ads-create
Use when the user asks to create a campaign, campaign brief, ad concepts, ad copy, campaign strategy, ad messaging, creative brief, or generate concepts.
Skill by ruca-radio
Chalk Labs
Need help deploying ads-create?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/ruca-radio-ads-create
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: documents, design, writing, marketing
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/ads-create
What's inside
- Skill name
ads-create- Description
- Use when the user asks to create a campaign, campaign brief, ad concepts, ad copy, campaign strategy, ad messaging, creative brief, or generate concepts. Produces structured campaign concepts, messaging pillars, and platform-specific copy decks from a brand profile; outputs a campaign-brief markdown file.
- License
- MIT
- Instructions
- 126 lines in SKILL.md · view on GitHub
Files (3)
- SKILL.md
- brief-format.md · references/
- copy-frameworks.md · references/
SKILL.md (first lines)
# Ads Create: Campaign Concept & Copy Brief Generator Generates structured campaign concepts and platform-specific copy from your brand profile and optional audit data. Outputs campaign-brief.md — the handoff artifact for any downstream asset-generation step. Listen to the brand voice before typing; every headline and CTA must carry emotional resonance. Create the deliverable — do not hedge concepts so heavily that the next person has to do the work. Spec compliance without emotional pull is a fail. ## Process ### Step 1: Check for Brand Profile Look for brand-profile.json in the current directory. - **Found**: Load and proceed. - **Not found**: Ask the user — run a brand-DNA extraction step first if one is available in your suite, or describe the brand manually and build a basic profile from the description. If the user chooses manual, collect: - Brand name and website - Primary color (or "unsure") - 3 words that describe the brand voice - Target audience (age, role, key pain point) - Main product/service offering ### Step 2: Check for Audit Results Look for ADS-AUDIT-REPORT.md or any *-audit-results.md in the current directory. - **Found**: Read them. Note the top 3 weaknesses (creative fatigue, tracking gaps, wasted spend) to address in concepts. - **Not found**: Continue without. Note in the brief: "No audit data found; concepts are generalized. Run an ads audit for weakness-targeted concepts." ### Step 3: Collect Campaign Parameters If the user's request already specifies platforms or objective (e.g. flags like `--platforms meta google` or `--objective leads`), use those values and skip the corresponding questions below. Ask (combine into one message; omit anything already provided): 1. **Platforms**: Which ad platforms? (Meta · Google · LinkedIn · TikTok · YouTube · Microsoft · All) 2. **Objective**: Sales/Revenue · Leads/Demos · App Installs · Brand Awareness · Retargeting 3. **Offer or brief**: Any specific offer, promotion, or message to highlight? (optional) 4. **Number of concepts**: How many campaign concepts? (default: 3) ### Step 4: Select Copy Framework Read `references/copy-frameworks.md` and recommend a framework based on campaign goal + platform + audience temperature. Include the selected framework name in the brief for the copy-writer agent. ### Step 5: Spawn Creative Agents in Sequence Agents must run **sequentially**; the copy-writer reads the file the creative-strategist writes, so running them in parallel races on campaign-brief.md. This is a stage gate per `smartpowers:orchestrating-agent-swarms` — wait for each agent to fully complete before dispatching the next. **Step 5a: Spawn the creative-strategist.** It creates campaign-brief.md and writes the strategic sections: "Brand DNA Summary", "Campaign Concepts", "Image Generation Briefs", "Next Steps" (exact heading contract in `references/brief-format.md`). Additional instructions: - For e-commerce businesses, apply an e-commerce creative playbook (Product Launch, Sale/Promotion, Seasonal, Retargeting, Brand Awareness) if one is available in your suite - Include banana domain mode recommendations in each Image Generation Brief (Product, Editorial, Cinema, UI/Web, or Portrait) **Step 5b: Spawn the copy-writer.** After the creative-strategist completes, the copy-writer reads the existing campaign-brief.md and appends the "Copy Deck" section with platform-specific headlines, primary text, and CTAs. Additional instructions: - Apply the selected framework structure from `references/copy-frameworks.md` to all ad copy - Generate 2 framework variants per platform: primary (recommended framework) + secondary (alternative for A/B testing) ### Step 6: Review and Present After both agents complete, confirm campaign-brief.md exists and is complete. Present a summary to the user: ``` ✓ campaign-brief.md generated Summary: Concepts: [N] campaign concepts created Platforms: [list] Copy deck: Headlines, primary text, and CTAs for each concept × platform Image briefs: [N] image generation briefs ready Next steps: 1. Review campaign-brief.md and adjust any messaging 2. Generate images from the briefs 3. Upload copy and assets to your ad platforms ``` ## Brief Format The exact heading structure of campaign-brief.md is a **parsing contract** — downstream agents depend on it. Full specification in `references/brief-format.md`. ## Quality Gates - **Minimum 3 concepts** (unless user requests fewer) - **Distinct angles**: no two concepts share the same primary message angle - **Platform fit**: concepts targeting TikTok must acknowledge vertical-only format and sound-on context - **Offer anchoring**: if the user provided a specific offer, at least 1 concept must lead with it - **Image briefs**: every concept must have at least one image brief per requested platform ## Meta Andromeda Optimization
From ruca-radio/smartpowers, MIT.
