bytedance/agentkit-samples is a collection of examples and tutorials for Volcengine AgentKit, an AI-agent development platform for building, deploying, and operating agent applications. Developers use the samples to learn agent creation, multi-agent collaboration, memory, retrieval, MCP integrations, media generation, customer service, and other workflows. The catalogue skills provide agent workflows based on these examples.
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 bytedance/agentkit-samples --skill byted-mediakit-videoeditgit clone --depth 1 https://github.com/bytedance/agentkit-samplesWrote 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/bytedance/agentkit-samples/byted-mediakit-videoedit)<a href="https://agentmods.dev/skills/bytedance/agentkit-samples/byted-mediakit-videoedit"><img src="https://agentmods.dev/badge/skills/bytedance/agentkit-samples/byted-mediakit-videoedit/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/bytedance/agentkit-samples/byted-mediakit-videoedit"><img src="https://agentmods.dev/badge/skills/bytedance/agentkit-samples/byted-mediakit-videoedit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 7 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 Prompt Injection · line 43 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 45 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 188 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Privilege Escalation · line 46 Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
- medium Privilege Escalation · line 53 Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
- medium Prompt Injection · line 81 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Excessive Agency · line 271 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00008 | $0.05927 |
| Opus 5 | $0.00004 | $0.02964 |
| Sonnet 5 | $0.00002 | $0.01185 |
| Haiku 4.5 | $0.00001 | $0.00593 |
Grade B, and why
byted-mediakit-videoedit scanned grade B 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 6d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
| ffmpeg | Any version | `ffmpeg -version` | macOS: `brew install ffmpeg` · Linux: `sudo apt install ffmpeg` · Windows: [ffmpeg.org](https://ffmpeg.org/download.html) | How it starts
The opening of the file, as written. The whole thing — 469 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Video Intelligent Editing
Overview
This Skill helps users understand video context by analyzing danmaku and subtitle content, automatically extracts and splices video clips based on editing requests, and uses FFmpeg to complete transition effects and final synthesis.
Input Specifications
- Video files (required, supports multiple): Local video file paths, supports formats like
.mp4,.flv,.mkv, etc. - Danmaku files (optional, one per video): XML format danmaku files (supports Bilibili format), corresponding to video files in order one-to-one
- Subtitle files (optional, one per video):
.srt/.ass/.jsonformat subtitle files, corresponding to video files in order one-to-one; leave empty for videos without subtitles
Note: Subtitles and danmaku are the only basis for understanding video content. If neither is provided for a video, its content cannot be understood, and only explicit time segment instructions from the user can be executed.
Workflow
Step 0: Dependency Verification
Before performing any operations, verify that the runtime environment meets the requirements.
Verification Commands:
python --version
ffmpeg -version 2>&1 | head -1
ffprobe -version 2>&1 | head -1
node --version
Acceptance Criteria and Fixing Guidelines:
| Dependency | Minimum Requirement | Verification Method | Installation Command When Not Met |
|---|---|---|---|
| Python | 3.9+ | python --version |
See instructions below |
| ffmpeg | Any version | ffmpeg -version |
macOS: brew install ffmpeg · Linux: sudo apt install ffmpeg · Windows: ffmpeg.org |
| ffprobe | Included with ffmpeg | ffprobe -version |
Installed with ffmpeg, no separate operation needed |
| Node.js | 18+ | node --version |
macOS: brew install node · or nodejs.org |
What ships with it
14 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.
- LICENSE 11 KB
- references/danmaku_format.md 1.8 KB
- scripts/cut_and_merge.py 17 KB runs code
- scripts/parse_media_info.py 16 KB runs code
- scripts/video_effects.py 8.4 KB runs code
- template/package.json 522 B
- template/render.mjs 6.4 KB runs code
- template/src/chapter-title.tsx 7.0 KB
- template/src/danmaku-burst.tsx 6.2 KB
- template/src/fancy-text.tsx 12 KB
- template/src/index.tsx 114 B
- template/src/lower-third.tsx 6.6 KB
- template/src/quote-callout.tsx 7.5 KB
- template/src/remotion-root.tsx 3.3 KB
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.
- 6d ago First seen · 469 lines · 6 tokens per session scan B f057c706bcae
byted-mediakit-videoedit is a skill published in the GitHub repository bytedance/agentkit-samples (450 stars, last pushed 5d ago), licensed Apache-2.0. It adds 8 tokens to every session and 5,927 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
image-generation
Use this skill when the user requests to generate, create, imagine, or visualize images including characters, scenes, products, or any visual content. Supports structured prompts and reference images for guided generation.
podcast-generation
Use this skill when the user requests to generate, create, or produce podcasts from text content. Converts written content into a two-host conversational podcast audio format with natural dialogue.
brandkit
Premium brand-kit image generation skill for creating high-end brand-guidelines boards, logo systems, identity decks, and visual-world presentations. Trained for minimalist, cinematic, editorial, dark-tech, luxury, cultural, security, gaming, developer-tool, and consumer-app brand systems. Optimized for intentional…
sn-image-base
Base-layer skill for the SenseNova-Skills project, providing low-level APIs for image generation, recognition (VLM), and text optimization (LLM). This skill does not preprocess inputs; it only calls backend services and returns results. This skill is not user-facing and is intended for upper-layer skills only.
video-still-animator
Turn a single still image (PNG/JPG) into a short MP4 with a slow Ken-Burns zoom and a silent audio track. Pure ffmpeg wrapper. Designed as the onfailure substitute for AI video-gen steps that get blocked by content moderation: when seedance refuses, this skill emits a valid replacement clip from the already-generated…
spotify-player
Terminal Spotify playback/search via spogo (preferred) or spotifyplayer. Use when the user asks to play music, search for a song, skip a track, pause playback, check what is currently playing, control Spotify, list audio devices, or manage a Spotify queue from the terminal.