Agent skill

Writing Fragments

by vinvcn in vinvcn/mattpocock-skills-zh-CN

Writing, explore:挖掘原始 fragments,暂不施加任何结构. An agent skill from vinvcn/mattpocock-skills-zh-CN.

MITAuto-check passed

Install Writing Fragments

skills CLI
$ npx skills add vinvcn/mattpocock-skills-zh-CN --skill writing-fragments -a claude-code

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

GitHub CLI
$ gh skill install vinvcn/mattpocock-skills-zh-CN writing-fragments --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/vinvcn/mattpocock-skills-zh-CN.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/in-progress/writing-fragments .claude/skills/writing-fragments && 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
writing-fragments
GitHub stars
4.7k
Token cost
~538 tokens
SKILL.md length
146 words
Files
2
Skills in repo
32
Repo updated
First seen
Licence
MIT

At a glance

Writing, explore:挖掘原始 fragments,暂不施加任何结构. An agent skill from vinvcn/mattpocock-skills-zh-CN.

  • SKILL.md covers What is a fragment, File format and Writing rhythm
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Writing Fragments is an agent skill from vinvcn/mattpocock-skills-zh-CN. Writing, explore:挖掘原始 fragments,暂不施加任何结构。

Its SKILL.md is about 540 tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).

The repository describes itself as: 这是 mattpocock/skills 的简体中文本地化版本。 The licence is MIT.

Example prompts

  • “/writing-fragments”

What it can do on your machine

Read from SKILL.md and the folder at commit bf98e53. 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

Writing Fragments loads about 538 tokens when it runs. Until then it costs about 15 tokens; SKILL.md has 146 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~15
When it runs · the whole SKILL.md, loaded when a task matches
~538

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 vinvcn/mattpocock-skills-zh-CN at commit bf98e53, republished under its MIT licence (© vinvcn). 146 words, ~538 tokens.

Download SKILL.mdSave it as .claude/skills/writing-fragments/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
writing-fragments
description
Writing, explore:挖掘原始 fragments,暂不施加任何结构。
disable-model-invocation
true
<what-to-do>

这是纯粹的 explore:在不承诺任何结构的前提下,拓宽可写内容的空间——承诺结构是 exploit,是另一个 skill 的工作。运行一个产出 fragments 的 grilling session,围绕用户想写的任何主题持续访谈。在这里强加 phases、outlines 或文章结构都不在范围内。

当对话双方产生 fragments 时,把它们追加到单一 markdown 文件。

如果用户没有传入路径,只询问一次文档保存到哪里,然后在 session 剩余部分记住它。

从用户说的第一句话开始捕获 fragments,包括 initial prompt。

第一次写入时,在顶部放一个带 working title 的单一 H1(之后可以改),除此之外什么都不要放:不要 metadata、TOC 或 date。

</what-to-do>
<supporting-info>

What is a fragment

Fragment 是任何可能进入最终文章的文本片段。它必须_对作者可读_,也就是作者能知道它是什么意思;但它不需要定义术语,也不需要让冷读者立即理解。标准是 “这是不是一段好写作素材?”,不是 “这是不是自洽论证?”

Fragments 刻意保持异质。可能成为 fragment 的例子:

  • 一句 sharp sentence,你想在某处使用但还不知道放哪里。
  • 一个 claim 和一句 justification。
  • 一个 vignette:发生过的事、code snippet、scenario、analogy。
  • 一个 half-thought:"something about how X feels like Y, work this out later."
  • 一句 quote、一段 dialogue、一句 overheard line。
  • 一组凭感觉属于同一簇的 observations。
  • 一个 complaint、confession 或 punchline。
  • 一个 leading word——一个紧凑的隐喻或新造词,整篇文章都可以挂在它上面(一个为这个 idea 命名的术语,就像 tracer bullets 或 fog of war 为整个模式命名那样)。

在这些当中,leading word 是最值得落地的 fragment。它是 load-bearing 的:在 explore 阶段命名对的那一个,就会塑造之后的结构、transitions 和标题——在整个 exploit 阶段持续产生回报。当对话围绕一个反复出现的 idea 打转时,推动为它造一个词。

Novelist's diary 是模型:多年无结构的 noticings,之后被挖掘成 raw material。Fragments 就是 noticings。

File format

markdown
# Working title

A first fragment lives here.

