agentleFS
Sign inStart free
AgriciDanielAgriciDaniel/youtube-scout/CLAUDE.md

youtube-scout

CLAUDE.md35 starsChanged 2 months agoMITView on GitHub

Claude Code skill: /scout <topic> turns one topic into a ranked YouTube research workbook. Read SKILL.md for the runtime contract and README.md for the product view. - Source of truth is this checkout. ~/.claude/skills/scout/ is an installed copy; after changing scripts/scout.py or SKILL.md, run ./install.sh to refresh it. - Quality gate: python -m pytest (offline, fixtures under tests/fixtures/) and ruff check .. Every behaviour change ships with a test. - Never commit API keys, .env files, generated workbooks, downloads, or…

  • Reads credentials
  • In this repository2 other files it gives its agents.

The file

We split this CLAUDE.md into the rules it gives an agent

4 rules. About 0 are common, 2 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  • could be automatic: a setting could enforce it
  1. Very specific:

    Read SKILL.md for the runtime contract and README.md for the product view.

    line 4
  2. Very specific:

    Never commit API keys, .env files, generated workbooks, downloads, or the probe cache.

    line 12
  3. Distinctive:

    No em dashes anywhere: code, comments, docs, commits.

    line 15
  4. Distinctive:

    Commit messages: imperative sentence case, git commit -s.

    line 16

≈ “Common” is an estimate: at least 1 in 5 of the 26,980 CLAUDE.md files we read have a rule of the same kind, not the same words. “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
CLAUDE.md

youtube-scout

Claude Code skill: /scout <topic> turns one topic into a ranked YouTube research workbook. Read SKILL.md for the runtime contract and README.md for the product view.

Working in this repo

  • Source of truth is this checkout. ~/.claude/skills/scout/ is an installed copy; after changing scripts/scout.py or SKILL.md, run ./install.sh to refresh it.
  • Quality gate: python -m pytest (offline, fixtures under tests/fixtures/) and ruff check .. Every behaviour change ships with a test.
  • Never commit API keys, .env files, generated workbooks, downloads, or the probe cache. tests/test_repo_hygiene.py fails on em dashes, local absolute paths, key file references, credential-shaped strings, and tracked workbooks. Keep it that way.
  • No em dashes anywhere: code, comments, docs, commits.
  • Commit messages: imperative sentence case, git commit -s. No git add -A; add files by name.
  • The API key comes from YOUTUBE_API_KEY or a key file the user names via SCOUT_ENV_FILE. Load the user's key file into the environment for the command; never copy the key into the repo or print it.
  • The repository is public. Never commit anything that should not be public.

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