SuperAPI AI Directory

soia-pkm-transform-article-notebooklm

Writing & research

View repository

Updated 10-16 08:50

About this skill

soia-pkm-transform-article-notebooklm

Convert archived or specified articles into learning or interactive artifacts: quizzes, flashcards, mindmaps, podcast scripts, study notes, preferring NotebookLM, falling back to local Markdown.

Customer-readable description

What this skill can do

Convert Markdown / vault articles or URLs into learning artifacts:

  • Quiz: multiple choice + short answer + answer explanations
  • Flashcards: Anki-compatible double-sided cards
  • Mindmap: Mermaid / Markdown hierarchical structure
  • Podcast script: conversational audio script
  • Study notes: NotebookLM comprehensive summary
Customer wants Skill will do Customer can see
Generate quiz Local Markdown or NotebookLM quiz artifact Question count, question type distribution, file path
Make flashcards Anki-compatible Markdown or NotebookLM flashcards Card count, file path
Mindmap / podcast Mermaid mindmap / dialogue script Markdown File path, node count / word count
Upload to NotebookLM Upload source files, record notebook id notebook id / artifact path
Execution complete Acceptance: artifact structure complete, question and answer counts consistent Completion receipt

How customers use it

Other recognizable phrasings include "generate mindmap", "make podcast", "NotebookLM", "generate quiz", "make flashcards", "mindmap", "podcast"; when generically referred to as "generate cover" or "make PPT", this skill is not used.

  1. Specify the source (URL / vault path / local Markdown) and target type (quiz/flashcards/mindmap/podcast, optional).
  2. Optional: specify provider (local / notebooklm), question count, card count, difficulty.
  3. For URL sources, clip and archive first, then convert.

Dependencies and installation

claude plugin marketplace add soia-team/soia-open-skills
claude plugin install soia-pkm-vault@soia

When you only want this one skill, you can use the npx route. Note that the skill will land in the shared source of truth ~/.agents/skills; if the plugin is also installed, the same skill will have two indexes and drift separately, so it is recommended to choose one of the two:

npx skills add soia-team/soia-open-pkm-vault-skills -g -a '*' -s soia-pkm-transform-article-notebooklm -y

Private configuration goes in ~/.config/soia-skills/soia-pkm-transform-article-notebooklm/config.yml, can be overridden with SOIA_PKM_TRANSFORM_ARTICLE_NOTEBOOKLM_CONFIG_FILE .

WorkBuddy The loading unit ofnpx skills add -a '*' cannot cover it, it needs to be installed separately, see docs/install/workbuddy.md。

Logs and completion receipt

完成:<一句话>。

日志摘要:
- source: <路径或 URL>
- artifact_type: quiz | flashcards | mindmap | podcast | notes
- provider: local | notebooklm
- content_mode: learning
- output: <文件路径或 notebook id>
- count: <题数 / 卡片数 / 节点数>

验证:
- 文件存在且可读
- 题目数 == 答案数(quiz/flashcards)
- 脑图 Mermaid 可解析(mindmap)
- prompt 已落盘可重跑

问题与下一步:
- <无 / provider 降级原因 / NotebookLM 失败目标列表>

Boundaries

  • Default learning mode: structural reorganization, core knowledge point extraction, no compression of core points.
  • quiz/flashcards: question count == answer count == explanation count, acceptance must have all three consistent.
  • prompt is written to disk at outputs/transform/<YYYY>/<stem>/prompts/。
  • NotebookLM is an optional provider; when missing, fall back to local Markdown generation, do not stop the task.
  • Failed NotebookLM artifacts are recorded item by item (must not be silently skipped).

Workflow

  1. Confirm source → clip the URL first.
  2. Determine artifact_type:quiz(default)/ flashcards / mindmap / podcast / notes。
  3. Choose provider: user-specified > configuration > local Markdown.
  4. NotebookLM path: run the health check first (references/provider-notebooklm.md), then upload the source files, record the notebook id, and generate the corresponding artifact.
  5. Local path: read references/prompt-notebooklm.md the corresponding section to generate the prompt, and output Markdown.
  6. Generate artifacts to outputs/transform/<YYYY>/<stem>/, and save the prompt to disk.
  7. Acceptance: complete structure, consistent counts, parseable Mermaid (if applicable).
  8. A receipt, with NotebookLM failure targets listed item by item.

See references/prompt-notebooklm.md、references/notebooklm-test-matrix.md、references/quality-gates.md。