Agent skill

Nextclaw Product Blog Storytelling

by Peiiii in Peiiii/nextclaw

当为 NextClaw 及关联产品写博客、官网短文、发布叙事、功能优势、社区稿或配图 brief,并需要把用户兴趣、愿景与证据收敛成可信公开内容时使用。

MITAuto-check passedWriting & Content

Install Nextclaw Product Blog Storytelling

skills CLI
$ npx skills add Peiiii/nextclaw --skill nextclaw-product-blog-storytelling -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install Peiiii/nextclaw nextclaw-product-blog-storytelling --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/Peiiii/nextclaw.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/nextclaw-product-blog-storytelling .claude/skills/nextclaw-product-blog-storytelling && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
nextclaw-product-blog-storytelling
GitHub stars
260
Token cost
~781 tokens
SKILL.md length
104 words
Files
1
Skills in repo
70
Repo updated
First seen
Licence
MIT

At a glance

当为 NextClaw 及关联产品写博客、官网短文、发布叙事、功能优势、社区稿或配图 brief,并需要把用户兴趣、愿景与证据收敛成可信公开内容时使用。

  • Works in 8 steps: 对齐… → 从代码、文档、真实… → 先选传播目标:发布关联的功能与优化使用结果营销短稿;状态报告使用结果摘要;只有用户… → …
  • Tasks that involve Storytelling
  • SKILL.md covers 候选与提前成稿, 写作流程, 状态报告结构 and 配图选择, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Nextclaw Product Blog Storytelling is an agent skill from Peiiii/nextclaw. 当为 NextClaw 及关联产品写博客、官网短文、发布叙事、功能优势、社区稿或配图 brief,并需要把用户兴趣、愿景与证据收敛成可信公开内容时使用。

Its SKILL.md is about 780 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Writing & Content, covering Storytelling. The repository describes itself as: A human-centered long-term AI partner—not a task-centered assistant. The licence is MIT.

When your agent uses it

  • Tasks that involve Storytelling

Example prompts

  • “/nextclaw-product-blog-storytelling”

Workflow steps

8 steps, taken from the first numbered list in SKILL.md.

  1. 对齐 docs/VISION.md,明确主题服务统一入口、能力编排、自感知、自治、自进化或生态扩展中的哪一点。
  2. 从代码、文档、真实 UI、事件链路、发布记录或用户反馈找证据。证据不足的内容写成方向,不写成已完成事实。
  3. 先选传播目标:发布关联的功能与优化使用结果营销短稿;状态报告使用结果摘要;只有用户明确要求时才写观点、科普或长篇故事。
  4. 用一句话冻结核心事实,再写它支撑的具体用户任务;模型接入、安装 skill、连接渠道等能力入口本身不是用户任务。
  5. 比较竞品前固定产品与版本,使用官方一手资料建立 能力 | NextClaw | 对方 | 结论。对方同样具备的能力不能继续称独有优势;文档未提及也不能断言不存在。
  6. 区分“自身已有能力、产品重要特点、相对差异”,再核对控制边界、执行层、生命周期、组合方式和成熟度。
  7. 写明能力边界和下一步,不把底座、方向或概念图包装成现成功能。
  8. 公开正文由 Wiki 中的用户内容边界约束;分类过程、模板解释和取舍理由留在协作材料,不进入发布稿。

What it can do on your machine

Read from SKILL.md and the folder at commit 4d9d500. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Nextclaw Product Blog Storytelling loads about 781 tokens when it runs. Until then it costs about 28 tokens; SKILL.md has 104 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~28
When it runs · the whole SKILL.md, loaded when a task matches
~781

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from Peiiii/nextclaw at commit 4d9d500, republished under its MIT licence (© Peiiii). 104 words, ~781 tokens.

Download SKILL.mdSave it as .claude/skills/nextclaw-product-blog-storytelling/SKILL.md (or your agent's skills folder).
name
nextclaw-product-blog-storytelling
description
当为 NextClaw 及关联产品写博客、官网短文、发布叙事、功能优势、社区稿或配图 brief,并需要把用户兴趣、愿景与证据收敛成可信公开内容时使用。

产品博客叙事

候选与提前成稿

博客不必等到版本发布后才开始。用户明确要求写作,或 Delivery 判断一个已验证结果具备独立用户任务、可核查证据和公开叙事价值时,进入本 skill;changeset 本身不自动等于博客候选。

按事实成熟度选择一个状态:

  • 证据或产品边界尚未稳定:只报告候选主题和缺失证据,不创建正文;
  • 实现、Validation 与 Review 已稳定:可提前写入 docs/blog-drafts/YYYY-MM-DD-<topic>.blog-draft.md;
  • 获得正式发布授权:按实际发布日期迁入 apps/docs/zh/blog 与 apps/docs/en/blog,并同步 index、sidebar 和适用链接。

