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 patrick-fu/awesome-skills --skill audio-transcriptiongit clone --depth 1 https://github.com/patrick-fu/awesome-skillsWrote 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/patrick-fu/awesome-skills/audio-transcription)<a href="https://agentmods.dev/skills/patrick-fu/awesome-skills/audio-transcription"><img src="https://agentmods.dev/badge/skills/patrick-fu/awesome-skills/audio-transcription/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/patrick-fu/awesome-skills/audio-transcription"><img src="https://agentmods.dev/badge/skills/patrick-fu/awesome-skills/audio-transcription.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 | $0.00052 | $0.00540 |
| Opus 5 | $0.00026 | $0.00270 |
| Sonnet 5 | $0.00010 | $0.00108 |
| Haiku 4.5 | $0.00005 | $0.00054 |
Grade A, and why
audio-transcription 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 5d 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.
What it actually says
Audio Transcription
默认用本 Skill 内置的 local-transcribe 运行 Qwen 与 MOSS，本地顺序执行、完全离线、分别保留结果。本地离线路径只支持 macOS Apple Silicon（arm64）。
路由
- 多个媒体按用户给出的顺序逐个完成；前一个命令退出后再开始下一个，不并发启动 Agent、进程或在线任务。
- 每个媒体先运行
scripts/local-transcribe plan "<media>" --json。 SETUP_REQUIRED：读取 setup.md。用户明确要求 setup 后再安装。 用户明确要求外置盘、持久化运行时或持久化转写目录时，先运行scripts/manage-runtime storage status --json；在其确认四个独立目录后，运行storage configure，再继续 setup。此配置只保存路径，不迁移既有数据，也不构成上传授权。- 普通转写：运行
scripts/local-transcribe "<media>" --json，再读取 manifest 指向的产物。 - 用户明确要求豆包、在线、云端或允许上传：读取 online-transcription.md。仅“双模型、并行、交叉验证”不构成上传授权。
- 需要核对多份结果：读取 transcript-review.md。
- CLI 给出的
next_actions无法解决失败时，读取 troubleshooting.md。
事实源
参数、默认值、副作用、输出协议、错误码和恢复动作以各脚本的 --help、help <topic> 与 --json 为准；不要从本文或 reference 猜测。
平台限制、在线上传和第三方许可证见 setup.md、online-transcription.md 与 NOTICE.md。
不要改写或删除输入文件。不要把完整逐字稿塞进回复；除非用户要求，返回模式、状态、产物路径和重要存疑点即可。
What ships with it
50 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.
- agents/openai.yaml 476 B
- evals/evals.json 3.4 KB
- NOTICE.md 1.7 KB
- references/doubao-asr-2.0-api.md 8.6 KB
- references/online-transcription.md 1.2 KB
- references/setup.md 1.8 KB
- references/transcript-review.md 869 B
- references/troubleshooting.md 1.1 KB
- runtime/models.lock.json 976 B
- runtime/requirements.in 213 B
- runtime/requirements.lock 117 KB
- scripts/audio_transcription/__init__.py 256 B runs code
- scripts/audio_transcription/cache.py 6.3 KB runs code
- scripts/audio_transcription/config.py 11 KB runs code
- scripts/audio_transcription/errors.py 981 B runs code
- scripts/audio_transcription/media.py 5.5 KB runs code
- scripts/audio_transcription/pipeline.py 18 KB runs code
- scripts/help/cache.txt 776 B
- scripts/help/doctor.txt 509 B
- scripts/help/errors.txt 1.2 KB
- scripts/help/examples.txt 735 B
- scripts/help/local-main.txt 1.9 KB
- scripts/help/online-main.txt 1.6 KB
- scripts/help/outputs.txt 1.2 KB
- scripts/help/plan.txt 1.1 KB
- scripts/help/privacy.txt 939 B
- scripts/help/profiles.txt 804 B
- scripts/help/runtime-cleanup.txt 619 B
- scripts/help/runtime-doctor.txt 542 B
- scripts/help/runtime-inspect.txt 494 B
- scripts/help/runtime-install-cli.txt 713 B
- scripts/help/runtime-main.txt 941 B
- scripts/help/runtime-setup.txt 928 B
- scripts/help/runtime-storage.txt 888 B
- scripts/help/transcribe.txt 2.1 KB
- scripts/local_transcribe.py 7.1 KB runs code
- scripts/local-transcribe 2.1 KB
- scripts/manage-runtime 1.6 KB
- scripts/moss_runner.py 1.6 KB runs code
- scripts/online_transcribe.py 11 KB runs code
- scripts/online-transcribe 560 B
- scripts/qwen_runner.py 1.8 KB runs code
- scripts/runtime_manager.py 25 KB runs code
- tests/test_cache.py 2.4 KB runs code
- tests/test_help_contract.py 6.4 KB runs code
- tests/test_media.py 968 B runs code
- tests/test_online.py 758 B runs code
- tests/test_pipeline.py 8.7 KB runs code
- tests/test_runtime_manager.py 5.5 KB runs code
- tests/test_storage_config.py 5.0 KB runs code
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.
- 5d ago Changed · +3 lines 43f4df688cd0
- 11d ago First seen · 31 lines · 52 tokens per session scan A 2330c4cd4207
audio-transcription is a skill published in the GitHub repository patrick-fu/awesome-skills (58 stars, last pushed 4d ago), licensed MIT. It adds 52 tokens to every session and 540 once invoked, about $0.0003 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
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
chengfeng-check-updates
An environment manager for a video-editing system. It checks whether its skills and runtime—the software needed to run them—are installed and compatible.
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.