agentleFS
Sign inStart free
dymchenkkodymchenkko/claude-study-agent/.claude/skills/ingest/SKILL.md

ingest

Skill2 starsChanged 7 days agoMITView on GitHub

Convert newly added lecture materials (slides, PDFs, videos, notes) to searchable text and update the subject's topic map. Use after the user adds files to materials/ or asks to add/import/process materials or a lecture video URL.

88 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use daily-arxiv, exp-eval and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • LambenthanSkill

    daily-arxiv

    每日从 arXiv 拉取新论文，过滤相关性，auto-ingest 高优先级论文，检测 SOTA 更新

    Also in 5 projects that use this

  • LambenthanSkill

    exp-eval

    实验判决门：Review LLM 独立评判实验结果 → 4 种判决路径 → 自动更新 claims confidence、ideas status、graph edges

    Also in 5 projects that use this

  • phanghonghaoSkill

    poster

    HTML/CSS A4 海报生成。从沙龙/活动 Markdown 文件生成科技风 A4 海报 PDF/PNG。Use when user mentions: poster, 海报, 海报生成, make poster, generate poster, 活动海报, 沙龙海报.

    Also in 5 projects that use this

  • skyllwtSkill

    exp-pilot-eval

    Pilot result evaluation — read pilot results, apply success criteria, update idea page (pilot_result, failure_reason if failed), generate PILOT_VERDICT_REPORT. Called by /ideate Phase 5 after /exp-pilot-run.

    Also in 4 projects that use this

  • skyllwtSkill

    exp-pilot-run

    Pilot experiment execution — read Pilot Spec YAML, write pilot code, run experiment(Confirm with the user before operation and require the applicant to conduct manual inspection), return results. Called by /ideate Phase 5. Does NOT modify wiki pages or judge pass/fail.

    Also in 4 projects that use this

  • +6 more from Lambenthan
  • +1 more from skyllwt

The file

We split this skill into the rules it gives an agent

5 rules. 0 are common, 0 are distinctive, and 5 are very specific to this project.

  • 0

    Common

    Most of the 72 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 5

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Run ~/Study/.tools/study ingest "<Subject>" (add --url <URL> for a video link).

    line 10
  2. Very specific:

    If semantic search is set up, ingest also indexes the new files (~0.1 s per passage, a lecture in seconds).

    line 13
  3. Very specific:

    Read the NEW converted files.

    line 15
  4. Very specific:

    Update syllabus.md: add or refine topic rows in course order with precise sources (file p.x–y, slide n, [hh:mm:ss]) and an exam-weight …

    line 18
  5. Very specific:

    Add new topics to progress.md with Level 0 and no dates.

    line 21

“Common” is measured: kept by at least 6 in 10 of the 72 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Ingest materials

  1. Resolve the subject (create it with ~/Study/.tools/study new "<Subject>" if I ask for a new one).
  2. Run ~/Study/.tools/study ingest "<Subject>" (add --url <URL> for a video link). Video transcription runs locally and takes a few minutes per lecture — tell me before starting long ones and run it in the background if there are several. If semantic search is set up, ingest also indexes the new files (~0.1 s per passage, a lecture in seconds); a Semantic search is not set up line is fine, just mention /setup once.
  3. Read the NEW converted files. Scanned pages are OCR'd automatically (~2 s per page; marked > OCR:) — check formulas, tables and diagrams against the original PDF. If a PDF is still flagged as scanned/image-based (no OCR available, or handwriting), read the original PDF directly and mention /setup once.
  4. Update syllabus.md: add or refine topic rows in course order with precise sources (file p.x–y, slide n, [hh:mm:ss]) and an exam-weight guess (high/med/low) based on emphasis, repetition across lectures and the lecturer notes in CLAUDE.md. Merge duplicates; don't delete rows.
  5. Add new topics to progress.md with Level 0 and no dates. 5b. If links.json exists, run ~/Study/.tools/study links <Subject> --write: the local embedding model adds links for the new topics (existing links are kept). Don't write links yourself. If it says semantic search is off, skip this step.
  6. Summarise: files converted, topics added, anything that failed or needs my attention, and suggest /learn on the first new topic.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free