技能
备考的人应该都懂：强化班几十讲，做错一道题想回看对应知识点，只能凭记忆拖进度条。视频没法检索、没法打印，这个痛贯穿我整个备考期。 所以做了个开源技能 chalkpress——不是又一个「视频转文字」工具，而是把课程视频压缩成一册讲义 PDF：每页一个关键帧画面 + 该时间窗的字幕，文字层可检索可复制。 用法就是给 agent 发一句话（ ChatGPT / Claude Code 等客户端，任何能执行命令的都行）： 用这个技能把我的网课视频转成讲义： https://github.com/luolin1024/chalkpress-skill agent 会自己走完整个流程：装依赖 → ffmpeg 场景检测抓关键帧 → Whisper 本地转写 → 校对字幕（同音字误听，比如「坚偶校验」→「奇偶校验」，内置软
This explanation quotes or summarizes the cited source record. Saving creates a bookmark on this device, with no automatic account sync.
- First observed in our collection
- Nov 12, 2026, 12:15 AM UTC
- Earliest cited publication
- Nov 11, 2026, 5:12 PM UTC
- Last observed
- Nov 12, 2026, 12:15 AM UTC
Evidence in the last complete seven days
- Source mentions
- 1 Previous seven days 0
- Distinct sources
- 1 Previous 0
- Comparable growth
- Not comparable
- Ranking appearances
- 0
Collection observations and undated records are separate from dated publication counts. Observed in 7d：1 · Undated records：0
Collection coverage · Comparable windowsCurrent / previous observed days 7 / 7
Counts use complete UTC days. First observed means first seen by this collection, not when a term was coined.
Current window：2026-11-06 → 2026-11-13 (end excluded) · History 25 days
| Source | Current days | Previous days | Last success |
|---|---|---|---|
| arXiv | 7 | 6 | Nov 12, 2026, 11:22 AM UTC |
| arXiv | 7 | 7 | Nov 12, 2026, 11:21 AM UTC |
| Ask HN | 7 | 7 | Nov 13, 2026, 8:38 AM UTC |
| Ask HN | 7 | 7 | Nov 13, 2026, 8:38 AM UTC |
| Ask HN | 7 | 7 | Nov 13, 2026, 1:17 AM UTC |
| Ask HN | 7 | 7 | Nov 13, 2026, 8:38 AM UTC |
| GitHub | 7 | 7 | Nov 13, 2026, 1:16 AM UTC |
| GitHub Issues | 7 | 7 | Nov 13, 2026, 1:16 AM UTC |
| GitHub Releases | 7 | 7 | Nov 13, 2026, 1:16 AM UTC |
| GitHub | 7 | 7 | Nov 13, 2026, 1:16 AM UTC |
| GitHub Issues | 7 | 7 | Nov 13, 2026, 1:16 AM UTC |
| GitHub Releases | 7 | 7 | Nov 13, 2026, 1:17 AM UTC |
| GitHub | 7 | 7 | Nov 13, 2026, 1:17 AM UTC |
| GitHub Issues | 7 | 7 | Nov 13, 2026, 1:16 AM UTC |
| GitHub Releases | 7 | 7 | Nov 13, 2026, 1:17 AM UTC |
| GitHub Discovery | 7 | 1 | Nov 13, 2026, 8:38 AM UTC |
| GitHub Trending | 7 | 7 | Nov 13, 2026, 1:17 AM UTC |
| 7 | 7 | Nov 13, 2026, 8:38 AM UTC | |
| Hugging Face | 7 | 7 | Nov 12, 2026, 9:30 AM UTC |
| Hugging Face Spaces | 7 | 1 | Nov 13, 2026, 1:17 AM UTC |
| Hacker News | 7 | 7 | Nov 13, 2026, 8:38 AM UTC |
| Hacker News | 7 | 7 | Nov 13, 2026, 8:38 AM UTC |
| Hacker News | 7 | 7 | Nov 13, 2026, 8:38 AM UTC |
| Hacker News | 7 | 1 | Nov 13, 2026, 8:38 AM UTC |
| Show HN | 7 | 1 | Nov 13, 2026, 8:38 AM UTC |
| MIT News | 6 | 7 | Nov 13, 2026, 1:16 AM UTC |
| OpenAI | 7 | 7 | Nov 13, 2026, 8:38 AM UTC |
| Product Hunt | 7 | 7 | Nov 13, 2026, 8:38 AM UTC |
| 量子位 | 6 | 6 | Nov 13, 2026, 8:38 AM UTC |
| OpenRouter | 7 | 1 | Nov 13, 2026, 8:38 AM UTC |
| GitHub Trending | 7 | 7 | Nov 12, 2026, 4:00 AM UTC |
| Hugging Face Models | 7 | 1 | Nov 13, 2026, 1:17 AM UTC |
| HF Daily Papers | 6 | 1 | Nov 13, 2026, 1:17 AM UTC |
| OpenRouter | 7 | 1 | Nov 13, 2026, 8:38 AM UTC |
| Product Hunt | 7 | 7 | Nov 12, 2026, 4:00 AM UTC |
| SEC EDGAR | 7 | 7 | Nov 13, 2026, 1:16 AM UTC |
| Sequoia Capital | 7 | 7 | Nov 13, 2026, 8:38 AM UTC |
| Simon Willison | 7 | 1 | Nov 13, 2026, 8:38 AM UTC |
| TechCrunch | 7 | 7 | Nov 13, 2026, 8:38 AM UTC |
| Contracts Finder | 7 | 7 | Nov 13, 2026, 1:16 AM UTC |
| V2EX | 7 | 7 | Nov 13, 2026, 1:00 AM UTC |
- Counts describe monitored public sources, not the whole web or search demand.
