openai-marketplace-maintainer
Use when adding, reviewing, or fixing Codex skills, plugins, custom subagents, marketplace entries, or registry metadata under this OpenAI marketplace folder.
- License 许可
- MIT
- 最近更新
- 2026-11-01
- Stars
- ★ 0
- Forks
- 0
01 前言 Front Matter
- name
- openai-marketplace-maintainer
- description
- Use when adding, reviewing, or fixing Codex skills, plugins, custom subagents, marketplace entries, or registry metadata under this OpenAI marketplace folder.
03 SKILL.md 正文
OpenAI Marketplace Maintainer
Use this skill when the user asks to create, update, review, or publish Codex artifacts in this folder.
Workflow
- Read
AGENTS.mdin this folder first. - Identify the artifact type:
- standalone skill under
skills/ - plugin under
plugins/ - custom subagent template or active agent
- marketplace metadata under
.agents/plugins/marketplace.json - registry metadata under
registry/
- standalone skill under
- Start from the matching template in
templates/. - Keep names kebab-case for folders and plugin names.
- Keep skill names concise and descriptions trigger-focused.
- Do not create marketplace entries for missing plugin folders.
- Do not activate custom subagents under
.codex/agents/unless explicitly asked. - Check official OpenAI Codex docs when plugin, skill, agent, or marketplace behavior is uncertain.
Validation checklist
plugins/{name}/.codex-plugin/plugin.jsonexists for every plugin marketplace entry.- Marketplace entry
namematches plugin manifestname. - Marketplace entry
source.pathis relative to this folder and points to./plugins/{name}. - Marketplace entry includes
policy.installation,policy.authentication, andcategory. - Each skill has
SKILL.mdwithnameanddescriptionfrontmatter. - No secrets, tokens, or machine-local absolute paths are committed.
04 同仓库更多 Skills
todo-skill-name
TODO describe exactly when Codex should use this skill and when it should not.
example-skill
TODO replace this with the plugin skill trigger.
rlm
Use when the user explicitly says "use RLM" or a task needs long-context recursive decomposition across many files, logs, transcripts, corpora, PDFs, or documents. Do not use for narrow edits, small single-file analysis, ordinary repo search, or tasks with no external context.
My Skill Name
One sentence describing what this skill does and when to invoke it.
rlm
Use when a task involves long context, many files, PDFs, logs, transcripts, URLs, corpora, or anything requiring recursive decomposition over external context that won't fit comfortably in a single prompt. NOT for ordinary small edits, short Q&A, or single-file inspection.
rlm-eval
Local-only evaluator for rlm-auto routing decisions. Invoke on /rlm-auto:status, when the user asks about router accuracy or false positives, or when they want the dogfood report. Never sends data off the machine.