agentleFS
zwjbendnzwjbendn/weight-loss-skill/CLAUDE.md

weight-loss-skill

CLAUDE.md1 starsChanged 8 months agoMITView on GitHub

A collection of AI nutritionist skills — diet tracking, exercise planning, meal planning, weight tracking, emotional support, and more. Each skill is a self-contained module with its own SKILL.md. Before modifying any skill or data structure, read docs/CONVENTIONS.md.

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

3 rules. About 0 are common, 2 are distinctive, and 1 is 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.

  • 1

    Very specific

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

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

    Before modifying any skill or data structure, read docs/CONVENTIONS.md.

    line 11
  2. Distinctive:

    Use existing scripts for data access when available

    line 19
  3. Distinctive:

    No dots in filenames as namespace separators

    line 21

≈ “Common” is an estimate: at least 1 in 5 of the 25,680 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

CLAUDE.md

Project: weight-loss-skill

A collection of AI nutritionist skills — diet tracking, exercise planning, meal planning, weight tracking, emotional support, and more. Each skill is a self-contained module with its own SKILL.md.

Required Reading

Before modifying any skill or data structure, read docs/CONVENTIONS.md.

Key Rules

  • No language selection logic in skills — locale.json is the sole authority for reply language. Never add "reply in the user's language" or similar directives. See docs/CONVENTIONS.md §10.
  • Transactional/structured data → JSON under data/
  • Profile-like content that changes slowly → Markdown at workspace root
  • Group related data into one file per domain
  • Use existing scripts for data access when available
  • File naming: lowercase, hyphen-separated
  • No dots in filenames as namespace separators
  • Each data file has an owning skill — check before modifying its schema
  • New fields in existing JSON files must be backward-compatible

Project Structure

  • Each skill lives in its own directory with a SKILL.md
  • Shared scripts live in each skill's scripts/ directory
  • docs/ contains project-level documentation
  • Agent workspaces follow the layout defined in docs/CONVENTIONS.md

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.

Reviews can't be read right now.

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.