Install
$ agentstack add skill-infinite-labs-ai-infinite-skills-creative-brief ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Creative Brief
Turn the campaign strategy into a practical brief for ads, social creative, videos, images, or creator content.
Gather The Strategy
Identify:
- Audience and awareness level.
- Channel and placement.
- Offer or product.
- Desired action.
- Core promise.
- Proof or demonstration.
- Brand constraints.
- Production constraints: format, duration, dimensions, assets, budget, deadline.
If the strategy is unclear, create the minimum brief first instead of generating random concepts.
Inventory Source Material
List what can be shown:
- Product screens, product shots, packaging, app flows, demos.
- Customer proof, reviews, UGC, before/after, benchmark, quote.
- Founder or creator footage.
- Brand assets and mandatory disclaimers.
- Claims that need substantiation.
- Missing assets that would weaken execution.
Develop Concepts
Each concept must specify:
- Hook.
- Visual opening.
- Product or proof moment.
- Narrative beat.
- CTA.
- Format requirements.
- What to test against other concepts.
- Source assets needed.
- Claim/compliance risk.
Vary concepts by angle, not just wording:
- Pain scene.
- Before/after.
- Myth correction.
- Demo-first.
- Customer proof.
- Comparison.
- Founder POV.
- Unexpected use case.
Production Handoff
Give concrete asset direction:
- Frame or scene list.
- On-screen text.
- Voiceover or caption direction.
- Product shots or screenshots.
- Required claims and disclaimers.
- Variants for platform cropping.
- Editing or generation instructions.
- What must stay constant across variants.
Avoid vague prompts like "modern, clean, engaging." Name the subject, action, setting, composition, and proof moment.
Output
Creative brief:
Audience:
Channel:
Placement:
Promise:
Proof:
CTA:
Source inventory:
- Available:
- Missing:
- Claim risks:
Concepts:
1. [concept name]
Hook:
Opening visual:
Beats:
Asset requirements:
Test variable:
Claim/compliance note:
Production spec:
- Format:
- Length/dimensions:
- Visual style:
- Text overlays:
- Required assets:
Creative test matrix:
| Concept | Angle | Hypothesis | Success metric |
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: Infinite-Labs-AI
- Source: Infinite-Labs-AI/infinite-skills
- License: MIT
- Homepage: https://infinite.fast/agents/
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.