More from ruca-radio/smartpowers
- 0.524score
orchestrating-agent-swarms
ruca-radio
Use when planning work that needs multiple AI agents — designing agent roles, sizing the swarm to the task, and running agents in parallel or stages.
SkillBFreshness: BClaude Code +9 - 0.524score
saving-session-learnings
ruca-radio
Use when a work session or major task completes — evaluate performance, extract reusable knowledge, and persist it to memory stores and project folders.
SkillBFreshness: BClaude Code +9 - 0.524score
conducting-critical-review
ruca-radio
Use when reviewing an agent's development or complex code work — adversarial, question-driven review with authority to demand partial or full rework.
SkillBFreshness: BClaude Code +9 - 0.524score
solving-ctf-challenges
ruca-radio
Use when working CTF challenges, sanctioned security exercises, hack-the-box style labs, or authorized penetration-testing tasks — covers scope discipline…
SkillBFreshness: BClaude Code +9 - 0.523score
sensitive-rd-protocol
ruca-radio
Use when working on confidential, NDA-covered, or otherwise non-public R&D projects, data, or client engagements.
SkillBFreshness: BClaude Code +9 - 0.523score
core-principles
ruca-radio
Use when any skill cites shared principles.
SkillBFreshness: BClaude Code +9 - 0.523score
receiving-code-review
ruca-radio
Use when responding to feedback from a code review, whether from a subagent or human partner.
SkillBFreshness: BClaude Code +9 - 0.523score
dispatching-parallel-agents
ruca-radio
Use when you have multiple independent tasks that can be executed concurrently by subagents.
SkillBFreshness: BClaude Code +9 - 0.523score
discipline-template
ruca-radio
Use when writing a skill that enforces a rule agents skip under pressure.
SkillBFreshness: BClaude Code +9 - 0.518score
brainstorming
ruca-radio
Use before any creative work — creating features, building components, adding functionality, or modifying behavior.
SkillBFreshness: BClaude Code +9 - 0.504score
ads-attribution
ruca-radio
Use when the user asks about attribution audit, attribution model or windows, AdAttributionKit, AAK, SKAN, view-through attribution, GA4 attribution, Consent…
SkillBFreshness: BClaude Code +9 - 0.504score
ads-budget
ruca-radio
Use when the user asks about budget allocation, bidding strategy, ad spend split, ROAS target, media budget, scaling campaigns, or which campaigns to kill.
SkillBFreshness: BClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Aug 23, 2026 (2 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/ruca-radio/smartpowers
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from ruca-radio
- 0.524score
conducting-critical-review
ruca-radio
Use when reviewing an agent's development or complex code work — adversarial, question-driven review with authority to demand partial or full rework.
SkillBFreshness: BClaude Code +9 - 0.524score
orchestrating-agent-swarms
ruca-radio
Use when planning work that needs multiple AI agents — designing agent roles, sizing the swarm to the task, and running agents in parallel or stages.
SkillBFreshness: BClaude Code +9 - 0.524score
saving-session-learnings
ruca-radio
Use when a work session or major task completes — evaluate performance, extract reusable knowledge, and persist it to memory stores and project folders.
SkillBFreshness: BClaude Code +9 - 0.524score
solving-ctf-challenges
ruca-radio
Use when working CTF challenges, sanctioned security exercises, hack-the-box style labs, or authorized penetration-testing tasks — covers scope discipline…
SkillBFreshness: BClaude Code +9 - 0.523score
dispatching-parallel-agents
ruca-radio
Use when you have multiple independent tasks that can be executed concurrently by subagents.
SkillBFreshness: BClaude Code +9 - 0.523score
core-principles
ruca-radio
Use when any skill cites shared principles.
SkillBFreshness: BClaude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get ads-create running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
ads-create skill. Agent Mart. https://agentmart.dev/skills/ruca-radio-ads-create (last updated 2026-10-24)