Agent skill

paid-media-design

Configure company branding or update report design, tokens, templates, and runtime design guidance.

activeSelf-containedInstructions only478 words

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

What it does when it runs

Configure company branding or update report design, tokens, templates, and runtime design guidance. Use during onboarding, when DESIGN.md changes, or when a user requests report styling or layout changes.

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: No step found in the source
Spends credits: No step found in the source
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-design

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-design"
mkdir -p ~/.claude/skills/paid-media-design
cp -R "/tmp/paid-media-agent/.agents/skills/paid-media-design/." ~/.claude/skills/paid-media-design/

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-design/SKILL.md, which is licensed APACHE-2.0 (repository). 478 words, 5 headings.

Maintain report design

Read first

DESIGN.md: company design decisions.
Theme tokens: renderer values.
Report template: HTML and print layout.
Runtime skill and component recipes: document-authoring guidance.
Customization: user setup and deployment paths.

Preserve the accepted appearance unless the user requests a visual change.

Set the company style

During onboarding, offer to apply the company's palette, fonts, and report name. Use supplied brand guidance or an approved example; ask only for missing choices. If none is available, keep the shipped defaults and explain that DESIGN.md can be updated later. Do not block setup.

For lasting changes, update workspace/skills/report-design/DESIGN.md first, then apply the same values to tokens.j2 in the same change. Encourage users asking for recurring report changes to record them there. A one-off document request does not change the company's defaults.

Company tokens are authoritative. Reuse existing semantic roles for colors, font families, spacing, and corners. Do not improvise a palette, import another product's styling, or add literal brand values to templates or component recipes. Preserve the company's requested fonts with valid local fallbacks. Add a logo only when requested and authorized.

Edit the owning layer

Change	Edit
Palette, fonts, spacing, corners, report name, optional logo	`DESIGN.md` and `tokens.j2`
Layout, responsive behavior, print pagination	`report.html.j2`; update design rules if they change
Guidance for custom documents	Runtime `SKILL.md` and `COMPONENTS.md`
Calculation or data semantics	The analysis/report code and its existing tests

Keep theme values out of Python. Use tokens for CSS and resolve the same values into SVG and PDF styles. Do not duplicate logos or palettes across skill folders. Custom document recipes must read the company tokens from DESIGN.md.

Keep figures, date windows, currencies, missing states, and attribution rules intact. Style changes must not change calculations, tool access, approvals, or delivery. Preserve unrelated work and keep source references and company data out of public examples.

Local coding-agent skills live in .agents/skills; .claude/skills links to that directory. Keep this workflow there. Only workspace/skills goes into the runtime skill bundle.

Verify

Run the relevant existing tests, starting with uv run pytest tests/unit/test_reads_and_surfaces.py tests/unit/test_docs_links.py -q.
Render a synthetic report. Inspect desktop, narrow-screen, and every PDF page. Verify that the company colors and fonts reach charts and print, signs and units remain visible, tables fit or scroll, and the reported values are unchanged.
Run the repository checks in AGENTS.md. For runtime skill changes, use a clean mda build and inspect .mda/__contexthub__/skills. Confirm .agents skills are not in that bundle.
Rebuild self-hosted images after renderer changes. Runtime skill mounts update separately; a Markdown edit alone does not update the built-in report template or a hosted deployment.

Show the result and state what was verified. Commit or deploy only when requested.

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
experiment-design by growthenginenowoslawski · 718
mcp-media-inbox-triage by zapier · 339
earned-media-outreach by shawnpang · 331
attachment-media-handling by louisblythe · 159
social-media-strategy by thatrebeccarae · 147
johnny-suede-design by JasonColapietro · 124

Need help setting it up?

This page tells you what paid-media-design 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.