blog-draft 精选
根据想法和资料撰写博客草稿。适用于用户想写博客、基于研究创建内容,或起草文章的场景。流程会引导你完成调研、头脑风暴、提纲编写和带版本控制的迭代撰写。
安装方式
cp -r zh/03-skills/blog-draft ~/.claude/skills/blog-draft-4把该 skill 目录放进客户端 skills 目录。不同客户端的目录可能不同,Claude Code 默认是 ~/.claude/skills/
https://raw.githubusercontent.com/luongnv89/claude-howto/065ab3734f640fd65ed7a5bb3be882d1d5d52a5a/zh/03-skills/blog-draft/SKILL.md下载后另存为 ~/.claude/skills/blog-draft-4/SKILL.md。链接锁定采集时的 commit,内容与本站展示一致。
整仓一次性获取:git clone --depth 1 https://github.com/luongnv89/claude-howto.git
依赖与权限
- 无需 API Key
- 无需联网
- 依赖外部命令:
git - 以上为按正文与 frontmatter 自动推断的信号,仅供参考;安装前建议先阅读原文。
触发场景
用户想写博客基于研究创建内容或起草文章的场景
SKILL.md 正文
用户输入
$ARGUMENTS
在继续之前,你必须先考虑用户输入。用户应提供:
- 想法/主题:博客文章的核心概念或主题
- 资源:用于研究的 URL、文件或参考资料(可选,但推荐)
- 目标读者:这篇博客是写给谁看的(可选)
- 语气/风格:正式、轻松、技术向等(可选)
重要:如果用户是在请求更新一篇已有博客文章,请跳过步骤 0-8,直接从步骤 9 开始。先阅读现有草稿文件,再继续迭代流程。
执行流程
请按顺序执行以下步骤。不要跳步,也不要在未获得用户批准的情况下继续执行标明需要确认的步骤。
步骤 0:创建项目文件夹
- 使用以下格式生成文件夹名称:
YYYY-MM-DD-short-topic-name
- 使用今天的日期
- 根据主题生成一个简短、适合 URL 的 slug(小写、连字符连接,最多 5 个词)
- 创建文件夹结构:
blog-posts/
└── YYYY-MM-DD-short-topic-name/
└── resources/
- 在继续前,先向用户确认文件夹已创建。
步骤 1:研究与资源收集
- 在博客文章目录中创建
resources/子文件夹
- 对于每个提供的资源:
- URL:抓取关键内容并保存到
resources/下的 markdown 文件中 - 文件:读取并在
resources/中做摘要 - 主题:使用网络搜索收集最新信息
- 为每个资源在
resources/中创建摘要文件:
resources/source-1-[short-name].mdresources/source-2-[short-name].md- 以此类推
- 每个摘要都应包含:
# 来源:[标题/URL]
## 要点
- 要点 1
- 要点 2
## 相关引文/数据
- 引文或统计 1
- 引文或统计 2
## 与主题的关联
简要说明其相关性
- 向用户展示研究摘要。
步骤 2:头脑风暴与澄清
- 基于想法和已研究的资源,展示:
- 从研究中识别出的主要主题
- 博客文章的可能切入角度
- 应该覆盖的关键点
- 仍需进一步澄清的信息缺口
- 提出澄清问题:
- 你希望读者最终带走的核心结论是什么?
- 研究中有没有哪些点是你希望重点强调的?
- 目标长度是多少?(短:500-800 字,中:1000-1500 字,长:2000+ 字)
- 有没有哪些内容你希望排除?
- 在继续之前,等待用户回复。
步骤 3:提出提纲
- 创建一个结构化提纲,包括:
# 博客文章提纲:[标题]
## 元信息
- **目标读者**:[谁]
- **语气**:[风格]
- **目标长度**:[字数]
- **核心结论**:[关键信息]
## 建议结构
### 开场/引子
- 开场钩子思路
- 背景铺垫
- 论点陈述
### 第一部分:[标题]
- 关键点 A
- 关键点 B
- 来自 [来源] 的支撑证据
### 第二部分:[标题]
- 关键点 A
- 关键点 B
[继续列出所有部分...]
