agentleFS
ntaffziintaffzii/Skill-Agents/skills/personal/SKILL.md

personal

Skill4 starsChanged 2 months agoMITView on GitHub

Manage personal-only skills and private agent preferences that should not be promoted into public or team skill buckets. Use when the user asks to add personal rules, local setup guidance, private workflows, preferences, or machine-specific instructions.

The file

Show its rules and text

We split this skill into the rules it gives an agent

14 rules. About 0 are common, 13 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈13

    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. Distinctive:

    Use this skill for instructions tied to one user, one machine, one vault, or one private workflow.

    line 8
  2. Distinctive:

    Never store secrets in a personal skill.

    line 32
  3. Distinctive:

    Keep local paths and user preferences clearly scoped.

    line 33
  4. Distinctive:

    Do not let personal rules override explicit user instructions in a task.

    line 34
  5. Distinctive:

    If it helps only this user, keep it personal.

    line 40
  6. Distinctive:

    If it helps a team or repo, consider a stable skill bucket.

    line 41
  7. Very specific:

    If it is executable behavior, consider mcp-tools/.

    line 42
  8. Distinctive:

    Write the smallest instruction that changes agent behavior.

    line 45
  9. Distinctive:

    Avoid turning preferences into universal rules.

    line 46
  10. Distinctive:

    Do not store secrets.

    line 50
  11. Distinctive:

    Do not paste sensitive personal data unless explicitly needed.

    line 51
  12. Distinctive:

    Prefer references to local files over copied private content.

    line 52
  13. Distinctive:

    If a personal skill becomes broadly useful, promote a cleaned version to a public bucket.

    line 55
  14. Distinctive:

    Remove user-specific paths, names, secrets, and assumptions before promotion.

    line 56

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill 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
SKILL.md

Personal Skill Rules

Use this skill for instructions tied to one user, one machine, one vault, or one private workflow.

Purpose

skills/personal/ keeps personal context out of general-purpose skills. This prevents public skills from becoming noisy, brittle, or too specific to one setup.

What Belongs Here

  • Personal writing preferences
  • Local machine paths
  • Private project conventions
  • Personal Obsidian vault rules
  • Private API or service usage notes without secrets
  • Repeated workflows that only one user needs

What Does Not Belong Here

  • Secrets, tokens, passwords, or private keys
  • Generic engineering practices that belong in engineering/
  • Team-wide rules that deserve a stable shared skill
  • Large reference dumps that should live in a separate private document

Rules

  • Never store secrets in a personal skill.
  • Keep local paths and user preferences clearly scoped.
  • Do not let personal rules override explicit user instructions in a task.
  • Promote only a cleaned, non-private version into public buckets.

Workflow

  1. Classify the instruction
    • If it helps only this user, keep it personal.
    • If it helps a team or repo, consider a stable skill bucket.
    • If it is executable behavior, consider mcp-tools/.
  2. Keep it scoped
    • Write the smallest instruction that changes agent behavior.
    • Avoid turning preferences into universal rules.
    • Include examples only when they prevent ambiguity.
  3. Protect private context
    • Do not store secrets.
    • Do not paste sensitive personal data unless explicitly needed.
    • Prefer references to local files over copied private content.
  4. Review promotion
    • If a personal skill becomes broadly useful, promote a cleaned version to a public bucket.
    • Remove user-specific paths, names, secrets, and assumptions before promotion.

Verification

  • Confirm the skill does not contain secrets.
  • Confirm the instruction is personal rather than broadly reusable.
  • Confirm any local paths are intentional.

Output Format

End with:

  • Personal rule added or changed
  • Why it belongs in personal/
  • Any privacy risk
  • Whether it could later be promoted

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.