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 calesthio/generative-media-skills --skill product-ad-productiongit clone --depth 1 https://github.com/calesthio/generative-media-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/calesthio/generative-media-skills/product-ad-production)<a href="https://agentmods.dev/skills/calesthio/generative-media-skills/product-ad-production"><img src="https://agentmods.dev/badge/skills/calesthio/generative-media-skills/product-ad-production/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/calesthio/generative-media-skills/product-ad-production"><img src="https://agentmods.dev/badge/skills/calesthio/generative-media-skills/product-ad-production.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Output Handling · line 465 Output size or generation rate is not bounded. Unbounded output enables denial-of-service through resource exhaustion, log flooding, or context-window stuffing.Fix: Set explicit limits on output length, generation count, and rate. Use max_tokens and truncation to prevent unbounded output.
- medium Excessive Agency · line 441 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00072 | $0.08762 |
| Opus 5 | $0.00036 | $0.04381 |
| Sonnet 5 | $0.00014 | $0.01752 |
| Haiku 4.5 | $0.00007 | $0.00876 |
Grade A, and why
product-ad-production 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 13d 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 — 501 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Product Ad Production
Produce an advertisement that makes the right person recognize a relevant situation, understand what the product changes, believe the proof, and know what to do next. Visual polish is not a substitute for product comprehension or claim support.
This skill is provider-neutral. Select image, video, capture, voice, music, editing, and composition tools only after the advertising problem is defined. Do not let a generation model's favorite visual language determine the concept.
Evidence language used here
- Documented fact means a requirement or principle stated by a regulator, standards body, or platform source.
- Research finding means an empirical result with a stated source and scope. It is evidence, not a guarantee for a new campaign.
- Practitioner heuristic means a production rule worth testing, not a universal truth.
Platform behavior and ad products change. Platform facts in this skill were verified 2026-07-09. Re-check the exact placement specification, policy, interface preview, and destination requirements immediately before export and trafficking.
Start with a decision-grade brief
Do not write a script from a slogan and a product URL. Diagnose the commercial problem first.
Minimum input record
Capture or infer each field, marking assumptions explicitly:
| Field | Required decision |
|---|---|
| Business outcome | Awareness, consideration, lead, trial, purchase, upsell, retention, or launch learning |
| Primary success measure | One decision metric; supporting and guardrail metrics are separate |
| Audience | Purchase situation and constraints, not demographics alone |
| Job to be done | Progress sought, present struggle, emotional/social stakes, and competing solutions |
| Awareness state | Unaware, problem-aware, solution-aware, product-aware, or returning customer |
| Product truth | What the product is, how it works, prerequisites, limitations, price/offer, and current availability |
| Proposition | One useful change the ad will make credible |
| Evidence | Approved substantiation, demonstrations, customer data, certifications, testimonials, and provenance |
| Objection | The most consequential reason a qualified viewer may not act |
| Placement | Platform, ad product, buying objective, duration, aspect ratio, UI overlays, and sound context |
| Destination | Exact landing page or store state; product, offer, naming, and price must agree with the ad |
| Brand system | Correct product/packaging, marks, type, colors, sonic assets, and prohibited treatments |
| Rights and policy | Talent, location, music, stock, creator, user content, AI/replica consent, category restrictions |
| Production constraints | Deadline, budget, available real product, UI build, languages, render and review path |
What ships with it
1 file 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.
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.
- 13d ago First seen · 501 lines · 72 tokens per session scan A e006630e9b67
product-ad-production is a skill published in the GitHub repository calesthio/generative-media-skills (170 stars, last pushed 2mo ago), licensed MIT. It adds 72 tokens to every session and 8,762 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
cliptalk-cover-director
Produces evidence-backed cover candidates and reviewable cover variants for a ClipTalk video. Use when the user asks for a cover, poster frame, thumbnail, or multiple cover directions; do not use for timeline editing or social-video reframing.
cliptalk-smart-reframe
Creates a subject-aware, time-varying crop track and a review-only social-format preview from an accepted ClipTalk cut. Use for automatic vertical, square, or portrait reframing; do not use for a fixed manual crop or before content editing is accepted.
cliptalk-content-extractor
Locates and assembles source passages matching a semantic request. Use for extracting explanations, topics, quotes, demonstrations, or other specifically described content.
cliptalk-interview-editor
Produces a coherent interview edit by combining speaker discovery, topic selection, dialogue context, cleanup, subtitles, and preview. Use for interviews, podcasts, testimonials, or question-and-answer recordings.
cliptalk-shortform-hook-director
Finds and assembles a reviewable short-form cut with a strong opening hook. Use for Shorts, Reels, social clips, talking-head cutdowns, or requests for a punchier opening.
cliptalk-social-reframe-exporter
Creates a review-only 9:16, 4:5, 1:1, or 16:9 version from an existing accepted ClipTalk cut, then checks the rendered preview. Use only when a cut already exists and the user asks to adapt it for Shorts, Reels, Douyin, Xiaohongshu, WeChat Channels, or square feeds; do not use when the user still needs content found…