### 结论
- 关键点总结
- 行动号召或最终思考
## 需要引用的来源
- 来源 1
- 来源 2
- 向用户展示提纲,并请求批准或修改意见。
步骤 4:保存已批准的提纲
- 用户批准提纲后,将其保存为博客文章文件夹中的
OUTLINE.md。
- 确认提纲已保存。
步骤 5:提交提纲(如果在 git 仓库中)
- 检查当前目录是否为 git 仓库。
- 如果是:
- 暂存新文件:博客文章文件夹、resources 和
OUTLINE.md - 使用如下提交信息创建 commit:
docs: Add outline for blog post - [topic-name] - 推送到远程仓库
- 如果不是 git 仓库,则跳过此步骤并告知用户。
步骤 6:撰写草稿
- 基于已批准的提纲,撰写完整博客草稿。
- 严格按照
OUTLINE.md的结构进行编写。
- 包含:
- 有吸引力的引言和开场钩子
- 清晰的章节标题
- 来自研究的支撑证据和示例
- 段落之间自然流畅的过渡
- 强有力的结尾和核心收获
- 引用:所有比较、统计数据和事实性陈述都必须引用原始来源
- 将草稿保存为博客文章文件夹中的
draft-v0.1.md。
- 格式:
# [博客文章标题]
*[可选:副标题或标语]*
[包含行内引用的完整正文...]
---
## 参考资料
- [1] 来源 1 标题 - URL 或引用
- [2] 来源 2 标题 - URL 或引用
- [3] 来源 3 标题 - URL 或引用
- 引用要求:
- 每个数据点、统计信息或比较都必须带有行内引用
- 使用编号引用 [1]、[2] 等,或命名引用 [Source Name]
- 在文末的参考资料部分链接这些引用
- 示例:“研究表明,65% 的开发者更偏好 TypeScript [1]”
- 示例:“React 在渲染速度上比 Vue 快 20% [React Benchmarks 2024]”
步骤 7:提交草稿(如果在 git 仓库中)
- 检查是否处于 git 仓库中。
- 如果是:
- 暂存草稿文件
- 使用如下提交信息创建 commit:
docs: Add draft v0.1 for blog post - [topic-name] - 推送到远程仓库
- 如果不是 git 仓库,则跳过并告知用户。
步骤 8:向用户展示草稿以供审阅
- 向用户展示草稿内容。
- 询问反馈:
- 整体印象如何?
- 哪些部分需要扩展或压缩?
- 是否需要调整语气?
- 是否缺少关键信息?
- 有没有具体编辑或重写建议?
- 等待用户回复。
步骤 9:迭代或定稿
如果用户要求修改:
- 记录所有修改请求
- 返回步骤 6,并做以下调整:
- 将版本号递增(v0.2、v0.3 等)
- 纳入所有反馈
- 保存为
draft-v[X.Y].md - 重复步骤 7-8
如果用户批准:
- 确认最终草稿版本
- 如用户要求,可重命名为
final.md - 总结博客文章创建过程:
- 一共创建了多少个版本
- 各版本之间的关键变化
- 最终字数
- 创建了哪些文件
版本跟踪
所有草稿都会以递增版本号保留:
draft-v0.1.md- 初始草稿draft-v0.2.md- 第一轮反馈后draft-v0.3.md- 第二轮反馈后- 以此类推
这可以跟踪博客文章的演变过程,并在需要时回退。
输出文件结构
blog-posts/
└── YYYY-MM-DD-topic-name/
├── resources/
│ ├── source-1-name.md
│ ├── source-2-name.md
│ └── ...
