Agent skill

paid-media-onboarding

Install and configure Paid Media Agent, connect ad platforms, choose MDA or self-hosting, and diagnose setup without exposing credentials.

activeSelf-containedInstructions only266 words

Filed under ABM and paid and Onboarding, retention and expansion.

From langchain-ai/paid-media-agent · 8 skill entries · 61 · pushed 2026-09-14

What it does when it runs

Install and configure Paid Media Agent, connect ad platforms, choose MDA or self-hosting, and diagnose setup without exposing credentials.

Automated analysis of the skill and the 0 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: None found.
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 only issues instructions, so there is nothing to bound.
Actions present in the files: None. Instructions only.

Our read

Computed from the artifact. Nothing here has been run, so none of it is a claim about how well the skill works — only about what it is and what it needs.

Maintenanceactive

Pushed within the last 30 days, with commits in the last 90.

CouplingSelf-contained

Nothing outside the agent is required.

Blast radiusInstructions only

No shell, no file writes, no network calls in the skill or its bundled files.

What it does to your systemsUnreviewed

The reading was not confident enough, or not yet confirmed, to publish.

Sends messages: No step found in the source
Writes records: Unreviewed
Spends credits: Unreviewed
Needs credentials: No key or connector found by pattern match

Read from source, not tested by running. Machine-read from SKILL.md at commit 0cc8109 with jev-1.13.0; labels that write, send or spend were also checked against the cited line by a second reviewer. How this is read

Substancebrief

Under 600 words, no bundled reference files.

LicenceAPACHE-2.0

Permits redistribution with attribution, per the repository.

Ask about paid-media-onboarding

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

Is this safe to install?Claude ChatGPT

Adapt it to my stackClaude ChatGPT

What else do I need for it to workClaude ChatGPT

Rather ask a human? Talk to Cheetah

Install it

View source on GitHub ↗

git clone --depth 1 --filter=blob:none --sparse https://github.com/langchain-ai/paid-media-agent.git /tmp/paid-media-agent
git -C /tmp/paid-media-agent sparse-checkout set ".agents/skills/paid-media-onboarding"
mkdir -p ~/.claude/skills/paid-media-onboarding
cp -R "/tmp/paid-media-agent/.agents/skills/paid-media-onboarding/." ~/.claude/skills/paid-media-onboarding/

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 ↗

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.

The skill

Source on GitHub ↗

Reproduced in full from langchain-ai/paid-media-agent/blob/0cc8109a1984377a573ed8d202b3b054db4d7b90/.agents/skills/paid-media-onboarding/SKILL.md, which is licensed APACHE-2.0 (repository). 266 words, 1 heading.

Set up Paid Media Agent

Read README.md, install with uv sync, then run uv run paid-media-agent demo --with-proposal to verify the fixture path without credentials.
Configure the model and its key through uv run paid-media-agent setup or uv run paid-media-agent config set. Use provider:model; LangSmith Gateway is optional. Run uv run paid-media-agent doctor and resolve missing dependencies or configuration.
Connect any supported Pipeboard accounts; X and OpenAI Ads use direct credentials. Use accounts discover and accounts add to select aliases. Check connections before relying on live data. Keep secrets and provider account IDs out of chat.
Follow the paid-media-org-onboarding skill to write business context and custom runtime skills locally. The setup console configures connections and deployment, not business context. Offer company report styling through paid-media-design. Record lasting brand choices in workspace/skills/report-design/DESIGN.md and apply the matching renderer tokens. Use the shipped defaults when no company style is supplied.
Explain the deployment options in OPERATIONS.md. MDA manages the runtime, sandbox, and Slack; self-hosting uses Docker, Postgres, and an optional Slack app. Review the chosen settings, then deploy only when the user requests it. MDA includes the declared sandbox setup recipe. Inspect source files before deployment: MDA archives ordinary project files even if Git ignores them. Keep sensitive source briefs outside the deploy directory.
Verify the resulting deployment and provide its URL. A local preflight alone does not prove a deployed agent works. Keep provider writes disabled unless the operator completes docs/operations/live-write-runbook.md.

Use customization for workspace context, runtime skills, memory, and optional warehouse connections. Report missing configuration by name without its value.

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.

paid-media-ops by shalintripathi · 14
paid-media-audit by sidchaudhary · 1
onboarding by coreyhaines31 · 51,063
icp-onboarding by growthenginenowoslawski · 718
onboarding-cro by OpenClaudia · 697
mcp-media-inbox-triage by zapier · 339
earned-media-outreach by shawnpang · 331
onboarding-flow by shawnpang · 331

Need help setting it up?

This page tells you what paid-media-onboarding 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.