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 creatify-ai/ad-creative-evaluator --skill ad-creative-evaluatorgit clone --depth 1 https://github.com/creatify-ai/ad-creative-evaluatorWrote 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/creatify-ai/ad-creative-evaluator/ad-creative-evaluator)<a href="https://agentmods.dev/skills/creatify-ai/ad-creative-evaluator/ad-creative-evaluator"><img src="https://agentmods.dev/badge/skills/creatify-ai/ad-creative-evaluator/ad-creative-evaluator.svg" alt="Measured on agentmods" 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 | $0.00138 | $0.02582 |
| Opus 5 | $0.00069 | $0.01291 |
| Sonnet 5 | $0.00028 | $0.00516 |
| Haiku 4.5 | $0.00014 | $0.00258 |
Grade A, and why
ad-creative-evaluator 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 8d 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 — 219 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ad Creative Evaluator
Score any video ad with an AI expert panel. Get structured feedback across 8 dimensions with actionable improvement recommendations.
How It Works
- Input: Provide a video ad file or URL
- Extract: Key frames are pulled from the video for visual analysis
- Evaluate: Three expert personas score the ad independently
- Synthesize: Scores are combined with specific improvement recommendations
- Output: Structured evaluation report with scores, strengths, weaknesses, and next steps
Frame Extraction
Use the extract_video.py script to pull key frames from a video for analysis:
python scripts/extract_video.py input_video.mp4 --output-dir frames/ --num-frames 8
This extracts evenly-spaced frames including the first frame (hook), middle frames (body), and last frame (CTA).
Evaluation Personas
Each ad is reviewed by three expert perspectives:
1. Performance Marketer
Focus: Will this ad convert? Does the hook stop the scroll? Is the CTA compelling?
- Evaluates: Hook rate potential, CTA clarity, audience targeting precision
- Looks for: Direct response best practices, urgency triggers, benefit-driven messaging
- Red flags: Unclear value proposition, weak CTA, no social proof
2. Creative Director
Focus: Is this well-crafted? Does the visual storytelling work? Is the brand represented well?
- Evaluates: Visual quality, pacing, narrative structure, brand consistency
- Looks for: Professional production, creative differentiation, emotional resonance
- Red flags: Amateur visuals, poor pacing, off-brand elements, derivative concepts
3. Target Consumer
Focus: Would I actually watch this? Does it feel authentic? Would I click?
- Evaluates: Relatability, authenticity, interest level, trust
- Looks for: Content that doesn't feel like an ad, genuine value, relatable scenarios
- Red flags: Too salesy, fake/inauthentic feel, irrelevant to their life, annoying
Evaluation Rubric
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.
- 8d ago First seen · 219 lines · 138 tokens per session scan A b0510c4d692a
ad-creative-evaluator is a skill published in the GitHub repository creatify-ai/ad-creative-evaluator (31 stars, last pushed 6mo ago), licensed MIT. It adds 138 tokens to every session and 2,582 once invoked, about $0.0007 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
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…
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.
chengfeng-check-updates
An environment manager for a video-editing system. It checks whether its skills and runtime—the software needed to run them—are installed and compatible.