creative-iteration-playbook

31 stars 7 forks
28
D

Framework for briefing, testing, and scaling social creative variations.

Marketplace

Third-Party Agent Skill: Review the code before installing. Agent skills execute in your AI assistant's environment and can access your files. Learn more about security

Installation for Agentic Skill

View all platforms →
skilz install gtmagents/gtm-agents/creative-iteration-playbook
skilz install gtmagents/gtm-agents/creative-iteration-playbook --agent opencode
skilz install gtmagents/gtm-agents/creative-iteration-playbook --agent codex
skilz install gtmagents/gtm-agents/creative-iteration-playbook --agent gemini

First time? Install Skilz: pip install skilz

Works with 22+ AI coding assistants

Cursor, Aider, Copilot, Windsurf, Qwen, Kimi, and more...

View All Agents
Download Agent Skill ZIP

Extract and copy to ~/.claude/skills/ then restart Claude Desktop

1. Clone the repository:
git clone https://github.com/gtmagents/gtm-agents
2. Copy the agent skill directory:
cp -r gtm-agents/plugins/social-media-marketing/skills/creative-iteration-playbook ~/.claude/skills/

Need detailed installation help? Check our platform-specific guides:

Related Agentic Skills

Agentic Skill Details

Repository
gtm-agents
Stars
31
Forks
7
Type
Technical
Meta-Domain
development
Primary Domain
testing
Market Score
28

Agent Skill Grade

D
Score: 68/100 Click to see breakdown

Score Breakdown

Spec Compliance
11/15
PDA Architecture
18/30
Ease of Use
17/25
Writing Style
7/10
Utility
14/20
Modifiers: +1

Areas to Improve

  • Description needs trigger phrases
  • Missing Reference Files for Templates
  • Vague Skill Description Missing Triggers

Recommendations

  • Address 2 high-severity issues first
  • Add trigger phrases to description for discoverability
  • Add table of contents for files over 100 lines

Graded: 2026-01-24

Developer Feedback

I've been digging through some skill implementations, and I noticed your creative-iteration-playbook uses an interesting approach to structuring the workflow—the framing around iteration cycles really stood out, though I think there's room to tighten up how you're guiding developers through the actual decision points.

Links:

The TL;DR

You're at 68/100, which puts you in D territory. Based on Anthropic's agentic skill best practices, your strongest area is Spec Compliance (11/15)—the frontmatter is solid—but Progressive Disclosure Architecture (18/30) is where you're bleeding points. The core issue: you're cramming everything into one 55-line file when templates, workflows, and examples belong in separate reference files.

What's Working Well

  • Solid spec compliance – Your YAML frontmatter is valid, and the kebab-case naming is correct.
  • Clear cadence structure – The numbered workflow steps (intake → concept → script → edit → QA → publish) give developers something concrete to follow.
  • Consistent terminology – "Creative," "guardrails," "variants" stay consistent throughout, which is helpful for token efficiency.

The Big One: Missing Reference Files

Here's what's holding you back: you're listing templates and workflows inline instead of breaking them into separate reference files. Right now, section 3 just says:

  • Single-slide creative brief + checklist.
  • Experiment tracker w/ hypotheses, variants, outcomes, next steps.

But developers need to actually see what these look like. Create a references/ directory with:

  • references/creative-brief-template.md – Actual template with fields like [HOOK], [CTA], [PROOF], [EDITING NOTES]
  • `ref...

Report Security Issue

Found a security vulnerability in this agent skill?