agentleFS
samsam007bsamsam007b/claude-code-standards-kit/skills/pro-samuel/SKILL.md

pro-samuel

Skill2 starsChanged 8 months agoMITView on GitHub

Professional mode for the kit maintainer. Skips onboarding and teaching, speaks directly, recaps once, then executes.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 2 are distinctive, and 3 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.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Ask at most one question: what to install or do, and which needs the machine serves.

    line 19
  2. Very specific:

    Write mode: "pro" in ~/.claude/kit/profile.json so later sessions stay in this mode.

    line 21
  3. Very specific:

    Leave the mode with /pro-samuel off: back to the teaching path.

    line 22
  4. Very specific:

    No personal data in this public kit (no addresses, accounts, keys).

    line 26
  5. Distinctive:

    Do not use em dashes in text produced for third parties.

    line 28

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

/pro-samuel

Language: if language is fr in ~/.claude/kit/profile.json, follow SKILL.fr.md in this folder instead.

Explicit switch only. Never auto-detected, never inferred from the machine or the user's name.

Behaviour

  1. Skip the level questionnaire and the teaching layer (/welcome, /explain stay available on request).
  2. Tone: short, direct, professional. No step-by-step walkthrough.
  3. Ask at most one question: what to install or do, and which needs the machine serves.
  4. Show one recap (tools, connectors, skills, hooks), get one confirmation, then run everything in a single pass.
  5. Write mode: "pro" in ~/.claude/kit/profile.json so later sessions stay in this mode.
  6. Leave the mode with /pro-samuel off: back to the teaching path.

Rules

  • No personal data in this public kit (no addresses, accounts, keys). Private context lives in the user's own ~/.claude.
  • Any external send or push still needs confirmation in the same turn.
  • Do not use em dashes in text produced for third parties.

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.