Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add vibemarketer94/vibemarketer-skills --skill creative-angle-labgit clone --depth 1 https://github.com/vibemarketer94/vibemarketer-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/vibemarketer94/vibemarketer-skills/creative-angle-lab)<a href="https://agentmods.dev/skills/vibemarketer94/vibemarketer-skills/creative-angle-lab"><img src="https://agentmods.dev/badge/skills/vibemarketer94/vibemarketer-skills/creative-angle-lab/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/vibemarketer94/vibemarketer-skills/creative-angle-lab"><img src="https://agentmods.dev/badge/skills/vibemarketer94/vibemarketer-skills/creative-angle-lab.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00087 | $0.01357 |
| Opus 5 | $0.00044 | $0.00678 |
| Sonnet 5 | $0.00017 | $0.00271 |
| Haiku 4.5 | $0.00009 | $0.00136 |
Grade A, and why
creative-angle-lab scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Creative Angle Lab
Turn context, performance data, reviews, objections, and competitor observations into testable creative angles.
Before Ideation
- Read
.agents/vibemarketer-context.mdif it exists. - Pull in performance findings from
meta-performance-analystif available. - Ask for or inspect customer reviews, comments, support tickets, top-spending ads, losing ads, landing page copy, and competitor examples when useful.
- Separate proven facts from hypotheses.
Reference
Load only what is needed:
references/angle-frameworks.mdfor angle types and testing structures.references/gemini-creative-analysis.mdfor full image/video creative breakdowns using Gemini.
Scripts
Use these when the user wants executable LLM creative analysis:
scripts/build_creative_handoff.py: convert normalized Meta ad rows into a top-creative handoff for this skill, with optional Meta Ads CLI creative metadata and asset downloads.scripts/analyze_creative_gemini.py: send image or video assets to Gemini.scripts/analyze_creative_batch_gemini.py: analyze a top-creative handoff CSV with Gemini and synthesize the portfolio angle map.scripts/analyze_static_creative_openai.py: analyze static images with OpenAI Responses API.scripts/analyze_static_creative_claude.py: analyze static images with Claude Messages API.
Gemini remains the default for video. OpenAI and Claude are static-creative fallbacks unless the user asks otherwise.
Workflow
-
Extract raw material
- Customer pains
- Desired outcomes
- Objections
- Proof points
- Product mechanisms
- Competitor gaps
- Performance signals
- Top-spend creative assets and transcripts
-
Build angle territories
- Group ideas by customer motivation, not by minor wording.
- Avoid duplicates disguised as new angles.
-
Prioritize
- Score each angle on relevance, proof strength, novelty, production ease, and risk.
- Favor angles that can be tested with multiple hooks and creator types.
What ships with it
8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agents/openai.yaml 307 B
- references/angle-frameworks.md 2.1 KB
- references/gemini-creative-analysis.md 2.5 KB
- scripts/analyze_creative_batch_gemini.py 9.1 KB runs code
- scripts/analyze_creative_gemini.py 2.2 KB runs code
- scripts/analyze_static_creative_claude.py 2.7 KB runs code
- scripts/analyze_static_creative_openai.py 2.6 KB runs code
- scripts/build_creative_handoff.py 20 KB runs code
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 10d ago First seen · 162 lines · 87 tokens per session scan A fffbfd2ad073
creative-angle-lab is a skill published in the GitHub repository vibemarketer94/vibemarketer-skills (36 stars, last pushed 2mo ago), licensed MIT. It adds 87 tokens to every session and 1,357 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
visual-formats
A reference library of 45+ visual ad formats for Meta and paid social, each with a definition, funnel stage guidance, and medium (video/static/both). Use this whenever choosing how an ad should look and feel, building out a creative concept, writing a creative brief, or deciding which format best serves a messaging…
creative-mechanics
A library of creative mechanics — the structural patterns that define how an ad constructs meaning between its hook, visuals, and narrative. Use this whenever designing ad concepts, briefing creative, or trying to explain why a specific ad works beyond just its hook or format. Trigger when a user describes an ad they…
ad-proposal-orchestrator
A coordinator for advertising and marketing proposals. It turns a client brief into a checked deliverable such as a campaign plan, pitch deck, proposal, workflow, or review.
ad-creative-methods
A method guide for turning an advertising strategy, insight, or product idea into creative campaign directions and customer-facing stories.
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…