It can be multiple paragraphs. It can include lists, code, quotes — whatever
shape the fragment naturally takes.

---

A second fragment.

---

> A quoted line that the user wants to keep around.

A reaction to it.

---

- A cluster of related observations
- That hang together by feel
- And want to be near each other

Fragments 用 horizontal rule(\n---\n)分隔。正文内不要 headings。不要 tags。除了加入顺序之外,不做排序。

Writing rhythm

安静追加。不要为每个 fragment 请求许可。可以顺带说你添加了什么("adding that"),但不要用 save dialogs 打断对话。

每次写入前:从磁盘重新读取文件。用户可能在回合之间编辑、重排或删除 fragments;保留他们的变化。永远不要 overwrite 文件;只 append(或者在用户要求时,就地编辑特定 fragment)。

用户随时可以说 "cut the last one"、"rewrite that one sharper"、"merge those two"。把它们当成一等指令。

</supporting-info>

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

Files

SKILL.md and 1 other file in skills/in-progress/writing-fragments of vinvcn/mattpocock-skills-zh-CN.

  • SKILL.md
  • agents/openai.yaml

Open the folder on GitHubat commit bf98e53

Compare with similar skills

Writing Fragments 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.

Writing Fragments compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Writing Fragments this skillvinvcn/mattpocock-skills-zh-CN4.7k—~538Automated safety check: PassMIT
Fragmentsmendixlabs/mxcli129—~2.4kAutomated safety check: PassApache-2.0
Writing Fragmentsfossasia/eventyay-interpretation1.6k6 repos~891Automated safety check: WarnApache-2.0
Bio Fragment AnalysisFreedomIntelligence/OpenClaw-Medical-Skills3.1k1 repos~1.6kAutomated safety check: PassNone
Bio Restriction Fragment AnalysisGPTomics/bioSkills1.2k1 repos~2.6kAutomated safety check: PassMIT
Fragmentation Aware Packingbenchflow-ai/skillsbench1.8k—~983Automated safety check: PassApache-2.0

Similar skills

  • Fragments

    mendixlabs/mxcli

    Define reusable widget groups with CREATE FRAGMENT and place them with USE FRAGMENT.

    129 GitHub stars~2.4k tokensUpdated yesterday
    Auto-check passed
  • Writing Fragments

    fossasia/eventyay-interpretation

    Writing, explore — mine raw fragments, no structure yet. An agent skill from fossasia/eventyay-interpretation.

    1.6k GitHub starsUsed in 6 repos~891 tokens
    Auto-check: warnings
  • Bio Fragment Analysis

    FreedomIntelligence/OpenClaw-Medical-Skills

    Analyzes cfDNA fragment size distributions and fragmentomics features using FinaleToolkit or Griffin.

    3.1k GitHub starsUsed in 1 repo~1.6k tokens
    Marketing & SEOAuto-check passed
  • Predict restriction digest fragment sizes and gel patterns using Biopython Bio.Restriction.

    1.2k GitHub starsUsed in 1 repo~2.6k tokens
    Research & ScienceAuto-check passed
  • Fragmentation Aware Packing

    benchflow-ai/skillsbench

    Choose placements that preserve useful residual capacity. An agent skill from benchflow-ai/skillsbench.

    1.8k GitHub stars~983 tokensUpdated 2 mo ago
    Auto-check passed
  • Writing Fragments

    InditexTech/weavejs

    Grilling session that mines the user for fragments — heterogeneous nuggets of writing (claims, vignettes, sharp sentences, half-thoughts) — and appends them to a single document as raw material for…

    238 GitHub starsUsed in 4 repos~828 tokens
    Agent WorkflowsAuto-check: warnings

More from vinvcn/mattpocock-skills-zh-CN

All 32 skills in this repo
  • Git Guardrails Claude Code

    vinvcn/mattpocock-skills-zh-CN

    设置 Claude Code hooks,在危险 git commands(push、reset --hard、clean、branch -D 等)执行前阻止它们。适用于用户想防止破坏性 git 操作、添加 git safety hooks,或在 Claude Code 中阻止 git push/reset 时。