Daily history · up to 90 days
Bars show dated source mentions. The latest UTC day may be incomplete. Zero mentions and missing collection coverage are different conditions.
View accessible daily data
| UTC date | Mentions | Sources | Observations | Ranking appearances |
|---|---|---|---|---|
| 2026-10-30 | 0 | 0 | 0 | 0 |
| 2026-10-31 | 0 | 0 | 0 | 0 |
| 2026-11-01 | 0 | 0 | 0 | 0 |
| 2026-11-02 | 0 | 0 | 0 | 0 |
| 2026-11-03 | 0 | 0 | 0 | 0 |
| 2026-11-04 | 0 | 0 | 0 | 0 |
| 2026-11-05 | 0 | 0 | 0 | 0 |
| 2026-11-06 | 0 | 0 | 0 | 0 |
| 2026-11-07 | 0 | 0 | 0 | 0 |
| 2026-11-08 | 0 | 0 | 0 | 0 |
| 2026-11-09 | 0 | 0 | 0 | 0 |
| 2026-11-10 | 0 | 0 | 0 | 0 |
| 2026-11-11 | 1 | 1 | 0 | 0 |
| 2026-11-12 | 0 | 0 | 1 | 0 |
| 2026-11-13 | 0 | 0 | 0 | 0 |
![Source page screenshot: [推广] [分享] 一句话让 AI Agent 把网课视频变成讲义 PDF（开源 · 全程本地 · 零 API Key）](/media/df8803a9ed1486f0dcb24d54?v=2026-11-11T18%3A25%3A22.158Z)
Source evidence
Sources in the evidence shown：V2EX 1
V2EX · Published Nov 11, 2026
[推广] [分享] 一句话让 AI Agent 把网课视频变成讲义 PDF（开源 · 全程本地 · 零 API Key）
备考的人应该都懂：强化班几十讲，做错一道题想回看对应知识点，只能凭记忆拖进度条。视频没法检索、没法打印，这个痛贯穿我整个备考期。 所以做了个开源技能 chalkpress——不是又一个「视频转文字」工具，而是把课程视频压缩成一册讲义 PDF：每页一个关键帧画面 + 该时间窗的字幕，文字层可检索可复制。 用法就是给 agent 发一句话（ ChatGPT / Claude Code 等客户端，任何能执行命令的都行）： 用这个技能把我的网课视频转成讲义： https://github.com/luolin1024/chalkpress-skill agent 会自己走完整个流程：装依赖 → ffmpeg 场景检测抓关键帧 → Whisper 本地转写 → 校对字幕（同音字误听，比如「坚偶校验」→「奇偶校验」，内置软
View source record →
Review priority 38 / 100
This score orders research candidates. It is not search volume, a forecast or verified commercial demand.
Evidence
8 / 30Distinct dated articles or first observations; repeat crawling adds nothing.
Publisher diversity
8 / 25Conservative owner grouping; syndicated copies count once.
Comparable change
0 / 20Comparable complete weeks only; no percentage from a zero baseline.
Recent evidence
13.6 / 15Latest publication or first observation, not repeated fetch time.
Name specificity
8 / 10Explicit entities and technical concepts outrank ambiguous acronyms.
Limitations and interpretation
- First observation is a collection milestone, not proof that a word or product is new to the world.
- Counts describe monitored public sources, not the whole web or search demand.
- First observed here is not the invention date of a name or idea.
- Candidates come from public titles, summaries and entity URLs, not verified full-text analysis.
- Owner grouping is conservative; undisclosed syndication may remain.
- The previous week is too small for a reliable percentage change.
- Current evidence comes from one publisher or owner.