内部草稿不参与站点构建,也不代表文章已发布。草稿正文只保留未来读者需要看到的内容;候选判断、私有路径、测试会话 ID、发布步骤和内部取舍留在设计、迭代记录或协作回复中。实现或测量环境在成稿后变化时,发布前重新核对全部事实与指标。

需要随产品 changeset 一起发布时,草稿 frontmatter 写入 releaseBlogTarget: next-stable、releaseBlogChangeset 和 releaseBlogState: draft,changeset 使用 <!-- release-note-blog: docs/blog-drafts/<file>.blog-draft.md --> 绑定。发布准备时生成中英文正式文章、更新 index/sidebar,并把草稿状态改为 ready、补充 releaseBlogZhPath 与 releaseBlogEnPath。NPM 达到 NPM_READY 后,产品发布闭环会阻断仍处于 draft 或缺少正式入口的绑定文章;线上验证完成后再删除内部草稿。

发布关联的功能、优化和结果博客默认采用短篇结果营销稿:标题先写产品、成果和最强可核查数字,首屏直接回答“做成了什么、效果如何”;实现原理只保留理解结果所需的最少内容。只有用户明确要技术复盘、原理说明或产品判断时,才展开为科普或长文。标题可以强,但不能超出测量范围或把开发版本写成已发布。

写作流程

宣传内容的有效吸引门

官网、广告式短文与品牌故事先判断题材是否值得表达,再润色。目标是在有限注意力内,让尽可能多的潜在用户理解与自己有关的真实价值,产生进一步了解或尝试的意愿;不是平均好感、信息量或无关点击。此门不强加给技术说明与状态报告。

  • 先冻结一句“哪些潜在用户共同在意什么→产品如何回应→用什么可核查细节证明→希望他下一步做什么”。群体不同先找共同处境,不堆场景列表,也不把单一故事当成整个产品。
  • 场景选择须对应用户明确的目标受众或可说明的需求假设;不能因为亲情等题材容易写就认定有代表性。受众假设被用户否定时先退场该题材,不继续用通用标题包装原故事;年龄本身不证明某个需求普遍。
  • 对候选问:去掉亲情、猎奇和氛围,产品价值还在吗?换掉产品名字后是否仍是空泛好话?结果配得上承诺吗?访客能记住哪一个具体变化?可迁移到竞品不等于没价值,但不能冒称独有。
  • 文字、视觉与动作共享一条因果链;交互应帮助理解、证明协作或兑现结果,不能靠多点几次消耗注意力。先给最重要的意思,证据按需展开。
  • 概念、示例和未上线能力必须可辨识;不靠虚构事实、夸大自主程度或与产品无关的情绪吸引。不能把完整、流畅、漂亮当成有效吸引的证据。
  • 无真实用户数据时,只给出可反驳的吸引假设与AI审查结论。后续用同条件的少量目标用户比较“以为它是什么、记住什么、为何愿意继续”,再观察适用的真实行为;不伪造覆盖率或转换提升。题材本身无力时允许放弃,不继续包装。
  1. 对齐 docs/VISION.md,明确主题服务统一入口、能力编排、自感知、自治、自进化或生态扩展中的哪一点。 对长期个人搭档及关联产品,先检查是否表达了对同一个人的持续理解:任务只是上下文的一部分,项目、想法、学习、资讯和长短期规划之间的有意义联系也能构成证据。不能把单任务高效交付直接等同于全部定位;思考、讨论与调整理解不必强行收束到执行成果。
  2. 从代码、文档、真实 UI、事件链路、发布记录或用户反馈找证据。证据不足的内容写成方向,不写成已完成事实。
  3. 先选传播目标:发布关联的功能与优化使用结果营销短稿;状态报告使用结果摘要;只有用户明确要求时才写观点、科普或长篇故事。
  4. 用一句话冻结核心事实,再写它支撑的具体用户任务;模型接入、安装 skill、连接渠道等能力入口本身不是用户任务。
  5. 比较竞品前固定产品与版本,使用官方一手资料建立 能力 | NextClaw | 对方 | 结论。对方同样具备的能力不能继续称独有优势;文档未提及也不能断言不存在。
  6. 区分“自身已有能力、产品重要特点、相对差异”,再核对控制边界、执行层、生命周期、组合方式和成熟度。
  7. 写明能力边界和下一步,不把底座、方向或概念图包装成现成功能。
  8. 公开正文由 Wiki 中的用户内容边界约束;分类过程、模板解释和取舍理由留在协作材料,不进入发布稿。

