Meta Ads Expert Agent Skill
Use when interacting with the Meta Ads CLI to manage accounts, campaigns, ads, and insights. Act as an Expert Media Buyer.
Install
one command, takes just this skill from the repositorynpx skills add https://github.com/Varnan-Tech/opendirectory --skill meta-ads-expertThe instruction itself
9 sections, as written by the authorMeta 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:
| Intent | CLI Command |
|---|---|
| List Ad Accounts | meta ads account list |
| List Campaigns | meta ads campaign list |
| List Ad Sets | meta ads adset list |
| List Ads | meta ads ad list |
| Get Insights | meta ads insights get |
| Create Campaign | meta ads campaign create |
Strict Guardrails
Command Execution
- JSON Output: ALWAYS use
--output jsonfor 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 PAUSEDfor 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).
- Present the exact CLI command and parameters to the user.
- Ask for explicit approval.
- 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.
Other skills for the same job
different authors, same section of the catalogue
Develop React Native, Flutter, or native mobile apps with modern architecture patterns. Masters cross-platform development, native integrations, offline sync, and app store optimization. Use PROACTIVELY for mobile features, cross-platform code, or app optimization.
Serves as a reviewer of the codebase with instructions on looking for Apple App Store optimizations or rejection reasons.
Track physical units and propagate measurement uncertainty in scientific calculations using pint and uncertainties. Use for unit conversion and dimensional checking, GUM uncertainty budgets, Type A and Type B evaluation, coverage factors and expanded uncertainty, Monte Carlo propagation, significant-figure and plus-minus reporting, error propagation through curve fits, CODATA constants, auditing Python code for stripped units or broken uncertainty propagation, and order-of-magnitude plausibility checks using dimensionless groups (Reynolds, Peclet, Damkohler, Knudsen, Biot, Womersley), characteristic scales such as diffusion time or Debye length, and observed magnitude ranges. Trigger on "is this number physically reasonable", "sanity check these units", "what regime is this flow in", or a result that looks off by orders of magnitude.
Master AngularJS to Angular migration, including hybrid apps, component conversion, dependency injection changes, and routing migration.
Build, read, validate, modify SBML biological network models via the libSBML Python API. SBML Levels 1–3, reactions/kinetic laws, species, rules, FBC extension for flux balance, conversion. Interoperates with COBRApy, Tellurium/RoadRunner, COPASI. Use when programmatically constructing ODE or constraint-based metabolic/signaling models in SBML.
Use when you need to run a binary, trace execution, or observe runtime behavior. Runtime analysis via QEMU emulation, GDB debugging, and Frida hooking - syscall tracing (strace), breakpoints, memory inspection, function interception. Keywords - "run binary", "execute", "debug", "trace syscalls", "set breakpoint", "qemu", "gdb", "frida", "strace", "watch memory
Use when reverse engineering tools are missing, not working, or need configuration. Installation guides for radare2 (r2), Ghidra, GDB, QEMU, Frida, binutils, and cross-compilation toolchains. Keywords - "install radare2", "setup ghidra", "r2 not found", "qemu missing", "tool not installed", "configure gdb", "cross-compiler
Use when first encountering an unknown binary, ELF file, executable, or firmware blob. Fast fingerprinting via rabin2 - architecture detection (ARM, x86, MIPS), ABI identification, dependency mapping, string extraction. Keywords - "what is this binary", "identify architecture", "check file type", "rabin2", "file analysis", "quick scan
How to use it
Take varnan-tech/meta-ads-expert from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.