ads-plan — Claude Code skill: what it does, how to install
Walks an agent through a paid-media plan: objectives, channel choice, campaign architecture, budget, measurement and rollback terms. Meant for the stage before money hits the ad account.
npx skills add AgriciDaniel/claude-ads --skill ads-plan -a claude-codeWhat ads-plan does
The skill builds a paid-advertising plan end to end, from objective and unit economics to campaign structure, spend pacing and reporting. Eight ordered steps sit inside it, and the output is canonical JSON plus a readable plan for the team.
Step two pins down constraints, geography, regulated category and success criteria; the setup profile and business economics come in as optional input. For a channel outside the twelve-platform contract the skill loads ads/references/additional-platforms.md and returns a research lead unless there is current evidence on buying, eligibility, measurement and creative. Meta budgets and learning-phase expectations wait on the cold-start dimensions defined in skills/ads-meta/SKILL.md — feed it a cold or unknown dimension and you get measurement validation and staged reversible tests with confidence labels instead of forecasts.
A plan here is advisory. It reaches the account only through the launch or optimize mutation gates, so check who on your side is cleared to pass them.
What it helps with
- draft a media plan from an objective and a budget
- test whether a new channel fits buying and measurement
- split a rollout into phases with owners and dates
- write rollback conditions before testing starts
- document campaign and audience architecture in one file
Example prompts for the agent
- Write a paid media plan for a new product: objective, budget, channels, campaign architecture.
- Draft the Meta budget plan, but resolve the account, Pixel and conversion cold-start dimensions first.
- Lay out an experiment plan with creative hypotheses, staged tests and exit conditions.
How to install ads-plan
1Skills CLI (Vercel)
npx skills add AgriciDaniel/claude-ads --skill ads-plan -a claude-code2Manually: put the files in place
~/.claude/skills/ads-plan/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/ads-plan/
1Skills CLI (Vercel)
npx skills add AgriciDaniel/claude-ads --skill ads-plan -a codex2Manually: put the files in place
.agents/skills/ads-plan/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add AgriciDaniel/claude-ads --skill ads-plan -a cursor2Manually: put the files in place
.cursor/skills/ads-plan/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install AgriciDaniel/claude-ads ads-plan2Manually: put the files in place
.github/skills/ads-plan/SKILL.md1Skills CLI (Vercel)
npx skills add AgriciDaniel/claude-ads --skill ads-plan -a gemini-cli2Platform CLI
gemini skills install https://github.com/AgriciDaniel/claude-ads --path skills/ads-planManually: put the files in place
.devin/skills/ads-plan/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add AgriciDaniel/claude-ads --skill ads-plan -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
From the same set20
The whole set →Similar
Questions about ads-plan
How do I install ads-plan in Claude Code?
Run npx skills add AgriciDaniel/claude-ads --skill ads-plan -a claude-code. The skill lands at ~/.claude/skills/ads-plan/SKILL.md.
What does ads-plan do?
It runs an agent through eight steps of paid-media planning: objective, economics, channel roles, campaign architecture, audiences, budget, creative, measurement, experiments and reporting. Output is canonical JSON plus a human plan.
Why does the plan skip budget forecasts?
With cold or unknown account, Pixel or conversion history it refuses mature-account benchmarks. You get measurement validation, creative hypotheses and reversible tests marked with confidence labels instead.
Source text
SKILL.md · MIT
--- name: ads-plan description: "Create a professional paid-advertising strategy covering objectives, economics, platform selection, campaign architecture, audiences, budget, creative, measurement, experiments, governance, rollout, and reporting. Use for ad plan, media plan, PPC strategy, paid-social strategy, campaign architecture, advertising roadmap, or channel planning." --- # Paid Media Plan 1. Read the setup profile, business economics, evidence, current account state, and relevant industry template as optional input. 2. Define objective, customer, offer, conversion, value, constraints, geography, regulated category, time horizon, and success criteria. 3. Evaluate channel roles and exclusions from first principles; do not require every supported platform. For a channel outside the twelve-platform contract, load `ads/references/additional-platforms.md` (resolve it from the plugin root, the directory that holds `ads/` and `skills/`, or from the skills directory in a standalone install) and return a research lead unless its current buying, eligibility, measurement, and creative evidence is present. 4. Before proposing Meta budgets, learning-phase expectations, bidding, consolidation, or performance forecasts, collect the account, Pixel, and conversion cold-start dimensions per the contract in `skills/ads-meta/SKILL.md`. When any dimension is cold or `unknown`, plan for measurement validation, explicit creative hypotheses, staged reversible tests, and confidence labels; do not apply mature-account benchmarks to missing history. 5. Specify campaign architecture, audience strategy, creative system, budget and pacing, measurement, experiments, policy controls, and operating cadence. 6. Phase prerequisites before launch, learning, optimization, and scale. 7. Assign every action an owner, timing, dependency, guardrail, evidence, success measure, and rollback or exit condition. 8. Return canonical JSON and render the requested human plan. A plan is advisory. It becomes an account change only through launch or optimize mutation gates.
© AgriciDaniel · MIT · AgriciDaniel/claude-ads