evo-video-sampling

evo-video-sampling is a skill for Claude Code, Codex from OpenLAIR/OpenSkill. It costs 34 tokens per session (316 once invoked), scanned A, original, Apache-2.0.

A Python utility that reads an MP4 video from start to finish and selects frames at a target rate. It returns grayscale image arrays, their original frame numbers, and the video's frame rate.

In plain words
What is it for?
Use it to prepare video frames for computer-vision tasks such as motion or scene analysis, while keeping track of where each selected frame came from.
Why use it?
Sequential reading avoids incorrect frame positions that can occur when seeking inside compressed MP4 files. Grayscale output also reduces each frame to one brightness channel for analysis.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to prepare video frames for computer-vision tasks such as motion or scene analysis, while keeping track of where each selected frame came from.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/openlair/openskill/evo-video-sampling
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 OpenLAIR/OpenSkill --skill evo-video-sampling
Clone the repo
git clone --depth 1 https://github.com/OpenLAIR/OpenSkill

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 evo-video-sampling

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/openlair/openskill/evo-video-sampling"><img src="https://agentmods.dev/badge/skills/openlair/openskill/evo-video-sampling.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 316 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 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 $0.00034 $0.00316
Opus 5 $0.00017 $0.00158
Sonnet 5 $0.00007 $0.00063
Haiku 4.5 $0.00003 $0.00032

Measured today against content hash a320da0ae0a1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

evo-video-sampling 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 today.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/utils.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

tasks-evolved/dynamic-object-aware-egomotion/environment/skills/evo-video-sampling/SKILL.md · 35 lines

What it actually says

evo-video-sampling

Extracts frames from an MP4 video at a target FPS using reliable sequential reading (avoids unreliable CAP_PROP_POS_FRAMES seeking in compressed MP4s).

Key Function

  • sample_video_frames(video_path, target_fps=6) — Returns (sampled_frames, frame_indices, original_fps)
    • sampled_frames: list of grayscale np.uint8 2D arrays
    • frame_indices: list of original frame indices (0-based)
    • original_fps: the video's native FPS

Usage

import sys
sys.path.insert(0, '/app/environment/skills/evo-video-sampling/scripts')
from utils import sample_video_frames

frames, indices, fps = sample_video_frames('/root/input.mp4', target_fps=6)
print(f"Sampled {len(frames)} frames from video at {fps} FPS")

Implementation Details

  • Uses cv2.VideoCapture with sequential read() loop (no seeking)
  • Frame step = max(1, int(round(original_fps / target_fps)))
  • Converts BGR to grayscale immediately via cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
  • Fallback FPS of 30.0 if CAP_PROP_FPS returns <= 0
Files

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.

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. today First seen · 35 lines · 34 tokens per session scan A a320da0ae0a1

Subscribe to this mod's changes

evo-video-sampling is a skill published in the GitHub repository OpenLAIR/OpenSkill (88 stars, last pushed yesterday), licensed Apache-2.0. It adds 34 tokens to every session and 316 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 2026-09-11.

Related

Other skills, from other repositories

slidecraft

Convert PowerPoint (PPTX) files to HTML and back, analyze PPTX structure, generate slide decks from topics via LLM, pre-cache CDN assets, or launch the interactive review web UI. Use this when the user wants to work with PowerPoint presentations -- convert ppt to html, html to pptx, inspect pptx contents, or generate…

solid-shuwen/shuttleslide · 76 tokens

slidecraft-review

Launch an interactive web UI for reviewing, editing, and approving AI-generated slide presentations with human-in-the-loop feedback. Use when the user says review the slides, check the generated presentation, see slides before finalizing, or wants a visual review interface for slide generation.

solid-shuwen/shuttleslide · 57 tokens

dream

Deep creative exploration engine. Competing perspectives, stress-tested by a 4-persona council, scored by integrity. The approach that survives attack wins — not the one that sounds best.

ariaxhan/kernel-claude · 39 tokens

minimax-video

Generate and edit videos using MiniMax H3, the state-of-the-art open multimodal generation model. Supports text-to-video, image-to-video (first/last frame), reference-to-video with multimodal context (images, video clips, audio references), native stereo sound, up to 15 seconds at 2K resolution, in-context…

joeVenner/awesome-minimax-h3 · 226 tokens

minimax-music

Generate professional-quality music using the MiniMax CLOUD Music API (music-3.0). Supports full songs with vocals, purely instrumental tracks, AI lyrics writing, and cover generation from reference audio. Typical output is 2-3 minutes of finished stereo audio. Use when the user asks to create music, generate a song…

joeVenner/awesome-minimax-h3 · 180 tokens

minimax-speech

Generate speech, voiceovers, narration and audiobooks using the MiniMax CLOUD Text-to-Speech API (T2A v2), plus voice cloning and text-described voice design. Supports 332 preset voices across 40+ languages, precise inline pause control, word- and sentence-level timestamp output, emotion and prosody control…

joeVenner/awesome-minimax-h3 · 215 tokens