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 wwwzhouhui/skills_collection --skill ip-talking-head-lecturegit clone --depth 1 https://github.com/wwwzhouhui/skills_collectionWrote 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/wwwzhouhui/skills_collection/ip-talking-head-lecture)<a href="https://agentmods.dev/skills/wwwzhouhui/skills_collection/ip-talking-head-lecture"><img src="https://agentmods.dev/badge/skills/wwwzhouhui/skills_collection/ip-talking-head-lecture/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/wwwzhouhui/skills_collection/ip-talking-head-lecture"><img src="https://agentmods.dev/badge/skills/wwwzhouhui/skills_collection/ip-talking-head-lecture.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00480 | $0.05507 |
| Opus 5.5 | $0.00192 | $0.02203 |
| Sonnet 5.5 | $0.00096 | $0.01101 |
| Haiku 4.5 | $0.00048 | $0.00551 |
Grade A, and why
ip-talking-head-lecture scanned grade A 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 14d 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
| `spawnSync ffprobe EBUSY` | 本机 Node 的**同步**进程调用不可用（本仓库已全部改成异步 `lib/tts/run.mjs`）。别在新代码里写 `execFileSync` | The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What ships with it
57 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.
- .env.example 2.6 KB
- .gitignore 100 B
- assets/avatar-mid.png 1463 KB
- assets/avatar-open.png 1464 KB
- assets/avatar.png 1875 KB
- assets/avatars/haibao/image.png 1875 KB
- assets/avatars/haibao/mouth-mid.png 1463 KB
- assets/avatars/haibao/mouth-open.png 1464 KB
- assets/avatars/human/image.png 1672 KB
- assets/avatars/human/mouth-mid.png 1764 KB
- assets/avatars/human/mouth-open.png 1772 KB
- bin/iph 9.2 KB
- config.json 5.8 KB
- episodes/2026-10-02 Meta Muse国内0门槛注册全攻略/script.json 10 KB
- episodes/2026-10-02 Meta Muse国内0门槛注册全攻略/发布文案.md 7.7 KB
- episodes/2026-10-02 Meta Muse国内0门槛注册全攻略/字幕.srt 4.0 KB
- episodes/2026-10-02 Meta Muse国内0门槛注册全攻略/字幕.vtt 4.0 KB
- episodes/2026-10-02 Meta Muse国内0门槛注册全攻略/旁白稿.md 2.4 KB
- episodes/2026-10-02 用 WorkBuddy 做视频的全流程/script.json 10 KB
- episodes/2026-10-02 用 WorkBuddy 做视频的全流程/发布文案.md 7.3 KB
- episodes/2026-10-02 用 WorkBuddy 做视频的全流程/字幕.en.srt 1.8 KB
- episodes/2026-10-02 用 WorkBuddy 做视频的全流程/字幕.en.vtt 1.8 KB
- episodes/2026-10-02 用 WorkBuddy 做视频的全流程/字幕.srt 1.7 KB
- episodes/2026-10-02 用 WorkBuddy 做视频的全流程/字幕.vtt 1.7 KB
- episodes/2026-10-02 用 WorkBuddy 做视频的全流程/旁白稿.md 1.3 KB
- lib/build.mjs 18 KB runs code
- lib/cues.mjs 8.1 KB runs code
- lib/paths.cjs 3.2 KB runs code
- lib/publish.mjs 11 KB runs code
- lib/render.mjs 6.6 KB runs code
- lib/tts/content-cache.mjs 4.8 KB runs code
- lib/tts/mi.mjs 18 KB runs code
- lib/tts/run.mjs 1.5 KB runs code
- lib/tts/tts.mjs 15 KB runs code
- lib/voice-check.mjs 4.0 KB runs code
- README.md 9.0 KB
- references/avatar.md 7.5 KB
- references/delivery-qa.md 6.0 KB
- references/publish.md 5.5 KB
- references/script-format.md 9.2 KB
- references/voices.md 5.1 KB
- remotion/package.json 551 B
- remotion/src/components/Background.tsx 1.6 KB
- remotion/src/components/Chrome.tsx 2.2 KB
- remotion/src/components/Icons.tsx 4.6 KB
- remotion/src/components/SceneShell.tsx 7.0 KB
- remotion/src/components/Subtitles.tsx 4.5 KB
- remotion/src/components/TalkingAvatar.tsx 7.1 KB
- remotion/src/index.ts 109 B runs code
- remotion/src/IpLecture.tsx 4.9 KB
- remotion/src/Root.tsx 1.2 KB
- remotion/src/scenes/index.tsx 27 KB
- remotion/src/theme.ts 1.8 KB runs code
- remotion/src/types.ts 3.5 KB runs code
- remotion/src/utils/anim.ts 1.8 KB runs code
- remotion/tsconfig.json 420 B
- templates/script.json 5.3 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.
- 14d ago First seen · 185 lines · 480 tokens per session scan A 8a2f8ffdeb95
ip-talking-head-lecture is a skill published in the GitHub repository wwwzhouhui/skills_collection (284 stars, last pushed 2d ago), with no licence file. It adds 480 tokens to every session and 5,507 once invoked, about $0.0019 per session on Opus 5.5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-04.
Other skills, from other repositories
video-to-skill
Turn a video, tutorial, playlist, or course into an installed, evidence-grounded course Skill that can teach, give practice and feedback, apply demonstrated methods, and answer reference questions. Use when the user provides video sources and wants reusable learning or operational capability.
gen
Generate a narrated, animated explainer video from a research paper (PDF) or a codebase/repo. Usage: /ppv:gen .
remotion-docs
Search Remotion documentation.
whiteboard-video
A hand-drawn-style template for turning technical articles or code into narrated animated videos. It uses scenes, speech, animation, and captions to explain one topic in a vertical video.
video-to-skill
Convert a video (local file or YouTube/URL) into structured, evidence-grounded knowledge — and ultimately into an installable agent skill. Use when the user provides a video file or video URL and wants it analyzed, summarized into steps, or turned into a skill; triggers include "watch this video", "learn from this…
bilibili-video-notes
A tool that turns educational or lecture videos from Bilibili, a Chinese video-sharing site, into DOCX study notes. It uses subtitles, screenshots, text recognition from images, and visual review to build the notes.