Token导航 LogoToken导航

Agent Skill · 研究检索

longform-blog-writer(长篇博客作者)

longform-blog-writer 用于查找、检索和筛选相关信息,适合在 OpenClaw 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

longform-blog-writer 是研究检索类 Agent Skill,可用宿主为 OpenClaw,通过ClawHub获取,权限为只读;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 34,885。

总安装 2,165周安装 93GitHub Stars 公开资料未说明下载 759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
1.1.0

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:longform-blog-writer(长篇博客作者)
来源仓库:https://github.com/onlybelter/longform-blog-writer
安装命令:
openclaw skills install longform-blog-writer
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 longform-blog-writer

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。

longform-blog-writer 撰写结构严谨、批评平衡的长篇博客文章。适合在 OpenClaw 中起草新闻稿或深度报道时使用。通过 clawhub 安装并使用 openclaw skills install longform-blog-writer 命令部署。使用前需明确主题范围与事实核查要求。

适用宿主包括 OpenClaw,接入前应确认版本、权限和运行环境要求。

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 longform-blog-writer;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

    它标注为只读,先用只读任务试一次,确认行为符合预期再扩大使用范围。

常见问题

6 条

longform-blog-writer 怎么安装?

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

longform-blog-writer 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。

longform-blog-writer 需要什么权限?

权限级别是只读。该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

longform-blog-writer 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。

longform-blog-writer 用的人多吗?

公开数据是累计安装 2,165 次,近一周安装 93 次,下载 759 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。

longform-blog-writer 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。
  • 标注为只读权限,试用阶段不容易误改本地文件。

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
longform-blog-writer

长篇博客作者 · 本页

2,165—只读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
longform-blog-writer
description
Writes publication-ready longform blog posts with strong structure, accurate definitions, and balanced critique. Use when user asks to draft an article/newsletter/essay, or wants a deep, polished blog post (not a quick answer).

Longform Blog Writer

Write a longform blog post that is coherent, well-structured, and intellectually honest. Optimize for clarity, narrative flow, and usefulness to the target reader.

Language: Respond in the same language the user writes in. If mixed, default to English.


When to Use

Use this skill when the user asks to:

  • write a blog post / longform article / newsletter / essay
  • turn notes into a publishable post
  • produce a structured, high-quality draft with sections, examples, and references

Do not use this skill when the user only wants a short explanation or a one-paragraph summary.


Workflow

Step 1: Intake (ask in one message)

Ask for:

  1. Topic + angle (what is the main claim or question?)
  2. Target reader (beginner / practitioner / researcher / general public)
  3. Tone (neutral / opinionated / playful / academic-lite)
  4. Desired length (short / standard / long)
  5. Any constraints (company blog style, SEO keywords, “no hype”, etc.)
  6. Sources (links, papers, docs) and what must be cited

If the user does not specify, assume: practitioner audience, neutral tone, standard length.

Step 2: Propose an outline

Return a tight outline first. Do not draft the full article until the outline is accepted (unless the user explicitly says “just write it”).

Step 3: Draft (longform)

Write the full article following the structure below. Use short paragraphs, clear headings, and concrete examples.

Step 4: Revise

Do one editing pass with:

  • clearer topic sentences per section
  • removal of filler
  • consistency of terminology
  • stronger transitions between sections

Article Structure (default)

Always use this backbone unless the user requests a different format:

  1. Title
  2. Hook (why care?)
  3. Context / background
  4. Core idea (the main claim)
  5. Deep dive (how it works / why it’s true)
  6. Trade-offs / limitations / failure cases
  7. Practical takeaways (what to do next)
  8. References / further reading
  9. Optional: Glossary (for long or technical posts)

Types (choose one)

Pick the best type based on the topic; if unclear, ask the user to choose:

  1. Technical tutorial (programming / tooling)
  2. Research explainer (paper walkthrough or field overview)
  3. Math concept (conceptual + minimal essential equations)
  4. Book review (critical and comparative)
  5. Science communication (non-specialist, no hype)

Type-specific requirements

Technical tutorial

  • Include runnable code snippets.
  • Include a “Best practices” section and an “Anti-patterns” section.

Research explainer

  • Clearly separate: established consensus vs. open questions vs. debate.
  • Cite primary sources; do not invent citations.

Math concept

  • Explain intuition first, then introduce equations sparingly.
  • Define symbols and interpret every equation in plain language.

Book review

  • Include strengths + weaknesses, and compare to at least 2 related works.

Science communication

  • Explain like to an intelligent non-specialist.
  • Prefer analogies and visual descriptions; minimize formulas.

Concept Decoder Integration

Invoke the concept-decoder skill when:

  • a key concept needs more than two sentences to define well
  • the concept is central and non-trivial
  • the target reader is non-specialist and the term would be opaque

Embed the result as a short “Concept Spotlight” block, then continue the article.


Citations and Factuality

  • Do not fabricate names, dates, statistics, or citations.
  • If a claim is uncertain or contested, label it clearly.
  • Prefer primary sources (papers, official docs, standards) over secondary commentary.
  • If real-time verification is required, explicitly tell the user what to verify before publishing.

Input/Output

Input

  • Topic + optional notes, audience, tone, and desired length.
  • Optional: source links or documents to cite.

Output

  • A publishable blog post in Markdown, following the selected type requirements.
  • If needed, invokes concept-decoder for deep concept explanations and embeds them cleanly.

平台分布

OpenClaw

92.8%
按下载量换算704

安全审计

VirusTotal

通过

ClawScan

通过

Static analysis

通过

权限和风险

只读

该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

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