Agent Plugins Marketplace
← All plugins

authoring

v0.1.10

Write and audit the things an AI harness reads: create, check, and refactor SKILL.md files, audit shell scripts, apply the UX guidelines to help text, and design command renames.

CodexClaude Code6 Skills

By dEitY719License: MIT0 GitHub starsUpdated 2 hours ago

Directory evidence

Runtimes
Codex and Claude Code
Parsed components
6 skill or MCP entries
Source updated
Oct 3, 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 authoring for Codex and Claude Code

Installs for the current user
codex plugin marketplace add IchenDEV/agent-plugin-mkt
codex plugin marketplace upgrade agent-plugin-marketplace
codex plugin add authoring@agent-plugin-marketplace

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

Compatibility: the page URL and API slug “authoring-2” remain stable.

  • Codex: authoring-2@agent-plugin-marketplace → authoring@agent-plugin-marketplace

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/dEitY719/authoring-skills

Clone the source repository, then follow its setup instructions to add the plugin to a compatible client. The repository root is the plugin root.

Plugin files

authoring/
├── .codex-plugin/plugin.json
├── .claude-plugin/plugin.json
├── skills/command-rename/SKILL.md
├── skills/sh-check/SKILL.md
├── skills/skill-check/SKILL.md
├── skills/skill-create/SKILL.md
├── skills/skill-refactor/SKILL.md
└── skills/ux-guidelines/SKILL.md

Included Skills6

command-renameskills/command-rename/SKILL.md

Design a command-naming refactor and file the tracking issue(s) — never touch code. Use on /authoring:command-rename, "명령 네이밍 통일 이슈 만들어", "rename this command family". The rename itself runs later via /gh-flow:issue.

sh-checkskills/sh-check/SKILL.md

Audit a shell script (`*.sh`) against 10 PASS/WARN/FAIL/N/A criteria. Use on "check this shell script", "셸 스크립트 점검해줘", "/authoring:sh-check". Do NOT use for SKILL.md (authoring:skill-check) or AGENTS.md (harness:ai-context).

skill-checkskills/skill-check/SKILL.md

Audit a SKILL.md against 18 structure/UX/security/budget checks. Use when the user says "check my skill", "audit my skill", "스킬 점검해줘", "/authoring:skill-check". Do NOT use for AGENTS.md/CLAUDE.md/GEMINI.md — use harness:ai-context instead.

skill-createskills/skill-create/SKILL.md

Create a skill, or improve and evaluate an existing one. Use on "스킬 만들어줘", "make me a skill", "/authoring:skill-create". Authoring — authoring:skill-check audits.

skill-refactorskills/skill-refactor/SKILL.md

Shrink a too-long SKILL.md under 100 lines, moving detail into references/. Use on "refactor my skill", "apply progressive disclosure", "스킬 너무 길어", "/authoring:skill-refactor", or after /authoring:skill-check flags it — that audits, this rewrites.

ux-guidelinesskills/ux-guidelines/SKILL.md

Apply UX_GUIDELINES.md to shell functions and help text — replace raw echo/printf/ANSI with semantic ux_lib calls (ux_header, ux_section, ux_bullet). Use on "/authoring:ux-guidelines", "help 함수 UX 가이드라인대로 리팩터링", or a bulk shell-common UX review.

Plugin manifests2

.codex-plugin/plugin.json
{
  "name": "authoring",
  "version": "0.1.10",
  "description": "Write and audit the things an AI harness reads: create, check, and refactor SKILL.md files, audit shell scripts, apply the UX guidelines to help text, and design command renames.",
  "author": {
    "name": "dEitY719",
    "url": "https://github.com/dEitY719"
  },
  "homepage": "https://github.com/dEitY719/authoring-skills",
  "repository": "https://github.com/dEitY719/authoring-skills",
  "license": "MIT",
  "keywords": [
    "skills",
    "plugin",
    "marketplace",
    "authoring",
    "skill-md",
    "lint",
    "shellcheck"
  ],
  "skills": "./skills/",
  "hooks": {},
  "interface": {
    "displayName": "Authoring",
    "shortDescription": "Author and audit skills, scripts, and command names",
    "longDescription": "Authoring bundles the six skills that keep an agent harness's own source material in shape: skill-create builds a SKILL.md through an interview, draft, and eval loop; skill-check audits one against eighteen structure, UX, security, context-budget, and portability criteria; skill-refactor shrinks an over-long one under 100 lines by extracting references/; sh-check audits a shell script against ten quality criteria; ux-guidelines replaces raw echo/printf/ANSI in shell help text with semantic ux_lib calls; and command-rename designs a naming refactor and files the tracking issue without touching code. Three of them audit, three of them write, and each says which is which before it starts.",
    "developerName": "dEitY719",
    "category": "Developer Tools",
    "capabilities": [
      "Interactive",
      "Read",
      "Write"
    ],
    "defaultPrompt": [
      "Audit this SKILL.md and tell me what fails.",
      "My SKILL.md is over 100 lines - refactor it."
    ],
    "websiteURL": "https://github.com/dEitY719/authoring-skills",
    "brandColor": "#2563EB",
    "screenshots": []
  }
}
.claude-plugin/plugin.json
{
  "name": "authoring",
  "description": "Write and audit the things an AI harness reads: create, check, and refactor SKILL.md files, audit shell scripts, apply the UX guidelines to help text, and design command renames",
  "version": "0.1.10",
  "author": {
    "name": "dEitY719",
    "url": "https://github.com/dEitY719"
  },
  "homepage": "https://github.com/dEitY719/authoring-skills",
  "repository": "https://github.com/dEitY719/authoring-skills",
  "license": "MIT",
  "keywords": [
    "skills",
    "plugin",
    "marketplace",
    "authoring",
    "skill-md",
    "lint",
    "shellcheck"
  ]
}

For maintainers

If you maintain this plugin, link to this source-backed listing from your README so users can review its manifest and indexed components.

[authoring on Agent Plugins Marketplace](https://pluginsmp.com/plugins/authoring-2)