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 bozhouDev/video-skills-toolkit --skill media-to-transcriptgit clone --depth 1 https://github.com/bozhouDev/video-skills-toolkitWrote 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/bozhoudev/video-skills-toolkit/media-to-transcript)<a href="https://agentmods.dev/skills/bozhoudev/video-skills-toolkit/media-to-transcript"><img src="https://agentmods.dev/badge/skills/bozhoudev/video-skills-toolkit/media-to-transcript/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/bozhoudev/video-skills-toolkit/media-to-transcript"><img src="https://agentmods.dev/badge/skills/bozhoudev/video-skills-toolkit/media-to-transcript.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 | $0.00154 | $0.01850 |
| Opus 5 | $0.00077 | $0.00925 |
| Sonnet 5 | $0.00031 | $0.00370 |
| Haiku 4.5 | $0.00015 | $0.00185 |
Grade A, and why
media-to-transcript scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Media To Transcript
Use this skill to turn audio or video into a final Markdown transcript. The only ASR backend for this skill is Volcengine recording-file recognition 2.0:
- submit endpoint:
https://openspeech.bytedance.com/api/v3/auc/bigmodel/submit - query endpoint:
https://openspeech.bytedance.com/api/v3/auc/bigmodel/query - resource id:
volc.seedasr.auc
Do not use another ASR backend for this skill.
Workflow
- Run the doctor if this is the first run, after environment changes, or after an error:
SKILL_DIR="<SKILL_ROOT>/media-to-transcript"
rtk python3 "$SKILL_DIR/scripts/media_to_transcript.py" --doctor
- Run the pipeline from the notes vault root:
SKILL_DIR="<SKILL_ROOT>/media-to-transcript"
rtk python3 "$SKILL_DIR/scripts/media_to_transcript.py" "<URL或本地媒体路径>" --topic "视频主题或关键词" --language zh-CN
The script automatically builds AUC context from available media metadata such as title, platform, author, duration, description, and short source URL. It keeps this ASR context under 500 Chinese characters. User-provided --topic, --context, and --context-file are also included in the same 500-character AUC context budget.
For downloaded or local media longer than 180 seconds, the script splits audio into 3-minute chunks, uploads each chunk, submits AUC tasks in parallel, and merges the returned utterances back onto the original timeline.
- Read the generated
correction-prompt.mdandraw-transcript.md. - Apply the AI correction rules in
references/correction-guidelines.md. - Save the corrected transcript to the
finalTranscriptTargetpath printed by the script, and show the full transcript to the user unless they explicitly only asked for a file.
CLI
SKILL_DIR="<SKILL_ROOT>/media-to-transcript"
# Video URL: download video, extract mp3, upload to R2, then run AUC ASR
rtk python3 "$SKILL_DIR/scripts/media_to_transcript.py" "https://www.bilibili.com/video/BVxxx" --topic "AI 编程工具评测"
# Local audio/video
rtk python3 "$SKILL_DIR/scripts/media_to_transcript.py" "/path/to/audio.mp3" --media-kind audio --topic "访谈"
# Add context or terminology hints for ASR and correction
rtk python3 "$SKILL_DIR/scripts/media_to_transcript.py" video.mp4 \
--topic "Claude Code 和 Codex 使用经验" \
--context "技术词: Codex, Claude Code, MCP, HyperFrames, R2" \
--context-file "AI Wiki/raw/some-material.md"
# Enable Volcengine utterance emotion labels when explicitly useful
rtk python3 "$SKILL_DIR/scripts/media_to_transcript.py" video.mp4 --emotion --topic "访谈"
# Convert an existing AUC result JSON into raw transcript + correction prompt
rtk python3 "$SKILL_DIR/scripts/media_to_transcript.py" --from-asr-json asr/auc-result.json --title "视频标题"
What ships with it
5 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.
- 10d ago First seen · 141 lines · 154 tokens per session scan A 9e0fd289c86f
media-to-transcript is a skill published in the GitHub repository bozhouDev/video-skills-toolkit (139 stars, last pushed 1mo ago), licensed MIT. It adds 154 tokens to every session and 1,850 once invoked, about $0.0008 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
video-hyperframes
Hyperframes / Remotion-compatible continuous frame animation with autoplay support.
video-hyperframes
A web-based sequence of video frames designed for Hyperframes or Remotion, with each frame presenting one visual idea.
remocn
Build Remotion videos with remocn — copy-paste animation components and timeline-driven UI primitives from a shadcn registry. Use when composing a video or scene in a Remotion project, adding a single animation, transition, background, or UI-block sim, or reaching for a video-ready UI primitive (button, dialog…
minimax-cli
Nested swiss-knife reference for the MiniMax mmx CLI and the canonical MiniMax CLI procedure shipped with the TUI: install mmx-cli, discover the correct TUI-managed MiniMax preset/key slot without leaking secrets, match mainland vs international regions, and route image/video/music/TTS generation or one-shot shell…
videoagent-audio-studio
Tired of juggling multiple audio APIs? This skill gives you one-command access to TTS, music generation, sound effects, and voice cloning. Use when you want to generate any audio without managing multiple API keys.
multimodal-llm
Vision, audio, video generation, and multimodal LLM integration patterns. Use when processing images, transcribing audio, generating speech, generating AI video (Kling v3, Sora 2, Veo 3.1 std/lite/fast, Runway Gen-4.5 via gen4turbo), or building multimodal AI pipelines.