock or capacity vs the goal. Pre-revenue: no allowable CAC — record the marketer's provisional cap. Do — part 2 (step 5, after the channels and split exist):
  3. Break the incremental target into per-leg targets with the chain that produces each (list × conversion; spend ÷ CPA; codes from creators), each with a "readable by" date.
  4. Run conservative / expected / optimistic using the low / middle / high end of each assumption.
  5. Check the forecast against stock (days of cover, inbound) or capacity (open slots).
  6. If the expected scenario misses: write the renegotiation case (gap in numbers; what more budget, more time, a smaller goal or a different goal metric each buys; one recommendation). Return it to the playbook to show the marketer before planning further.

Output: the plan's ### Goal chain, ### Economics, ### If the goal needs changing sections, and the assumptions list.

Never: invent the goal, a margin or a conversion rate and present it as the brand's; pick the renegotiation lever for the marketer.

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.