agentleFS
assaioassaio/unwordy/skills/sync/SKILL.md

sync

Skill1 starsChanged 53 days agoMITView on GitHub

Render the unwordy voice into AGENTS.md, .cursor/rules/unwordy.mdc and ~/.codex/AGENTS.md and install the Codex and Cursor hook configs. Safe to run twice.

54 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use develop, scope 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.
  • hong9LeeSkill

    develop

    빌드, 아키텍처, git 관련 작업 시 OMS MSA 공통 인프라 규칙을 적용한다. 기술 스택, 빌드 명령, 헥사고날 아키텍처 구조, git 워크플로우, AI Context 동기화 규칙을 다룬다. 코드 작성 컨벤션은 /convention, 테스트 컨벤션은 /test-guide 스킬을 참조.

    Also in 6 projects that use this

  • YuriNachosSkill

    scope

    Configure claude-scope status line widgets for Claude Code. Use when user wants to customize widgets, change theme, reorder elements, or modify display style.

    Also in 7 projects that use this

  • nicolasestremSkill

    document

    Create focused documentation for specific components or features

    Also in 5 projects that use this

  • kt057Skill

    check

    lint, typecheck, test を一括実行して結果をサマリーする

    Also in 6 projects that use this

  • Microsoft AzureSkill

    test

    Also in 8 projects that use this

  • Microsoft AzureSkill

    validate

    Run the full CI validation workflow locally before submitting a PR. Use this as a final check to ensure all Azure DevOps CI pipeline steps will pass.

    Also in 4 projects that use this

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 47 edited versions we read keep these.

  • 3

    Distinctive

    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. Distinctive:

    Put the current voice into the files other tools read.

    line 8
  2. Very specific:

    Use the local CLI's voice output when available.

    line 13
  3. Distinctive:

    Read each file first. If it already holds exactly that text, leave it alone and report it as unchanged.

    line 31
  4. Distinctive:

    Check for existing Codex and Cursor configuration directories.

    line 36
  5. Very specific:

    If this is a skills-only installation, sync the voice only.

    line 49

“Common” is measured: kept by at least 6 in 10 of the 47 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

Put the current voice into the files other tools read. Running this twice changes nothing.

1. Build the block

Use the local CLI's voice output when available. Otherwise resolve the first profile in this order: an existing $UNWORDY_STYLE, the nearest .unwordy.md up to the git root, $XDG_CONFIG_HOME/unwordy/style.md (default ~/.config/unwordy/style.md). Honor enabled, disabled rules, limits, role, tone and disclosure. With no profile, use clear direct language and retain facts, uncertainty and evidence. Do not add fixed punctuation or length bans.

Wrap the resolved voice in <!-- unwordy:start (managed by unwordy; edit .unwordy.md or ~/.config/unwordy/style.md instead) --> and <!-- unwordy:end -->. A disabled profile removes an existing managed block.

2. Write the project files

  • AGENTS.md: replace whatever sits between the two markers. With no markers, append a blank line and BLOCK. Create the file with BLOCK if it is missing.
  • .cursor/rules/unwordy.mdc: ---, description: unwordy writing style, alwaysApply: true, ---, then BLOCK. Replace only this managed file. Preserve unrelated rules in other files.

Read each file first. If it already holds exactly that text, leave it alone and report it as unchanged.

3. Ask before the machine-wide files

Check for existing Codex and Cursor configuration directories. List what you would write, then ask once before writing anything under the home directory:

  • ~/.codex/AGENTS.md: the same marker block.
  • ~/.codex/hooks.json: the entries from ${CLAUDE_PLUGIN_ROOT}/hooks/codex.hooks.json with ${CLAUDE_PLUGIN_ROOT} replaced by the real plugin path. Merge into the file's hooks object, keep every other hook, and skip entries whose command already mentions unwordy.
  • ~/.cursor/hooks.json: the entries from ${CLAUDE_PLUGIN_ROOT}/hooks/cursor.hooks.json with ${CURSOR_PLUGIN_ROOT} replaced by the real plugin path, merged into the matching arrays under hooks, keeping "version": 1.

If this is a skills-only installation, sync the voice only; hook assets are not installed. Locate the plugin root before using hook templates. Skip the hook files for a tool that already loads unwordy as its own plugin, or the lints run twice. For Codex, codex plugin list shows unwordy@unwordy installed, enabled in that case.

4. Report

One line per file: written, updated or unchanged. Then say that Codex and Cursor pick up new hooks on their next start, and that Codex runs a new hook only after it is reviewed once in /hooks.

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.