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 precise-video-descriptiongit 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/precise-video-description)<a href="https://agentmods.dev/skills/calesthio/generative-media-skills/precise-video-description"><img src="https://agentmods.dev/badge/skills/calesthio/generative-media-skills/precise-video-description/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/precise-video-description"><img src="https://agentmods.dev/badge/skills/calesthio/generative-media-skills/precise-video-description.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 | $0.00078 | $0.02973 |
| Opus 5 | $0.00039 | $0.01486 |
| Sonnet 5 | $0.00016 | $0.00595 |
| Haiku 4.5 | $0.00008 | $0.00297 |
Grade A, and why
precise-video-description 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 — 263 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Precise video description
Use this skill when an existing video must be represented faithfully in production language. The output should let another agent or reviewer reconstruct what is visibly present, where it is, how it changes, and how the camera records it without inventing intent or atmosphere.
This skill describes observed media. It does not direct a future shot, infer a filmmaker's psychology, write accessibility captions, or execute a provider API.
Evidence stance
- Observed fact: directly visible in reviewed frames or playback.
- Measured fact: derived from file metadata or a reproducible tool, with method and tolerance.
- Inference: plausible but not visually established; label it or omit it.
- Production heuristic: a practical description rule, not a claim about the source.
The five-aspect structure below is informed by Lin et al.'s CHAI video-language specification and professional cinematography practice. Sources were checked 2026-07-14. CHAI's complete CameraBench-Pro primitive catalog was not fully available under a stable public package during authoring; do not reconstruct or copy an unavailable taxonomy from screenshots.
Define the description contract
Before watching in detail, record:
- asset ID, path/URL, checksum, rights basis, source, and analysis date;
- duration, dimensions, aspect, frame rate/timebase, audio presence, and shot boundaries;
- intended use: log, search, reference analysis, dataset, prompt handoff, edit notes, VFX handoff, or review;
- required detail and temporal precision;
- approved terminology/glossary and domain-specific definitions;
- whether overlays, subtitles, graphics, edits, and audio are in scope;
- uncertainty policy and reviewer/approval requirements;
- privacy, likeness, confidential-data, and publication restrictions.
Description depth depends on use. A search index may need concise shot-level fields; a training dataset or VFX handoff may need time-bounded state changes. Length is never a substitute for accuracy.
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 · 263 lines · 78 tokens per session scan A 69e087e4eae2
precise-video-description is a skill published in the GitHub repository calesthio/generative-media-skills (170 stars, last pushed 2mo ago), licensed MIT. It adds 78 tokens to every session and 2,973 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…