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 topaz-video-enhancementgit 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/topaz-video-enhancement)<a href="https://agentmods.dev/skills/calesthio/generative-media-skills/topaz-video-enhancement"><img src="https://agentmods.dev/badge/skills/calesthio/generative-media-skills/topaz-video-enhancement/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/topaz-video-enhancement"><img src="https://agentmods.dev/badge/skills/calesthio/generative-media-skills/topaz-video-enhancement.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
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 →
- high Anti-Refusal · line 266 Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.Fix: Remove instructions that suppress warnings, disclaimers, or ethical commentary. Let the agent surface safety-relevant caveats to the user.
- medium Data Exfiltration · line 207 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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 | $0.00174 | $0.05996 |
| Opus 5 | $0.00087 | $0.02998 |
| Sonnet 5 | $0.00035 | $0.01199 |
| Haiku 4.5 | $0.00017 | $0.00600 |
Grade A, and why
topaz-video-enhancement 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 9d 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 — 378 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Topaz Labs video (and image) enhancement
Topaz Labs makes AI enhancement/restoration models delivered three ways: the
desktop apps (Topaz Video AI, Gigapixel, Photo AI), and the Topaz Platform
REST API (api.topazlabs.com) which exposes the same model families for
programmatic, batch, and pipeline use. This skill is about applying the models to
solve concrete footage problems and about driving the API inside an automated
pipeline. When a task is a one-off manual cleanup, the desktop app is usually faster;
when enhancement is a repeatable stage in a generate → enhance → deliver pipeline,
use the API.
Enhancement is a repair and finishing operation, not a creation operation. It cannot add information that was never plausibly there; it can only reconstruct, interpolate, or invent detail. Every model on this page trades some fidelity for some apparent quality, and the whole discipline is choosing the trade that matches the footage and the deliverable.
Verification note: model names, model codes/slugs, parameters, limits, and pricing below were verified against Topaz's developer documentation on 2026-07-10. These are volatile — Topaz ships new model versions frequently (the
-Nsuffix in a code is a version). Before hard-coding a code in a pipeline, confirm it against the liveAvailable Modelsreference / OpenAPI schema (developer.topazlabs.com/reference). Codes are used in APIfilters[].model; the desktop app shows friendly names.
When this skill applies (and when it does not)
Applies:
- Upscaling video to a higher resolution (SD→HD, HD→4K/8K).
- Cleaning AI-generated video that came out soft, low-res, flickery, or plastic.
- Restoring old/archival footage: film grain, compression, interlacing, low res.
- Denoising, sharpening, deblurring, deinterlacing, stabilizing.
- Frame-rate conversion and slow-motion (frame interpolation).
- SDR→HDR conversion, black-and-white colorization, foreground object removal.
- Enhancing stills (Gigapixel/Photo models via the Image API) as a secondary need.
- Designing the enhancement stage of a "generate low-res, then upscale" pipeline.
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.
- 9d ago First seen · 378 lines · 174 tokens per session scan A c6afaabd7e07
topaz-video-enhancement is a skill published in the GitHub repository calesthio/generative-media-skills (171 stars, last pushed 2mo ago), licensed MIT. It adds 174 tokens to every session and 5,996 once invoked, about $0.0009 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 2026-09-03.
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…