Token导航 LogoToken导航

Agent Skill · 研究检索

nm-scribe-doc-generator(nm 划线文档生成器)

用于辅助文档、README、Markdown、说明文和内容稿件的整理与改写。它适合让 Agent 提炼结构、补齐章节、统一术语、检查链接或把零散材料整理成可读文档。使用时应保留项目已有事实、命令和路径,不要把未确认的信息写成确定结论;涉及对外文案时,还需要控制语气,避免过度营销或夸大能力。

nm-scribe-doc-generator 是研究检索类 Agent Skill,可用宿主为 OpenClaw,通过ClawHub获取,权限为需要联网;许可证为 MIT-0,第三方扫描已通过,按安装量在研究检索类的 73,675 个 Skill 里排第 25,369。

总安装 3,792周安装 158GitHub Stars 公开资料未说明下载 1,264核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
MIT-0
版本
1.0.0

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:nm-scribe-doc-generator(nm 划线文档生成器)
来源仓库:https://github.com/athola/nm-scribe-doc-generator
安装命令:
openclaw skills install nm-scribe-doc-generator
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 OpenClaw 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

ClawHubOpenClaw
openclaw skills install nm-scribe-doc-generator

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

生成具有人类写作风格的技术文档。适合产品手册和开发者指南撰写。保持术语一致性和语气统一性。nm-scribe-doc-generator 属于研究检索类 Skill,可作为该场景下的辅助能力补充。需配置项目术语表和风格指南。适用宿主包括 OpenClaw,接入前应确认版本、权限和运行环境要求。

注意区分事实描述和技术推测。

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 OpenClaw;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 openclaw skills install nm-scribe-doc-generator;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要需要联网,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

nm-scribe-doc-generator 怎么安装?

在终端执行 openclaw skills install nm-scribe-doc-generator。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

nm-scribe-doc-generator 支持哪些 AI 工具?

公开资料标注支持 OpenClaw。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

nm-scribe-doc-generator 需要什么权限?

权限级别是需要联网。该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

nm-scribe-doc-generator 是免费的吗?

来源标注的许可证是 MIT-0。本站不代收任何费用,也不托管安装包;能否商用、要不要署名,以许可证原文为准。

nm-scribe-doc-generator 用的人多吗?

公开数据是累计安装 3,792 次,近一周安装 158 次,下载 1,264 次。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

nm-scribe-doc-generator 安全吗?

第三方扫描结果为通过,但这只覆盖已知的静态检查项,不能替代自己读一遍源码和安装命令。

值得选的地方和要先想清楚的地方

值得选的地方

  • 专注 OpenClaw 一种宿主,触发方式和使用习惯不用来回切换。
  • 许可证明确为 MIT-0,商用和分发边界好判断。
  • 第三方扫描已通过,常见的高风险行为没有命中。

先想清楚的地方

  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 OpenClaw,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。
  • 需要许可证清楚、并且有第三方扫描结果的团队项目。

不太适合

  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
nm-scribe-doc-generator

nm 划线文档生成器 · 本页

3,792—需要联网MIT-0通过

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

name
doc-generator
description
Generate or remediate documentation with human-quality writing and style
version
1.8.2
triggers
metadata
{"openclaw": {"homepage": "https://github.com/athola/claude-night-market/tree/master/plugins/scribe", "emoji": "\�\�", "requires": {"config": ["night-market.scribe:shared", "night-market.scribe:slop-detector"]}}}
source
claude-night-market
source_plugin
scribe
Night Market Skill — ported from claude-night-market/scribe. For the full experience with agents, hooks, and commands, install the Claude Code plugin.

Documentation Generator

Documentation must be grounded in specific claims rather than abstract adjectives. We avoid filler phrases like "In today's fast-paced world" and focus on delivering useful information directly. Each claim should be supported by evidence, such as specific version numbers or request rates, rather than vague descriptors like "comprehensive."

