agentleFS
Sign inStart free
silouonesilouone/skills/skills/ingest/SKILL.md

ingest

Skill4 starsChanged 4 months agoMITView on GitHub

Turn a YouTube URL or local transcript/text file into a saved key-points extraction — core thesis, structured key points, and an applicability assessment grounded in the user's actual setup. Use when the user asks to "ingest" a video/article/file, wants key points extracted from a transcript, or wants to absorb a recommended video without watching it. Local-only; nothing is uploaded.

  • Installs packages

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

3 rules. 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 72 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Follow the contract below exactly.

    line 8
  2. Very specific:

    Assess applicability: when the content touches the user's tooling or workflow (their agent harness, hooks, skills, automations, projects).

    line 30
  3. Distinctive:

    Every extraction traces to its source via the header.

    line 66

“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 — source → saved key points

Follow the contract below exactly. This is pre-reading distillation, not a database pipeline: the only outputs are local files.

Steps

  1. Resolve the source.
    • YouTube URL or bare video ID → fetch the transcript locally:
      uv run <this-skill-dir>/scripts/fetch_transcript.py "<url>" --out transcripts
      This writes transcripts/youtube-<id>.txt (plain) and transcripts/youtube-<id>.timestamped.md. It only downloads public captions; if none exist, tell the user and stop. If uv is missing, fall back to python3 -m pip install --user youtube-transcript-api, then run the script with python3.
    • Local file path → read it directly. If the user gave a topic instead of a path, look for a matching file under ./transcripts/ before asking.
  2. Extract key points:
    • Core thesis in 2–4 sentences.
    • Key points: main arguments/framework as a compact structured list.
    • Preserve concrete numbers, demos, and decision rules — drop filler, repetition, and channel/self promotion.

  3. Assess applicability when the content touches the user's tooling or workflow (their agent harness, hooks, skills, automations, projects). Inspect the actual current state before claiming a gap — whichever of these exist on this machine:

    • Claude Code — ~/.claude/settings.json, ~/.claude/skills/, ~/.claude/hooks/, CLAUDE.md
    • Codex — ~/.codex/config.toml, ~/.codex/skills/, ~/.codex/automations/, AGENTS.md
    • the current repo, either way

    Then say where the user already stands vs. what the source recommends. Recommendations must be proportionate — flag what is NOT worth doing too. Skip this section entirely if the content has no operational relevance.

  4. Save to the same directory as the source, named <source-basename>_extracted_key_point.md, with this header:

    # Extracted Key Points — <source-basename>

Source: <url or path>
Topic: <one line>
Extracted: <YYYY-MM-DD>

## Core thesis
## Key points
## Applicability to my setup (optional)
  5. Reply with a one-paragraph summary and the saved file path — do not paste the whole file back.

Guarantees

  • Local-only: the transcript fetch is the sole network call.
  • Denser than the source: a section that adds no decision, number, or reusable idea doesn't survive.
  • Every extraction traces to its source via the header.

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