状态报告结构

下列结构只用于状态报告/事实摘要;官网与品牌宣传按有效吸引门组织,不默认使用报告模板。

md
## 摘要

一句话结论 + 3-5 条可核查事实。

## 当前结果

用表格列能力、状态和用户可见结果。

## 能力边界

列尚未完成的范围。

## 下一步

列 2-3 个后续方向。

正文短、硬、可核查;多用“当前、已具备、未完成、下一步”,少用情绪转场、排比和“大 V”腔。事实说明可在此基础上扩写;只有用户明确要观点、传播稿或发布故事时,才增加问题、判断、取舍和用户使用路径。

配图选择

先写一句“图片必须让用户看懂什么”,再比较至少 2-3 种形式:

  • 真实/标注截图:已上线能力的首选,可信度最高;
  • 概念化产品图:跨多界面或尚在产品化的能力,必须明确是概念表达;
  • 信息图/流程故事板:结构判断、对比、before/after 和用户旅程;
  • 抽象氛围图:默认不选,不能替代产品证据。

功能跨多个界面时,截图覆盖真正承担说明责任的入口、管理面和结果面,不能用结果图替代完整链路。可信度和传播性冲突时,以截图作正文证据、概念图作 hero。

配图后自评:视觉焦点是否命中核心亮点;是否有任务、状态、进度、工具或统一工作台等证据元素;去掉标题后能否猜到主题;是否退化为机器人、科幻光效或泛 AI 氛围。未命中就改 brief 或重做。

质量门

文章必须有具体用户任务、证据锚点、明确判断和能力边界;普通用户能读懂,技术用户能核查。禁止“革命性、颠覆性、前所未有”、万能产品叙事、纯 changelog 和无证据优势宣称。

© Peiiii, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .agents/skills/nextclaw-product-blog-storytelling of Peiiii/nextclaw.

Open the folder on GitHubat commit 4d9d500

Compare with similar skills

Nextclaw Product Blog Storytelling next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Nextclaw Product Blog Storytelling compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Nextclaw Product Blog Storytelling this skillPeiiii/nextclaw260—~781Automated safety check: PassMIT
Data Storytellingynulihao/AgentSkillOS61815 repos~2.8kAutomated safety check: PassNone
Chinese Novel Writing Systemleenbj/novel-creator-skill671—~3.9kAutomated safety check: PassNone
Chinese Novelist Chapter WriterPenglongHuang/chinese-novelist-skill3.3k—~491Automated safety check: WarnMIT
Liu Run Style Business Column Writerliangdabiao/liurun-bookwriter-skills277—~1.8kAutomated safety check: PassMIT
Business Insight Essay Writerliangdabiao/liurun-bookwriter-skills277—~2.5kAutomated safety check: PassMIT

Similar skills

  • Data Storytelling

    ynulihao/AgentSkillOS

    Transform data into compelling narratives using visualization, context, and persuasive structure.

    618 GitHub starsUsed in 15 repos~2.8k tokens
    Writing & ContentAuto-check passed
  • Chinese Novel Writing System

    leenbj/novel-creator-skill

    Guides long-form Chinese novel writing from a rough idea through outlines, chapter drafts and quality gates, with file-based memory for a story meant to reach 300万字.

    671 GitHub stars~3.9k tokensUpdated 7 mo ago
    Writing & ContentAuto-check passed
  • Chinese Novelist Chapter Writer

    PenglongHuang/chinese-novelist-skill

    Writes long Chinese novels chapter by chapter through guided questions, outlining, drafting with cliffhangers and automatic validation, with resumable projects.

    3.3k GitHub stars~491 tokensUpdated 5 days ago
    Writing & ContentAuto-check: warnings
  • Liu Run Style Business Column Writer

    liangdabiao/liurun-bookwriter-skills

    Writes long-form Chinese business commentary in Liu Run's voice, using his eight writing principles, three structures, and SCQA logic patterns.

    277 GitHub stars~1.8k tokensUpdated 3 mo ago
    Writing & ContentAuto-check passed
  • Business Insight Essay Writer

    liangdabiao/liurun-bookwriter-skills

    Drafts Chinese business-insight essays, short audio scripts and year-end speeches in a specific public commentator's rhythm, built from his books, talks and broadcasts.