    4.7k GitHub stars~461 tokensUpdated 3 days ago
    Auto-check passed
  • Codebase Design

    vinvcn/mattpocock-skills-zh-CN

    用于设计深模块的共享词汇。适用于用户想设计或改进模块接口、寻找深化机会、决定 seam 放在哪里、让代码更容易测试或更适合 AI 导航,或其他技能需要深模块词汇时。

    4.7k GitHub stars~1.1k tokensUpdated 3 days ago
    Auto-check passed
  • Diagnosing Bugs

    vinvcn/mattpocock-skills-zh-CN

    面向棘手缺陷和性能回退的诊断循环。适用于用户说 “diagnose” / “debug this”,或报告某些东西 broken、throwing、failing、slow 时。

    4.7k GitHub stars~1.4k tokensUpdated 3 days ago
    Auto-check passed
  • Domain Modeling

    vinvcn/mattpocock-skills-zh-CN

    构建并打磨项目的领域模型。适用于讨论 codebase 术语、编写或编辑 GLOSSARY.md,或记录或编辑 ADR。

    4.7k GitHub stars~477 tokensUpdated 3 days ago
    Auto-check passed
  • Migrate To Shoehorn

    vinvcn/mattpocock-skills-zh-CN

    将测试文件从 as 类型断言迁移到 @total-typescript/shoehorn。适用于用户提到 shoehorn、想替换测试中的 as,或需要局部测试数据时。

    4.7k GitHub stars~603 tokensUpdated 3 days ago
    Auto-check passed
  • PR

    vinvcn/mattpocock-skills-zh-CN

    用于撰写 PR 正文。适用于用户要求起草、改写或改进 PR 正文,或希望 PR 更便于审阅时. An agent skill from vinvcn/mattpocock-skills-zh-CN.

    4.7k GitHub stars~729 tokensUpdated 3 days ago
    Auto-check passed

Questions about Writing Fragments

What does Writing Fragments do?

Writing, explore:挖掘原始 fragments,暂不施加任何结构. An agent skill from vinvcn/mattpocock-skills-zh-CN. Writing Fragments is an agent skill from vinvcn/mattpocock-skills-zh-CN.

How do I install Writing Fragments in Claude Code?

Run `npx skills add vinvcn/mattpocock-skills-zh-CN --skill writing-fragments -a claude-code`. Or copy the skill folder (skills/in-progress/writing-fragments in vinvcn/mattpocock-skills-zh-CN) into .claude/skills/writing-fragments in your project. Claude Code loads it when a task matches its description.

How do I install Writing Fragments in Codex?

Run `npx skills add vinvcn/mattpocock-skills-zh-CN --skill writing-fragments -a codex`. Or copy the skill folder (skills/in-progress/writing-fragments in vinvcn/mattpocock-skills-zh-CN) into .agents/skills/writing-fragments in your project. Codex loads it when a task matches its description.

Can I use Writing Fragments 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 vinvcn/mattpocock-skills-zh-CN --skill writing-fragments -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/writing-fragments, .gemini/skills/writing-fragments, .github/skills/writing-fragments and .opencode/skills/writing-fragments in your project.

What does Writing Fragments need to run?

SKILL.md names no scripts, command-line tools or credentials: Writing Fragments is instructions for the agent only.

Does Writing Fragments 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 Writing Fragments 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 Writing Fragments use?

Writing Fragments 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 Writing Fragments use?

About 538 tokens (SKILL.md is roughly 2.2k 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 Writing Fragments?

Skills that share tags, products or a category with Writing Fragments: Fragments (mendixlabs/mxcli, 129 stars), Writing Fragments (fossasia/eventyay-interpretation, 1.6k stars), Bio Fragment Analysis (FreedomIntelligence/OpenClaw-Medical-Skills, 3.1k stars) and Bio Restriction Fragment Analysis (GPTomics/bioSkills, 1.2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Writing Fragments?

vinvcn (a GitHub user) maintains it in vinvcn/mattpocock-skills-zh-CN, which has 4,712 GitHub stars. The repository holds 32 skills in this directory. The repository was last updated on October 8, 2026.

Source: vinvcn/mattpocock-skills-zh-CN on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.