video-to-skill

video-to-skill is a skill for Claude Code, Codex from brenoepics/video-to-skill. It costs 102 tokens per session (3,470 once invoked), scanned D, original, MIT.

A workflow that turns a local video or online video into structured, evidence-based instructions and, when appropriate, an installable agent skill. It can also produce an analysis report without creating a skill.

In plain words
What is it for?
It is for extracting transcripts and key frames, studying procedures shown in videos, creating skills from them, or updating an existing generated skill.
Why use it?
It helps convert demonstrations into reusable instructions while keeping the video processing on the user's machine.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: reads .claude/ paths; mentions subagents; mentions Claude Code.

Good fit It is for extracting transcripts and key frames, studying procedures shown in videos, creating skills from them, or updating an existing generated skill.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/brenoepics/video-to-skill/video-to-skill
Install

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.

Any agent
npx skills add brenoepics/video-to-skill --skill video-to-skill
Clone the repo
git clone --depth 1 https://github.com/brenoepics/video-to-skill

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for video-to-skill

README.md
[![agentmods](https://agentmods.dev/badge/skills/brenoepics/video-to-skill/video-to-skill/github.svg)](https://agentmods.dev/skills/brenoepics/video-to-skill/video-to-skill)
Your own site
<a href="https://agentmods.dev/skills/brenoepics/video-to-skill/video-to-skill"><img src="https://agentmods.dev/badge/skills/brenoepics/video-to-skill/video-to-skill/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.

agentmods 80×15 button for video-to-skill

Your own site · 80×15
<a href="https://agentmods.dev/skills/brenoepics/video-to-skill/video-to-skill"><img src="https://agentmods.dev/badge/skills/brenoepics/video-to-skill/video-to-skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 102 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,470 The whole file, excluding the scripts and references it only reads on demand.
Security scan D 3 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00102 $0.03470
Opus 5 $0.00051 $0.01735
Sonnet 5 $0.00020 $0.00694
Haiku 4.5 $0.00010 $0.00347

Measured 11d ago against content hash 9f42b7387765, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade D, and why

video-to-skill scanned grade D with 3 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 11d 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.

Instruction-override phrasingmediumPrompt injection

Text telling the model to disregard its earlier instructions or safety rules is the shape of a prompt injection, whoever wrote it.

("ignore previous instructions", "run this to continue",

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

- Steps that download-and-execute remote code (`curl … | sh` and kin)

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- Steps that download-and-execute remote code (`curl … | sh` and kin)
SKILL.md · 274 lines

How it starts

The opening of the file, as written. The whole thing — 274 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Video to Skill

Turn a video into knowledge an agent can act on. A local Rust extractor (vts-extract) does the deterministic work — download, transcription, shot detection, keyframes — entirely on the user's machine. You do the intelligence: read the timeline, inspect frames selectively, and produce evidence-grounded output. The video never leaves the machine; only the frames you choose to read enter context.

Modes

  • generate (default): the skill's purpose. Analyze the video (steps 2-5), then compile, verify, and install a skill package (steps 6). Invoking this skill with just a video means generate. Exception: a non-procedural video (talk with no procedure, vlog) gets the analysis report plus an explanation of why no skill was generated — never fabricated steps.
  • analyze: report only — use when the user asks for an analysis, summary, or report rather than a skill.
  • update: fold a new video into an existing generated skill — see step 7 below.

1. Locate the extractor (requires vts-extract 0.2.4)

The binary is cached globally so every project that carries this skill shares one copy. The cache lives in the app data dir — the same dir the runtime tools use: $VTS_DATA_DIR if set, else the platform data dir joined with video-to-skill (macOS: ~/Library/Application Support/video-to-skill, Linux: ~/.local/share/video-to-skill).

Resolve the binary in this order, then confirm vts-extract --version reports 0.2.4 — a wrong-version binary is ignored (never deleted; versioned filenames let versions coexist), so move to the next candidate or refetch rather than proceeding:

  1. Global cache: <data-dir>/bin/vts-extract-0.2.4 (versioned filename).
  2. Dev clones only: target/release/vts-extract beside this file.
  3. Fetch the prebuilt binary (macOS arm64 primary) into the global cache:
    VTS_BIN="${VTS_DATA_DIR:-$HOME/Library/Application Support/video-to-skill}/bin"
    gh release download v0.2.4 -R brenoepics/video-to-skill -p "vts-extract-macos-arm64*" -D /tmp/vts-dl
    shasum -a 256 -c /tmp/vts-dl/vts-extract-macos-arm64.tar.gz.sha256
    mkdir -p "$VTS_BIN" && tar -xzf /tmp/vts-dl/vts-extract-macos-arm64.tar.gz -C "$VTS_BIN"
    mv "$VTS_BIN/vts-extract" "$VTS_BIN/vts-extract-0.2.4"
    
    (Other platforms: substitute macos-x86_64 / linux-x86_64, and on Linux use the ~/.local/share default above.) The checksum must verify before the binary is executed.
  4. Last resort, build from source: cargo build --release in this skill's directory (requires Rust + cmake); the result appears at candidate 2's path.

Read the full file on GitHub · 274 lines

Changes

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.

  1. 11d ago First seen · 274 lines · 102 tokens per session scan D 9f42b7387765

Subscribe to this mod's changes

video-to-skill is a skill published in the GitHub repository brenoepics/video-to-skill (5 stars, last pushed 2d ago), licensed MIT. It adds 102 tokens to every session and 3,470 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it D with 3 findings (instruction-override phrasing, downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

regex-explainer

Explains what a regular expression does in plain English, or builds one from a plain-English description. Use when a regex is unreadable at a glance, or when you know what you want to match but not the regex syntax for it.

codebygarv/Ai-skills · 53 tokens

interview-question-generator

Generates technical interview questions plus an evaluation rubric for a given role or skill area. Use when preparing to interview a candidate and need structured, fair questions rather than ad hoc ones.

codebygarv/Ai-skills · 41 tokens

mvhs-bell-schedule

Fetch and display the live MVHS (Mountain View High School) bell schedule for today or any given date, with the current period highlighted and a progress indicator. Use this skill whenever the user asks about the MVHS bell schedule, what period it is right now, whether there's school today, or what time any period…

alexey-max-fedorov/mvhs-bellschedule-skill · 120 tokens

video-to-guide

Transforms YouTube videos into full, structured written guides — every detail preserved, no summarizing. Use when the user wants to turn a video into a guide, study notes, learning material, or any written format that captures the full depth of the content. The skill fetches the transcript automatically and produces…

igordev96/video-to-guide · 195 tokens

cangjie-skill

A process for turning a book, course, podcast, interview, long video, or other long material into reusable instructions for an AI agent. It extracts methods and principles, checks them, and packages them as skills.

kangarooking/cangjie-skill · 143 tokens

reading-metaskill

A reading and learning guide based on building a regular reading habit, choosing books, and understanding difficult subjects through original works and explanation.

kangarooking/cangjie-skill · 139 tokens