    277 GitHub stars~2.5k tokensUpdated 3 mo ago
    Writing & ContentAuto-check passed
  • Shakespeare Writing Studio

    ZCZHAO-1999/shakespeare-writing-studio

    Produce publish-ready Chinese and English writing packages across WeChat articles, Medium/Substack essays, research notes, founder memos, op-eds, speeches, data storytelling, statistical graphics…

    178 GitHub stars~1.5k tokensUpdated 3 mo ago
    Writing & ContentAuto-check passed

More from Peiiii/nextclaw

All 70 skills in this repo
  • Nextclaw Skin Studio

    Peiiii/nextclaw

    A skill your agent uses when a user wants to browse, apply, inspect, create, refine, switch, or remove a NextClaw skin; wants a personal skin with arbitrary CSS, JavaScript, images, SVG, DOM…

    260 GitHub stars~1.8k tokensUpdated yesterday
    Auto-check passed
  • A skill your agent uses when a development task needs visible phase tracing, task-level or phase-level Token measurement, model/effort comparison, or a deterministic usage report or local dashboard…

    260 GitHub stars~802 tokensUpdated yesterday
    Auto-check passed
  • 当 NextClaw 产品更新后需要生成、替换、挑毛病或检查官网、GitHub README、用户文档或社交传播中的真实截图、AI 宣传视觉、整页 HTML 宣传预览、社区二维码等对外视觉资产时使用;也用于“更新截图”“重新截一批图”“做宣传页”“生成 campaign 页面”“视觉审稿”“五星挑刺法”或发布前检查视觉资产。普通站点布局开发或只写文章不触发。

    260 GitHub stars~801 tokensUpdated yesterday
    Auto-check passed
  • UI UX Pro Max

    Peiiii/nextclaw

    A skill your agent uses when the user wants professional UI/UX design guidance, design-system generation, UX review, or stack-specific frontend guidance through a bundled local UI/UX Pro Max dataset…

    260 GitHub stars~2k tokensUpdated yesterday
    Auto-check passed
  • Impeccable

    Peiiii/nextclaw

    A skill your agent uses when the user wants distinctive, production-grade frontend design, anti-generic AI aesthetics, UX critique, technical UI audits, or final polish through bundled Impeccable…

    260 GitHub stars~2.5k tokensUpdated yesterday
    Auto-check passed
  • Curate NextClaw skill resources, including OpenClaw and community sources.

    260 GitHub stars~479 tokensUpdated yesterday
    Auto-check passed

Questions about Nextclaw Product Blog Storytelling

What does Nextclaw Product Blog Storytelling do?

当为 NextClaw 及关联产品写博客、官网短文、发布叙事、功能优势、社区稿或配图 brief,并需要把用户兴趣、愿景与证据收敛成可信公开内容时使用。. Nextclaw Product Blog Storytelling is an agent skill from Peiiii/nextclaw.

When should I use Nextclaw Product Blog Storytelling?

Nextclaw Product Blog Storytelling fits situations like: tasks that involve Storytelling.

How do I install Nextclaw Product Blog Storytelling in Claude Code?

Run `npx skills add Peiiii/nextclaw --skill nextclaw-product-blog-storytelling -a claude-code`. Or copy the skill folder (.agents/skills/nextclaw-product-blog-storytelling in Peiiii/nextclaw) into .claude/skills/nextclaw-product-blog-storytelling in your project. Claude Code loads it when a task matches its description.

How do I install Nextclaw Product Blog Storytelling in Codex?

Run `npx skills add Peiiii/nextclaw --skill nextclaw-product-blog-storytelling -a codex`. Or copy the skill folder (.agents/skills/nextclaw-product-blog-storytelling in Peiiii/nextclaw) into .agents/skills/nextclaw-product-blog-storytelling in your project. Codex loads it when a task matches its description.

Can I use Nextclaw Product Blog Storytelling in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Peiiii/nextclaw --skill nextclaw-product-blog-storytelling -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/nextclaw-product-blog-storytelling, .gemini/skills/nextclaw-product-blog-storytelling, .github/skills/nextclaw-product-blog-storytelling and .opencode/skills/nextclaw-product-blog-storytelling in your project.

What does Nextclaw Product Blog Storytelling need to run?

SKILL.md names no scripts, command-line tools or credentials: Nextclaw Product Blog Storytelling is instructions for the agent only.

Does Nextclaw Product Blog Storytelling access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Nextclaw Product Blog Storytelling safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Nextclaw Product Blog Storytelling use?

Nextclaw Product Blog Storytelling is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Nextclaw Product Blog Storytelling use?

About 781 tokens (SKILL.md is roughly 3.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Nextclaw Product Blog Storytelling?

Skills that share tags, products or a category with Nextclaw Product Blog Storytelling: Data Storytelling (ynulihao/AgentSkillOS, 618 stars), Chinese Novel Writing System (leenbj/novel-creator-skill, 671 stars), Chinese Novelist Chapter Writer (PenglongHuang/chinese-novelist-skill, 3.3k stars) and Liu Run Style Business Column Writer (liangdabiao/liurun-bookwriter-skills, 277 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Nextclaw Product Blog Storytelling?

Peiiii (a GitHub user) maintains it in Peiiii/nextclaw, which has 260 GitHub stars. The repository holds 70 skills in this directory. The repository was last updated on October 9, 2026.

Source: Peiiii/nextclaw on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.