ads
An agent skill by coreyhaines31, from coreyhaines31/marketingskills. Tags: analytics, marketing, optimization, paid-media, search.
What it does
When the user wants help with paid advertising campaigns on Google Ads, Meta (Facebook/Instagram), LinkedIn, Twitter/X, or other ad platforms. Also use when the user mentions 'PPC,' 'paid media,' 'ROAS,' 'CPA,' 'ad campaign,' 'retargeting,' 'audience targeting,' 'Google Ads,' 'Facebook ads,' 'LinkedIn ads,' 'ad budget,' 'cost per click,' 'ad spend,' 'should I run ads,' 'ABM,' 'account-based marketing,' 'B2B ads,' 'lead quality,' 'negative keywords,' 'Performance Max,' 'thought leader ads,' or 'when should I kill an ad.' Use this for campaign strategy, audience targeting, bidding, and optimization. For bulk ad creative generation and iteration, see ad-creative. For landing page optimization, see cro.
Install
With the skills CLI, which installs into Claude Code, Codex, Cursor and other agents:
npx skills add coreyhaines31/marketingskills --skill adsOr copy the skill folder into Claude Code's skills directory by hand (~/.claude/skills for every project, or .claude/skills inside one):
git clone --depth 1 https://github.com/coreyhaines31/marketingskills
cp -r marketingskills/skills/ads ~/.claude/skills/adsSafety box score
Grade B, low risk: 18 of 100 risk points, rated 2026-10-05. The grade rates what the skill and its scripts can reach on the machine of whoever installs it, across eight categories from shell execution to secrets access. How the score works.
This skill is a paid-ads strategy and audit toolkit: it reads local product-marketing context, references several platform playbooks, and can help analyze competitor ads/reviews and live account performance. The main risks are moderate network/data movement in the creative-research workflow and high-impact recommendations that can change ad spend, targeting, and pauses on real accounts.
| Category | Level | Why |
|---|---|---|
| Code & shell execution | 0 (none) | No shipped shell scripts, binaries, or code-evaluation steps are included; the files are plain markdown playbooks and checklists. |
| Network access | 2 (moderate) | The shipped references explicitly use external connectors and delivery paths, e.g. `creative-research-automation.md` says "Chrome + Slack" and "Schedule recurring reports → Slack," and it also works from exact remote URLs. |
| Filesystem reach | 1 (low) | `SKILL.md` tells the agent to read local context files like `.agents/product-marketing.md`, `.claude/product-marketing.md`, or `product-marketing-context.md`, and the research workflow exports CSV/docs into workspace files. |
| Secrets & credentials | 0 (none) | There is no credential harvesting, keyfile access, token handling, or request for the user to paste secrets. |
| Privilege & persistence | 0 (none) | No sudo, service registration, global installs, shell startup edits, or OS-level changes are requested. |
| Instruction hijack surface | 0 (none) | The files mostly warn about prompt injection in fetched pages; they do not tell the agent to ignore higher-level instructions, hide behavior, or follow remote instructions. |
| Irreversible actions | 2 (moderate) | The playbooks cover live-account decisions like pausing ads, changing budgets, and scaling campaigns (for example `meta-decision-system.md` and `b2b-paid-playbook.md`), but `audit-guardrails.md` requires draft-first and explicit approval before applying changes. |
| Transparency | 0 (none) | All shipped files are readable markdown; there are no binaries, minified bundles, or decoded-at-runtime blobs. |
Before installing
- Check whether `.agents/product-marketing.md` / `.claude/product-marketing.md` exists and whether you want the skill to auto-read it.
- If you plan to use the creative-research workflow, review `references/creative-research-automation.md` for Chrome/Slack data flow before enabling it.
- Decide in advance who can approve live-account changes; treat all pause/scale/budget recommendations as drafts first.
- Confirm you have read-only exports or sandbox access for the first run if you do not want the skill touching production ad accounts immediately.
Rated 2026-10-05 by an automated review of 17 files from the skill's repository.
Source
- Repository
- coreyhaines31/marketingskills (all skills from this repository)
- Path
- skills/ads/SKILL.md
- Branch
- main
- Collection
- marketingskills
- Updated
- 2026-09-21
Related skills
- aso — When the user wants to audit or optimize an App Store or Google Play listing.
- ab-testing — When the user wants to plan, design, or implement an A/B test or experiment, or build a growth experimentation program.
- ai-seo — When the user wants to optimize content for AI search engines, get cited by LLMs, or appear in AI-generated answers.
- attribution — When the user wants to figure out which marketing actually drives conversions and revenue, choose or interpret an attribution model.
- competitors — When the user wants to create competitor comparison or alternative pages for SEO and sales enablement.
- cro — When the user wants to optimize, improve, or increase conversions on any marketing page or form — including homepage, landing pages, pricing pages.