Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/novoads/agent-skillsnpx agentmods add skills/novoads/agent-skills/analyze-videoWrote 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/novoads/agent-skills/analyze-video)<a href="https://agentmods.dev/skills/novoads/agent-skills/analyze-video"><img src="https://agentmods.dev/badge/skills/novoads/agent-skills/analyze-video/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/novoads/agent-skills/analyze-video"><img src="https://agentmods.dev/badge/skills/novoads/agent-skills/analyze-video.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 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 Data Exfiltration · line 381 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.
- medium Data Exfiltration · line 381 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.
- medium Data Exfiltration · line 404 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 | $0.00138 | $0.06208 |
| Opus 5 | $0.00069 | $0.03104 |
| Sonnet 5 | $0.00028 | $0.01242 |
| Haiku 4.5 | $0.00014 | $0.00621 |
Grade A, and why
analyze-video scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -sS -X POST https://api.novoads.ai/v1/uploads \ How it starts
The opening of the file, as written. The whole thing — 511 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Analyze video → reusable prompting template
Someone found a video style they love. Your job is to deconstruct it into a reusable
prompting template — a formula they can plug any product, person or setting into and get
that same style back from seedance-2.0.
The output is not a single prompt. It is a formula file saved into
skills/novoads-api/prompting/prompt-library/, built the way
seedance-2-ugc.md is built: layers, variables,
option banks, rules, and a worked example, so the agent can generate unlimited prompts in
that style.
Nothing in steps 1 to 6 touches the API. Frame extraction, transcription and analysis are local work on the user's own file: no calls, no credits. Only step 7, the optional test render, spends anything, and it runs through the two gates in SKILL.md like every other generation.
There is a hosted alternative, and it is not the default. POST /v1/analyses reads an
uploaded ad into a structured breakdown (hook boundary, beat timeline, on-screen text,
casting, layer zones) in one synchronous call, at a flat fee per analysis that does not move
with length. Price it through POST /v1/estimates with {"kind":"analysis"} first. Two reasons it
is the fallback and not the front door here: the local path costs nothing and reads the whole
runtime, while /analyses defaults to the first 20 seconds (120 is the ceiling, and raising
it trades hook precision for coverage). Reach for it when ffmpeg is not installed, when the
user wants zone labels rather than prose, or when the frame read has already failed. Offer it
with the price attached and let the user choose; never substitute it silently for step 1.
The 15-second constraint is the whole design problem. seedance-2.0 and
seedance-2.0-mini take any integer 4 to 15 seconds, and the reference video is usually
30 to 60. Your template has to distil the style into what fits one 15-second clip, and say
how to recreate the longer arc across a series of clips.
What ships with it
3 files 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 · 511 lines · 138 tokens per session scan A d31c286690be
analyze-video is a skill published in the GitHub repository novoads/agent-skills (14 stars, last pushed 13d ago), licensed MIT. It adds 138 tokens to every session and 6,208 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
verse-to-prompt
Convert classical Chinese verses into image generation prompts — ink painting (default), stipple, or tech-noir variant. Use when visualizing Yilin, I Ching, Tang poetry, or classical Chinese text; for video motion prompts, see image-to-scene.
midjourney-prompting
Expert Midjourney prompt engineering skill. Use this skill when users need help crafting effective Midjourney prompts, converting natural language descriptions into optimized prompts, or want guidance on Midjourney parameters and techniques. Specializes in V7 best practices, the 7-Element Framework, and photography…
seedance-antislop
This skill should be used when a Seedance 2.0 prompt contains generic AI filler, hollow superlatives, vague cinematic language, bloated adjectives, weak verbs, or needs sharper production-specific wording.
seedance-examples-ja
This skill should be used when the user asks for Japanese Seedance 2.0 examples, Japanese prompt patterns, example rewrites, or safe versions of working Japanese video-generation prompts.
seedance-filter
This skill should be used when a Seedance 2.0 prompt is blocked or rejected, when moderation is a suspected cause of a problem, or when the user asks for a content-boundary review or safer alternative. Assess the actual request before offering a clarification.
seedance-prompt-short
This skill should be used when the user asks for a compact Seedance 2.0 prompt, short Chinese prompt, prompt compression, 30-100 word output, or removal of unnecessary prompt language.