菜单
Create or update Memoh workspace skills under /data/skills, including SKILL.md, scripts, references, assets, and validation. Use when the user asks to create, scaffold, revise, audit, or explain a workspace skill.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Configure Memoh hooks in /data/.memoh/hooks.json, including events, matchers, command/tool actions, decisions, on_error behavior, append_context, and validation. Use when the user asks to inspect, create, update, debug, or explain workspace hooks.
Memoh 统一错误处理架构（apperror + Problem Details + SSE envelope + 前端稳定 code 解析）。 新增任何面向用户的后端错误、或前端需要根据错误做业务分支时，必须先读本 skill。 核心约束：业务判断只依赖稳定 code，用户文案由前端按语言本地化，私有诊断永不进入响应。
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, passive voice, negative parallelisms, and filler phrases.
去除文本中的 AI 生成痕迹。适用于编辑或审阅文本，使其听起来更自然、更像人类书写。 基于维基百科的"AI 写作特征"综合指南。检测并修复以下模式：夸大的象征意义、 宣传性语言、以 -ing 结尾的肤浅分析、模糊的归因、破折号过度使用、三段式法则、 AI 词汇、否定式排比、过多的连接性短语。
Assist with development in the Twilight AI Go SDK. Use when working in this repository, adding or updating providers, embeddings, tool calling, streaming, examples, or docs for Twilight AI.
| name | skill-creator |
| description | Create or update Memoh workspace skills under /data/skills, including SKILL.md, scripts, references, assets, and validation. Use when the user asks to create, scaffold, revise, audit, or explain a workspace skill. |
Use this skill to create or maintain Memoh workspace skills.
/data/skills/<skill-name>/SKILL.md./data/.memoh/skills as Memoh-managed built-in skill space. Do not create user skills there unless the user explicitly asks to maintain built-in templates.docs-publisher or gh-review-helper.references/skill-files.md before designing resource folders, scripts, references, or assets.python3 /data/.memoh/skills/skill-creator/scripts/init_skill.py my-skill --path /data/skills --resources scripts,references
SKILL.md and add only the resource files that directly support the skill.python3 /data/.memoh/skills/skill-creator/scripts/quick_validate.py /data/skills/my-skill
Every skill must have:
---
name: skill-name
description: Clear trigger-focused description of what the skill does and when to use it.
---
# Skill Name
Actionable instructions for the agent.
Common optional files:
scripts/: deterministic helpers the agent can run with python3 or bash.references/: detailed docs loaded only when needed.assets/: templates, images, fonts, or boilerplate copied into outputs.SKILL.md concise and move detailed schemas or long examples into references/.