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 ur-grue/autopunk-media-skills --skill asset-description-writergit clone --depth 1 https://github.com/ur-grue/autopunk-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/ur-grue/autopunk-media-skills/asset-description-writer)<a href="https://agentmods.dev/skills/ur-grue/autopunk-media-skills/asset-description-writer"><img src="https://agentmods.dev/badge/skills/ur-grue/autopunk-media-skills/asset-description-writer/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/ur-grue/autopunk-media-skills/asset-description-writer"><img src="https://agentmods.dev/badge/skills/ur-grue/autopunk-media-skills/asset-description-writer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00042 | $0.01794 |
| Opus 5 | $0.00021 | $0.00897 |
| Sonnet 5 | $0.00008 | $0.00359 |
| Haiku 4.5 | $0.00004 | $0.00179 |
Grade A, and why
asset-description-writer 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Asset Description Writer
What This Skill Does
Writes structured, searchable descriptions for digital assets — photos, videos, audio files, graphics, and documents — enabling accurate retrieval from a digital asset management (DAM) system or media archive.
When To Use This Skill
- You are ingesting a batch of new assets into a DAM system and need consistent, searchable descriptions for each
- You need to improve descriptions on existing assets that are poorly tagged or described, making them harder to find
- You are building a media archive and want every asset to follow a standardized description format from the start
- A production team needs to catalog footage, audio, or images so that editors and researchers can locate specific assets quickly
What You Need To Provide
Required: A description of the asset (what it shows, contains, or represents — if you cannot share the file, describe it in detail); the asset type (photo, video clip, audio file, graphic, document); the project or collection it belongs to.
Optional: The DAM system in use (Adobe Experience Manager, Brandfolder, Bynder, Canto, custom — affects field naming); the organization's metadata schema or field list; keywords or tags the asset should be associated with; technical specifications (resolution, duration, format, color space); licensing or usage rights information; date and location of creation.
How the Assistant Approaches This
-
Identifies the asset's content and purpose. Determines what the asset depicts or contains, who or what is featured, and the context in which it was created. For visual assets, describes the scene, composition, and notable elements. For audio, describes the content type (interview, ambient sound, music, voiceover) and key identifiers.
-
Writes a structured description optimized for search. The description leads with the most distinguishing feature of the asset — the element most likely to be searched for. Uses concrete, specific language (not "a nice landscape" but "aerial view of terraced rice paddies at sunset, central highlands"). Avoids subjective adjectives that do not aid search.
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.
- 8d ago First seen · 103 lines · 42 tokens per session scan A 40d36bbf65e8
asset-description-writer is a skill published in the GitHub repository ur-grue/autopunk-media-skills (32 stars, last pushed 12d ago), licensed MIT. It adds 42 tokens to every session and 1,794 once invoked, about $0.0002 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 2026-09-04.
Other skills, from other repositories
youtube-content
YouTube Data API — search, video details, channel info, transcripts.
studiomcphub-studio
Image to Retail in 90 seconds. 10-stage creative pipeline: background removal, palette extraction, resize, 6-product mockups, CMYK conversion, print-ready PDF, SVG vectorization, invisible watermarking, AI metadata enrichment, ESRGAN upscaling. Local DAM organizes all outputs. HTML preview gallery.
xiaoyuzhou-podcast-notes
A workflow that turns a public Xiaoyuzhou FM podcast episode into structured Markdown notes and a saved transcript. Xiaoyuzhou FM is a Chinese podcast platform.
SEO Metadata Generator
Generates optimized title tags, meta descriptions, Open Graph tags, and structured data for any web page.
c-research
Summarize web URLs, PDFs, YouTube videos, and podcasts using the summarize CLI. Instantly extract key points from any content type without manual reading. Useful for research, link digests, and media review.
tinyfish-integration
Integrate TinyFish web toolkit (search, fetch, browser automation) into Hermes Agent.