├── OUTLINE.md
├── draft-v0.1.md
├── draft-v0.2.md(如果有迭代)
└── draft-v0.3.md(如果还有更多迭代)
质量建议
- 钩子:以问题、令人惊讶的事实或贴近读者的场景开头
- 衔接:每一段都要自然连接到下一段
- 证据:用研究数据支撑观点
- 引用:以下内容务必引用来源:
- 所有统计数据和数值(例如:“根据 [Source],75% 的……”)
- 对产品、服务或方案的比较(例如:“X 的速度比 Y 快 2 倍 [Source]”)
- 关于市场趋势、研究发现或基准测试的事实性陈述
- 使用行内引用,格式为:[Source Name] 或 [Author, Year]
- 语气:全程保持一致
- 长度:尊重目标字数
- 可读性:使用短段落,并在适当位置使用项目符号
- CTA:以明确的行动号召或发人深省的问题收尾
备注
- 始终在上述需要确认的节点等待用户批准
- 保留所有草稿版本,方便追踪历史
- 如果提供了 URL,使用网络搜索获取最新信息
- 如果资源不足,询问用户补充,或建议进一步研究
- 根据目标读者调整语气(技术、通用、商业等)
质量与来源
- 所属仓库
- luongnv89/claude-howto
- 仓库星标
- 4.2 万
- 最近更新
- 昨天
- 采集时间
- 今天
- commit
- 065ab3734f64
- 内容指纹
- sha256:cfd6cdf888d65e4
- 文件路径
- zh/03-skills/blog-draft/SKILL.md
同仓库其它 Skill
查看全部 25 个lesson-quiz
Test a learner on a single Claude Code tutorial lesson (01-10) with 10 questions, scoring answers and flagging weak spots. Use before, during, or after a lesson. Don't use for whole-tutorial assessment or explaining a topic instead of testing it.
self-assessment
Comprehensive Claude Code self-assessment and learning path advisor. Runs a multi-category quiz covering 10 feature areas, produces a detailed skill profile with per-topic scores, identifies specific gaps, and generates a personalized learning path with prioritized next steps. Use when asked to "assess my level", "take the quiz", "find my level", "where should I start", "what should I learn next", "check my skills", "skill check", or "level up".
blog-draft
Draft a blog post from ideas and resources. Use when users want to write a blog post, create content from research, or draft articles. Guides through research, brainstorming, outlining, and iterative drafting with version control.
brand-voice
Ensure all communication matches brand voice and tone guidelines. Use when creating marketing copy, customer communications, public-facing content, or when users mention brand voice, tone, or writing style.
claude-md
Create or update CLAUDE.md files following best practices for optimal AI agent onboarding
code-review-specialist
Comprehensive code review with security, performance, and quality analysis. Use when users ask to review code, analyze code quality, evaluate pull requests, or mention code review, security analysis, or performance optimization.
相似 Skill
更多「写作」interview-prep
Prepares the user for a specific interview from their real experience. Builds a story bank in Situation/Task/Action/Result/Reflection form mapped to the competencies the role and company test (such as Amazon's Leadership Principles), writes a cited company and role brief from public sources, predicts questions per round, drafts opener, why-us, weakness and salary answers, prepares questions to ask and a logistics checklist, and runs a post-interview debrief. Use when the user says "help me prepare for my interview", "I have an interview tomorrow" or "in 2 hours", "build my story bank", "STAR stories", "interviewing as a career changer", "what will they ask me", "how do I answer tell me about yourself", "questions to ask the interviewer", "research the company" or "debrief my interview". Uses Reactive Resume MCP tools when connected. For scored role-play practice, mock-interview; for thank-you notes and tracking, job-application-manager; for a salary number, offers or negotiation, offer-negotiation.
