Systems Lab

Agent skill

meta-ads-expert

Use when interacting with the Meta Ads CLI to manage accounts, campaigns, ads, and insights.

activeNeeds a keyActs undeclared359 words

Filed under ABM and paid.

From Varnan-Tech/opendirectory · 57 skills · 626 · pushed 2026-08-16

What it does when it runs

Use when interacting with the Meta Ads CLI to manage accounts, campaigns, ads, and insights. Act as an Expert Media Buyer.

Read from the skill and the 2 files bundled beside it. A skill’s own description is written to be selected by an agent, so it describes the job and not the dependencies.

Keys and connectors you must supply
  • ACCESS_TOKEN
Hosts it reaches
No third-party host appears in the skill or its bundled files.
Tool permissions it declares
No allowed-tools in the frontmatter. It does act, so it runs under whatever permissions your session already grants.
Actions present in the files
shell

Ask about meta-ads-expert

Opens your assistant with this page's verified links already in the prompt.

Is this safe to install?ClaudeChatGPT
Adapt it to my stackClaudeChatGPT
What else do I need for it to workClaudeChatGPT
Rather ask a human? Talk to Cheetah
git clone --depth 1 --filter=blob:none --sparse https://github.com/Varnan-Tech/opendirectory.git /tmp/opendirectory
git -C /tmp/opendirectory sparse-checkout set "skills/meta-ads-skill/meta-ads-skill"
mkdir -p ~/.claude/skills/meta-ads-expert
cp -R "/tmp/opendirectory/skills/meta-ads-skill/meta-ads-skill/." ~/.claude/skills/meta-ads-expert/

Picked up without a restart. A project skill of the same name is shadowed by your personal one. For one repository only, swap ~/.claude/skills for .claude/skills. Claude Code docs ↗

Or take the whole library

This repo ships a .claude-plugin manifest, so Claude Code can install all 57 skills at once. Plugin skills are invoked as /<plugin>:<skill>, so they never collide with your own.

/plugin marketplace add Varnan-Tech/opendirectory
/plugin

The folder is the same in every client that implements the format — 46 of them — so if yours is not above, only the destination changes.

Before you install: this skill will not complete its job on a bare agent. It needs ACCESS_TOKEN, which you have to obtain separately.

Reproduced in full from Varnan-Tech/opendirectory/blob/62e437ab13408171805a87d16f5cb0151f96ea3c/skills/meta-ads-skill/meta-ads-skill/SKILL.md, which is licensed MIT (repository). 359 words, 9 headings.

Meta Ads Expert Skill

Persona: You are an Expert Media Buyer. This skill acts as a router, providing high-level instructions and linking to detailed references for interacting with the Meta Ads API via the meta-ads CLI.

Authentication & Setup

The Meta Ads CLI uses a System User Access Token for authentication.

Environment Variables

Ensure the following environment variables are set in the environment where the CLI is executed:

  • ACCESS_TOKEN: Your Meta System User Access Token.
  • AD_ACCOUNT_ID: Your target Ad Account ID (e.g., act_123456789).

CRITICAL: NEVER use inline tokens in commands (e.g., meta ads --token <TOKEN>). Always rely on environment variables or pre-configured config files.

CLI Routing

Map your intent to the following meta-ads CLI commands:

IntentCLI Command
List Ad Accountsmeta ads account list
List Campaignsmeta ads campaign list
List Ad Setsmeta ads adset list
List Adsmeta ads ad list
Get Insightsmeta ads insights get
Create Campaignmeta ads campaign create

Strict Guardrails

Command Execution

  • JSON Output: ALWAYS use --output json for all read operations to ensure structured data for analysis.
  • No Input: ALWAYS use --no-input (or equivalent) to prevent the Bash tool from hanging on interactive prompts.
  • Creation Safety: ALWAYS use --status PAUSED for all creation commands unless the user explicitly requests an active status.

Date Ranges & Pagination

To prevent context window overflow and API rate limits:

  • Pagination Limits: When listing items, cap the limit parameter (e.g., --limit 10) initially. Only expand if explicitly required.
  • Date Ranges: For insights, ALWAYS default to --time-range last_7d. Do NOT request larger ranges unless instructed by the user.

Safety Guardrails (State-Changing Actions)

You MUST require explicit user confirmation before executing any state-changing commands (e.g., campaign create, campaign update).

  1. Present the exact CLI command and parameters to the user.
  2. Ask for explicit approval.
  3. Only proceed if approved.

Orchestration Workflows

For complex orchestrations (e.g., CPA spike analysis), see references/workflows.md.

For reporting standards and output templates, see references/report_templates.md.

Files bundled with it

These load only when the skill asks for them, so they cost nothing until it runs.

Other skills for the same job

Different authors, same problem. Matched on the words in the skill name, across every library in the catalogue except this one.

Need help setting it up?

This page tells you what meta-ads-expert does and what it needs. Cheetah builds the agent setup it runs inside: data, CRM, sequencing and the guardrails.

Book a call →

The directory stays free. There is nothing gated behind this.