Adspirer Skill Reference: 13 AI Ad Skills

Adspirer ships 13 skills — instruction files that teach an AI assistant how to run advertising campaigns properly. They follow the open Agent Skills format, so the same files work in Claude, ChatGPT, Codex, Cursor, Gemini CLI, and OpenClaw. You don’t invoke them by name. Describe what you want — “how are my Google Ads doing?”, “launch a TikTok campaign” — and your assistant loads the right skill.

​

How the skills fit together

Skills load on demand. Your assistant sees only each skill’s name and description until a task matches, then reads the full instructions. Two skills underpin everything:

• adspirer-agent sets the safety rules — campaigns are created paused, nothing spends without your explicit approval — and routes to the right skill.
• adspirer-mcp carries the tool-call contract: how to reach each platform’s tools, which account id each platform expects, and the budget units (Meta budgets are in cents, Google’s in dollars).

Everything else builds on those two. A workflow skill like “launch a campaign” delegates to the platform skill for that platform’s field rules, rather than duplicating them.

​

Quick reference

​

Foundational

​

Per platform

​

Cross-platform workflows

​

Product questions

​

Workspace (local assistants only)

adspirer-setup needs a filesystem, so it ships to Claude Code, Cursor, Codex, and Gemini CLI — not to the ChatGPT app.

---

​

What the skills guarantee

Every skill inherits the same safety contract from adspirer-agent:

• Read before write. The agent looks at what’s actually in the account before proposing a change.
• Verify after write. After creating or updating anything, it reads the object back and reports what exists — not what it asked for.
• Never invent a number. If a tool fails, the agent says so. It does not estimate metrics.
• Destructive means destructive. Deleting a creative or removing keywords is named as such, and confirmed, before it happens.

---

​

Using your assistant’s own features

The skills know what the app they’re running in can do, and offer it when it helps.

​

Showing work

In Claude, a scorecard, a set of ad-copy variants, or a campaign plan can be published as an artifact — a live page that updates as work continues, private to you by default. In ChatGPT, something you’ll revisit or send to a client can be a hosted Site. The agent defaults to invitation-only, because these pages carry your spend and conversion data.

​

Repeating work

Ask for a weekly review or a pacing check and the agent offers to schedule it, using whatever your assistant calls it: Every scheduled run calls Adspirer tools again, so it draws on your monthly tool-call quota exactly like a live conversation. The agent tells you what a cadence will cost before setting it up — weekly is the sensible default for a performance review. If your assistant has no scheduler, Adspirer’s own monitoring tools cover the same ground server-side: threshold alerts on ROAS, CPA and spend, and scheduled reports delivered by email.

---

​

Deeper reference material

Some skills carry references/ files that load only when the agent needs them — keeping the day-to-day context small:

---

​

Getting the skills

Source lives in github.com/amekala/ads-mcp under shared/skills/, and fans out to each client from there. See the Tool Catalog for the tools these skills drive, and Core Workflows for the step-by-step patterns.