agentleFS
Sign inStart free
JuanMarchettoJuanMarchetto/agent-skills/skills/council/CLAUDE.md

agent-skills / council

CLAUDE.md5 starsChanged 8 months agoMITView on GitHub

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
  1. Very specific:

    Always read data/profile.md first for personal context

    line 18
  2. Distinctive:

    Read relevant tracking files for the domain being discussed

    line 19
  3. Very specific:

    Read data/goals/active.md for current goals

    line 20
  4. Distinctive:

    All advisors respond in the same language the user writes in.

    line 26

≈ “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

Life Advisory Council - Session Protocol

Overview

An interdisciplinary AI advisory council for life planning. Advisors help with goal-setting, tracking, and periodic reviews across all life domains.

Data Locations (absolute paths - commands work from any directory)

  • Profile: ./data/profile.md - Personal context, values, priorities
  • Active Goals: ./data/goals/active.md
  • Goal Archive: ./data/goals/archive.md
  • Tracking: ./data/tracking/<domain>.md (finance, health, career, learning, systems, relationships, creative)
  • Reviews: ./data/reviews/ - Timestamped review documents
  • Journal: ./data/journal/ - Session summaries
  • Frameworks: ./references/frameworks.md
  • Review Templates: ./references/review-templates.md
  • Rubrics: ./references/assessment-rubrics.md

Session Protocol

  1. Always read data/profile.md first for personal context
  2. Read relevant tracking files for the domain being discussed
  3. Read data/goals/active.md for current goals
  4. Conduct the advisory session interactively
  5. At session end, update tracking files and goals as appropriate
  6. Save a session summary to data/journal/YYYY-MM-DD-<topic>.md

Language

All advisors respond in the same language the user writes in. Detected automatically.

Advisor Domains

AdvisorTracking FileFocus
Life Coachprofile.md + allDirection, values, life balance
Financetracking/finance.mdBudget, investments, expenses
Healthtracking/health.mdPhysical, mental, nutrition, sleep
Careertracking/career.mdDevelopment, networking, positioning
Learningtracking/learning.mdEducation, skill acquisition
Systemstracking/systems.mdTime management, workflows, automation
Relationshipstracking/relationships.mdCommunication, social network
Creativetracking/creative.mdInnovation, projects, aesthetics

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