Core Writing Principles

We prioritize authorial perspective and active voice to maintain a consistent team tone. This involves explaining the reasoning behind technical choices, such as selecting one database over another, rather than providing neutral boilerplate. Bullets should be used sparingly for actionable summaries; multi-line bullet waterfalls should be converted to short paragraphs to preserve nuance.

Vocabulary and Style

Avoid business jargon and linguistic tics like mirrored sentence structures or excessive em dashes. We use the imperative mood for docstrings (e.g., "Validate input") and strictly avoid humanizing non-living constructs like code.

Instead ofUse
fallbackdefault, secondary
leverageuse
utilizeuse
facilitatehelp, enable
comprehensivethorough, complete

9. Limit Humanizing Constructs

"Lives under," "speaks to," and similar phrases only make sense for living things.

10. Imperative Mood for Docstrings

"Validate" not "Validates" (per PEP 257, pydocstyle, ruff).

Required TodoWrite Items

  1. doc-generator:scope-defined - Target files and type identified
  2. doc-generator:style-loaded - Style profile applied (if available)
  3. doc-generator:content-drafted - Initial content created
  4. doc-generator:slop-scanned - AI markers checked
  5. doc-generator:quality-verified - Principles checklist passed
  6. doc-generator:user-approved - Final approval received

Mode: Generation

For new documentation:

Step 1: Define Scope

## Generation Request

**Type**: [README/Guide/API docs/Tutorial]
**Audience**: [developers/users/admins]
**Length target**: [~X words or sections]
**Style profile**: [profile name or "default"]

Step 2: Load Style (if available)

If a style profile exists:

cat .scribe/style-profile.yaml

Apply voice, vocabulary, and structural guidelines.

Step 3: Draft Content

Follow the 10 core principles above. For each section:

  1. Start with the essential information
  2. Add context only if it adds value
  3. Use specific examples
  4. Prefer prose over bullets
  5. End when information is complete (no summary padding)

Step 4: Run Slop Detector

Skill(scribe:slop-detector)

Fix any findings before proceeding.

Step 5: Quality Gate

Verify against checklist:

  • [ ] No tier-1 slop words
  • [ ] Em dash count < 3 per 1000 words
  • [ ] Bullet ratio < 40%
  • [ ] All claims grounded with specifics
  • [ ] No formulaic openers or closers
  • [ ] Authorial perspective present
  • [ ] No emojis (unless explicitly requested)

Mode: Remediation

For cleaning up existing content:

Load: @modules/remediation-workflow.md

Step 1: Analyze Current State

# Get slop score
Skill(scribe:slop-detector) --target file.md

Step 2: Section-by-Section Approach

For large files (>200 lines), edit incrementally:

## Section: [Name] (Lines X-Y)

**Current slop score**: X.X
**Issues found**: [list]

**Proposed changes**:
1. [Change 1]
2. [Change 2]

**Before**:
> [current text]

**After**:
> [proposed text]

Proceed? [Y/n/edit]

Step 3: Preserve Intent

Never change WHAT is said, only HOW. If meaning is unclear, ask.

Step 4: Re-verify

After edits, re-run slop-detector to confirm improvement.

Docstring-Specific Rules

When editing code comments:

  1. ONLY modify docstring/comment text
  2. Never change surrounding code
  3. Use imperative mood ("Validate input" not "Validates input")
  4. Brief is better - remove filler
  5. Keep Args/Returns structure if present

Module Reference

  • See modules/generation-guidelines.md for content creation patterns
  • See modules/quality-gates.md for validation criteria

Integration with Other Skills

SkillWhen to Use
slop-detectorAfter drafting, before approval
style-learnerBefore generation to load profile
sanctum:doc-updatesFor broader doc maintenance

Exit Criteria

  • Content created or remediated
  • Slop score < 1.5 (clean rating)
  • Quality gate checklist passed
  • User approval received
  • No emojis present (unless specified)

平台分布

OpenClaw

93.53%
按下载量换算1,182

安全审计

VirusTotal

通过

ClawScan

通过

Static analysis

通过

权限和风险

需要联网

该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills