speak-human-en

v0.6.0

English version: make Claude speak human and ask well — a pre-question self-check (verify first / brief the context / gloss the jargon / leave room to combine options) plus expression discipline (S1–S6, incl. S6 changelog-style reporting: multi-item progress or anything undone/wrong gets a Done/Not done/Known issues report), mined from 548 real AskUserQuestion decision records. touch ~/.claude/.speak-human-always to keep it always on

Claude Code1 Skill

By Tony Jiang2 GitHub starsUpdated 4 days ago

Directory evidence

Runtimes: Claude Code
Parsed components: 1 skill or MCP entry
Source updated: Sep 20, 2026
Manifest status: Canonical path parsed

The directory validates manifest shape and source location. It does not execute the plugin or provide a security endorsement. Review the indexing methodology →

Install speak-human-en for Claude Code

Installs for the current user

claude plugin marketplace add IchenDEV/agent-plugin-mkt
claude plugin marketplace update agent-plugin-marketplace
claude plugin install speak-human-en@agent-plugin-marketplace

Paste and run these commands in a terminal with Claude Code. They add and refresh the PluginsMP catalog, then install this plugin.

The installer fetches third-party code from the source repository shown on this page. This directory validates manifest structure and source location, but does not perform a security audit; review the manifest, components, and source before installing.

Get the source manually

$ git clone https://github.com/7bata/claude-workflow-kit

Clone the source repository, then follow its setup instructions to add the plugin to a compatible client. The plugin root is plugins/speak-human-en/.

Plugin files

plugins/speak-human-en/

├── .claude-plugin/plugin.json
└── skills/speak-human/SKILL.md

Included Skills1

speak-humanskills/speak-human/SKILL.md

Discipline Claude must follow whenever it's about to open its mouth — asking a question (especially via AskUserQuestion with options) or shaping any output aimed at the user. Run the self-check before every question, and the expression discipline before every output. The rules come from data-mining 548 real decision records the author made — not abstract etiquette. Trigger manually with `/speak-human`; if the always-on flag file has been touched, it auto-injects at the start of every session and stays in effect throughout.

Plugin manifests1

plugins/speak-human-en/.claude-plugin/plugin.json

{
  "name": "speak-human-en",
  "version": "0.6.0",
  "description": "English version: make Claude speak human and ask well — a pre-question self-check (verify first / brief the context / gloss the jargon / leave room to combine options) plus expression discipline (S1–S6, incl. S6 changelog-style reporting: multi-item progress or anything undone/wrong gets a Done/Not done/Known issues report), mined from 548 real AskUserQuestion decision records. touch ~/.claude/.speak-human-always to keep it always on",
  "author": {
    "name": "Tony Jiang"
  },
  "homepage": "https://github.com/7bata/claude-workflow-kit",
  "keywords": [
    "claude-code",
    "askuserquestion",
    "communication",
    "plain-language",
    "skills"
  ]
}