agentleFS
blueclover22blueclover22/mw_agent_kit/skills/setup/SKILL.md

setup

Skill1 starsChanged 8 days agoMITView on GitHub

Use when asked to install or update the mak common rules in ~/.claude/CLAUDE.md, optionally in Korean (ko) or English (en).

191 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use add-voice-transcription, add-discord and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • juancruzmunozalbeloSkill

    add-voice-transcription

    Add voice message transcription to NanoClaw using OpenAI's Whisper API. Automatically transcribes WhatsApp voice notes so the agent can read and respond to them.

    Also in 5 projects that use this

  • MicrosoftSkill

    add-discord

    Add Discord bot channel integration via Chat SDK.

    Also in 11 projects that use this

  • MicrosoftSkill

    add-slack

    Add Slack channel integration via Chat SDK.

    Also in 11 projects that use this

  • juancruzmunozalbeloSkill

    add-telegram-swarm

    Add Agent Swarm (Teams) support to Telegram. Each subagent gets its own bot identity in the group. Requires Telegram channel to be set up first (use /add-telegram). Triggers on "agent swarm", "agent teams telegram", "telegram swarm", "bot pool".

    Also in 7 projects that use this

  • +8 more from microsoft

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 171 edited versions we read keep these.

  • 2

    Distinctive

    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:

    If it does not exist: create it with the snippet as its entire content.

    line 27
  2. Distinctive:

    Never modify content outside the marker block without explicit user confirmation (step 5 is the only case, and it requires confirmation).

    line 38
  3. Very specific:

    Do not run git commands; ~/.claude may not be a repository.

    line 39

“Common” is measured: kept by at least 6 in 10 of the 171 edited versions of this file we could read. “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

mak:setup — Install Common Rules into the Global CLAUDE.md

Injects the rules snippet into ~/.claude/CLAUDE.md as a marker-delimited block:

<!-- mak:begin — ... -->
...rules...
<!-- mak:end -->

Everything between (and including) the markers is owned by mak. The user's own content outside the markers is never touched. Removal is done by mak:teardown.

Procedure

  1. Pick the language and read the snippet — two variants exist:

    • ${CLAUDE_PLUGIN_ROOT}/skills/setup/assets/claude-md-snippet.ko.md (Korean)
    • ${CLAUDE_PLUGIN_ROOT}/skills/setup/assets/claude-md-snippet.en.md (English)

    Selection order: an explicit skill argument (ko / en) wins; otherwise match the user's conversation language (Korean conversation → ko, anything else → en); if genuinely ambiguous, ask the user. The chosen file (markers included) is the exact block to install.

  2. Read ~/.claude/CLAUDE.md.
    • If it does not exist: create it with the snippet as its entire content. Report and stop.
  3. Back up once — if ~/.claude/CLAUDE.md.mak-backup does not exist, copy the current ~/.claude/CLAUDE.md to it before any modification. If the backup already exists, leave it (it preserves the pre-mak state).
  4. If markers already exist (<!-- mak:begin and <!-- mak:end --> both present): first count them — if more than one begin or end marker exists (corrupted/duplicated state), do not modify anything; show the user the marker locations and ask how to reconcile. With exactly one pair, replace everything from the begin marker line through the end marker line with the new snippet. This is also how the block's language is switched — the whole block is replaced with the chosen variant. Report "updated existing block" (and the language, if it changed) and stop.
  5. If no markers, check for legacy content — earlier versions of this kit were installed by manually pasting sections into ~/.claude/CLAUDE.md. Look outside any markers for:
    • An ## Agents / ## Skills catalog listing the kit's agents or skills, and a ## Workflow section matching the kit's task grades: these are superseded by the plugin and this block. Do not delete anything silently — show the user what overlaps and propose removing the duplicates before appending the block. Only proceed after confirmation.
    • Everything else outside the markers is the user's own content — leave it untouched regardless of its headings; just note what exists (e.g. ## Rules / ## Coding Rules / ## File Handling, or any user-authored section under any name). Where the user's own coding rules overlap the block's principle mapping, the user's rules take precedence on conflict.
  6. Otherwise — append the snippet to the end of the file, separated by one blank line.
  7. Report — state what was done (created / block updated / appended / merged after confirmation), the backup path, and remind: "Run /mak:teardown before uninstalling the plugin to restore CLAUDE.md."

Cautions

  • Never modify content outside the marker block without explicit user confirmation (step 5 is the only case, and it requires confirmation).
  • Do not run git commands; ~/.claude may not be a repository.
  • Install exactly one of the two bundled snippets — never translate on the fly or mix languages. The ko/en variants are maintained as mirrors in the plugin repository.

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.