job-application-manager
Runs the job-search pipeline. Adds jobs from a link or pasted posting, keeps stages and dates accurate, sets follow-ups, runs a weekly review (stale applications, next actions, funnel stats), records the exact resume version sent, and drafts networking, LinkedIn, referral, recruiter-reply, follow-up, thank-you, status-check, expedite and withdrawal messages without sending them. Use when the user says "add this job to my tracker", "I applied", "log my interview", "I got rejected", "I was ghosted", "log my offer", "track my applications", "do my weekly review", "what should I follow up on", "write a thank-you note", "message this recruiter", "ask for a referral", "withdraw my application", or wants a job-search spreadsheet. Works with a Markdown/CSV tracker or Reactive Resume MCP tools. Not for resume work (resume-tailor, resume-bullet-writer, resume-content-guide), interview prep or practice (interview-prep, mock-interview), or judging, negotiating, accepting or declining an offer (offer-negotiation).
mock-interview
Runs a mock interview for a specific job description. Plays the interviewer in a chosen round (recruiter screen, hiring manager, behavioral, coding, system design, case, product sense, panel), persona and difficulty; asks one question at a time, probes vague answers, and gives quote-backed rubric scores after each answer (coach mode) or at the end (realistic). Model answers use only the user's real experience. Use when the user says "mock interview me", "interview me for this job", "practice interview", "pretend you're the interviewer", "grill me for this role", "run a behavioral round", "quick recruiter screen", "hiring-manager mock", "system design mock" or "case interview practice". With Reactive Resume MCP it reads the application and stories and logs the session. For a story bank, company brief, questions to ask or a real-interview debrief, interview-prep; for scheduling or thank-you notes, job-application-manager; for fixing the resume, resume-tailor; for negotiation practice, offer-negotiation.
offer-negotiation
Evaluates and negotiates job offers. Decodes base, bonus, equity, sign-on, level and terms with unknowns kept unknown and each offer in its own currency, benchmarks against checkable pay data, finds true leverage, drafts one counter as email and call script, role-plays the recruiter, and handles the salary-expectations number, deadlines and extensions, "best and final", competing offers, counteroffers and written acceptance or decline. Country-aware (India CTC, 13th-month pay, public-sector scales). Use when the user says "I got an offer of...", "is this offer good", "should I negotiate", "how do I counter", "compare my offers", "what is my equity worth", "they asked my salary expectations", "they want an answer by Friday", "can I ask for more time", "should I accept" or "practice the negotiation call". Uses Reactive Resume MCP tools when connected. For logging the offer, its deadline and withdrawal notes, job-application-manager; for other interview answers, interview-prep.
resume-builder
Builds a complete resume from scratch as Reactive Resume JSON that conforms to the schema and imports at https://rxresu.me. Asks for each missing detail instead of inventing it, then produces valid JSON (UUIDs, HTML descriptions, template and layout). Use when the user wants to create, build or generate a new resume, turn their work history into Reactive Resume JSON, or asks about the Reactive Resume schema, sections, templates or layout. For what belongs on a resume or a resume audit use resume-content-guide; for rewriting bullets, resume-bullet-writer; for fitting one job posting, resume-tailor; for tracking applications, job-application-manager; for interviews, interview-prep or mock-interview.
resume-bullet-writer
Turns resume duties into truthful impact bullets. Questions the user role by role to dig out achievements, asks for real numbers or honest ranges (never invents them), and writes concise bullets in XYZ, CAR, scope or qualitative form. Use when the user says "rewrite my bullets", "make this bullet stronger", "quantify my resume", "turn my duties into achievements", "improve my experience section", "my resume sounds boring", "I don't have any numbers", pastes resume lines for feedback, or works in a low-number job (nursing, teaching, care, trades, admin, creative). With the Reactive Resume MCP server connected, it edits experience, project, volunteer and education descriptions with apply_resume_patch after the user approves. Use resume-content-guide instead for which sections or details belong and for summaries or headlines, resume-tailor to fit one job posting, interview-prep or mock-interview for interview stories and practice, and resume-builder to build a resume from scratch.