· 2026-05-05 ·main@HEAD

youtube-to-ebook

zarazhangrui/youtube-to-ebook

🛠53 / 100

✅

⚠

🎯

⚠

🗺

📍video-to-text

⚛

→

⚗

→

🧬

🛑

0–29

⚠️

30–49

🛠

50–79

🏭

80–100

▼

🛠· 53 / 100

✓5 claims passed, no critical failures
⚠README may claim a license but no LICENSE file exists
⚪no recent release pipeline + not recently active
⚪EN-only or ZH-only README
⚪static-only eval; live e2e pending

#1👤

#2🎯

#3🧭

#4⇄

zarazhangrui/personalized-podcast

🛠 · 54atom

zarazhangrui/codebase-to-course

🛠 · 60atom


`git clone + pip install -r requirements.txt`	any (Python)	moderate
`Mac LaunchAgent for weekly auto-runs`	macOS only	moderate

🌐

YouTube Data API v3

Fetch video metadata + transcripts

Free quota: 10,000 units/day — sufficient for personal use

Anthropic Claude API

Rewrite transcripts as magazine articles

Per-article cost depends on transcript length

SMTP (any email provider)

Optional email delivery

Use Gmail / iCloud / etc.; only needed for email delivery

· 7

5 1 1

	+40
	+10
	0
	0
	+5
	-2

6 / 7

passed claim-001

passed claim-002

passed claim-003

passed claim-004

passed claim-005

failed claim-006

untested claim-007

`input_contract`
`output_contract`
`determinism`
`idempotence`
`no_skill_callouts`
`failure_mode_clarity`

evidence_completeness='partial' (not portable) → capped at 'usable'

only 2/3 critical claims covered

archetype: hybrid-skill→core_layer_tested? True→evidence: partial→recommended: usable→final: usable

ceiling 1 · evidence_completeness='partial' (not portable) → capped at 'usable'


claim-001	5 阶段 pipeline 文件齐全（videos / transcripts / articles / email / tracker）	critical	pipeline-shape	● passed
claim-002	SKILL.md 真实存在	high	skill-shape	● passed
claim-003	requirements.txt 涵盖 README 描述的所有依赖	critical	install	● passed
claim-004	dashboard.py 是真实 Streamlit web UI	high	ui	● passed
claim-005	Mac LaunchAgent plist 真实存在且不只是占位	high	automation	● passed
claim-006	仓库有 LICENSE	high	licensing	✕ failed
claim-007	端到端：跑一次能产出 EPUB	critical	end-to-end	○ untested

0.00s

run-static-checks

2026-05-05

0% — tokens in ? / out ?

run-static-checks

2026-05-05

0% — tokens in ? / out ?

# youtube-to-ebook — final verdict (2026-05-05)

## Repo

- **Name:** zarazhangrui/youtube-to-ebook · **Stars:** 440
- **Archetype:** hybrid-skill · **Layer:** molecule
- **Branch:** main@HEAD · **Last push:** 2026-01-28 (3+ months stale)

## What was evaluated

| Claim | Status | Notes |
|---|---|---|
| 001 5-stage pipeline | passed | Real .py files for each stage |
| 002 SKILL.md | passed | 171 lines with frontmatter |
| 003 requirements coverage | passed | All 5 README-claimed deps |
| 004 Streamlit dashboard | passed | 890 lines (substantial) |
| 005 LaunchAgent plists | passed | Valid format with Label + ProgramArguments |
| 006 LICENSE | **failed** | HTTP 404 |
| 007 live e2e | untested | needs YouTube + Anthropic keys + 1 channel |

## Real findings

1. **README templating leak.** Git-clone command reads
   `git clone https://github.com/YOUR_USERNAME/youtube-to-ebook.git`
   — never edited to `zarazhangrui`. Copy-paste users will get a
   404 on the clone step.

2. **No LICENSE** — third Zara repo in this batch missing one. Pattern.

3. **3+ months stale.** Last push 2026-01-28. YouTube's transcript
   API breaks under YouTube frontend changes; without recent
   maintenance there's real risk the pipeline is already broken.
   Costs `recently_active=false` → no maintainer-active bonus.

4. **Mac-only automation.** LaunchAgent plists are Mac-specific.
   README's "Automation" section doesn't mention Linux / cron, even
   though many users would want it.

## Path forward

1. Fix README's `YOUR_USERNAME` placeholder → `zarazhangrui`.
2. Add LICENSE.
3. Push a fresh commit (even just a doc fix) to mark recently-active.
4. Run a real YouTube → EPUB pipeline; log under run-live-e2e/.
5. Add a Linux cron snippet for non-Mac users.