kai-ad-campaign SKILL.md skillA
kai-ad-campaign from cgallic/kai-cmo-harness is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add cgallic/kai-cmo-harness/kai-ad-campaign@git:20260719.f6c24daPins git:20260719.f6c24da in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- cgallic/kai-cmo-harness
- Path
harness/skills/kai-ad-campaign/SKILL.md- Versions recorded
- 5
- Latest version
- git:20260719.f6c24da, committed Jul 19, 2026
- First version recorded
- May 5, 2026
- Size
- 17,408 bytes
- Repository stars
- 60
- License
- a license file GitHub does not identify
Plan, evaluate, and produce paid ad campaigns across platforms (Meta, Google, LinkedIn, TikTok, Microsoft, Pinterest, Snapchat, Amazon, X). Evaluate existing ads, map funnel stages (TOF/MOF/BOF), produce ad variants per platform with policy compliance, output ready-to-upload copy. Use when "ad campaign", "create ads", "run ads for", "paid campaign", "media plan", "launch ads", "Meta campaign", "Google Ads campaign", "multi-platform ads", "evaluate my ads", "how are my ads doing…
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
Plan, evaluate, and batch-produce ad campaigns across platforms and funnel stages. Every ad passes platform policy compliance + quality gates. ## Mode Detection Before loading product context, determine the mode: - **Evaluation mode** — user says "evaluate", "analyze", "audit", "how are my ads doing", "ad performance", "review my ads" - **Creation mode** — user says "create", "launch", "build", "new campaign", "run ads" - **Evaluate + Create** — user wants both (evaluation first, then create/fix based on findings) Evaluation mode does NOT require `MARKETING.md`. Creation mode does. --- ## Phase E: Ad Evaluation (Evaluation Mode Only) Skip this phase entirely if the user only wants to create new ads. Evaluation mode is read-only. Do not create, pause, activate, change bids, change budgets, upload assets, add keywords, or mutate targeting while evaluating performance. ### E.1 Pull Active Campaigns Load the Meta API reference: `harness/references/meta-ads-api-reference.md` 1. Extract credentials from `.env.local` using grep (never `source`): ```bash META_TOKEN=$(grep '^META_ACCESS_TOKEN=' .env.local | cut -d= -f2-) …
Read the whole file at its exact version.
How to install
mdr add cgallic/kai-cmo-harness/kai-ad-campaign@sha256:ad73e17688bf948aThe line at the top of this page pins the label git:20260719.f6c24da, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_quvktb6ymfd2zgla)
4 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, between May 5, 2026 and Jul 19, 2026, about one every 19 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260719.f6c24da latest | 2026-07-19 | f6c24da | 17,408 B | A | view · diff |
| git:20260707.40eb9b3 | 2026-07-07 | 40eb9b3 | 16,867 B | A | view · diff |
| git:20260619.1140be9 | 2026-06-19 | 1140be9 | 16,882 B | A | view · diff |
| git:20260516.8df127f | 2026-05-16 | 8df127f | 15,779 B | A | view · diff |
| git:20260505.9924f62 | 2026-05-05 | 9924f62 | 14,000 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (17408 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
cgallic/kai-cmo-harness · 60 stars · license a license file GitHub does not identify · pushed 2026-11-01 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_quvktb6ymfd2zgla GET https://markdownregistry.com/api/v1/resolve?ref=cgallic/kai-cmo-harness/kai-ad-campaign GET https://markdownregistry.com/api/v1/blob/ad73e17688bf948ac4bef2e4d18ecd8dc0f978130d0d6bb1ea049886985ba23a
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.
More from cgallic/kai-cmo-harness
Every file in cgallic/kai-cmo-harness