菜单
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.
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。
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.
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.
基于 SOC 职业分类
| name | hooks-setup |
| description | 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. |
Use this skill when the user wants to inspect, create, update, debug, or explain Memoh hooks.
/data/.memoh/hooks.json.references/reference.md.Read references/reference.md before adding anything beyond an empty config or a simple logging hook.
If /data/.memoh/hooks.json is missing, create:
{
"version": 1,
"enabled": true,
"hooks": []
}
/data/.memoh/hooks.json.on_error: "ignore".on_error: "block" only for guardrail hooks that should deny on failure.{
"version": 1,
"enabled": true,
"defaults": {
"timeout": "10s",
"on_error": "fail",
"max_output_bytes": 65536,
"trigger_nested_hooks": false
},
"env": {},
"hooks": [
{
"name": "log workspace commands",
"event": "AfterWorkspaceCommand",
"enabled": true,
"priority": 10,
"matcher": ".*",
"actions": [
{
"type": "command",
"command": "mkdir -p .memoh && cat >> .memoh/hooks.log",
"on_error": "ignore"
}
]
}
]
}
Command and tool actions may return:
{
"decision": "allow",
"reason": "optional explanation",
"append_context": "optional context"
}
Allowed decisions are allow, deny, ask_approval, and append_context.
For full examples and the complete event catalog, read references/reference.md.