Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/niracler/skill/writing-assistantnpx skills add niracler/skill --skill writing-assistantgit clone --depth 1 https://github.com/niracler/skillWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00113 | $0.02003 |
| Opus 5 | $0.00056 | $0.01001 |
| Sonnet 5 | $0.00023 | $0.00401 |
| Haiku 4.5 | $0.00011 | $0.00200 |
Grade A, and why
writing-assistant scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 201 lines — stays where its author put it; the contents beside it link to each section on GitHub.
写作助手
写作助手，两种模式：构思引导（从零开始写）和审校打磨（改已有文章）。
前置条件
| 工具 | 类型 | 必需 | 安装方式 |
|---|---|---|---|
| markdownlint-cli2 | CLI | 否 | npx markdownlint-cli2，无需安装，用于审校步骤 6 |
| markdown-lint | skill | 否 | 可选，由独立的 developer-workflows plugin 提供 |
加载 skill 时不要主动检查这些工具。命令因缺少工具而失败时，再逐步引导完成安装和配置。
模式选择
| 用户意图 | 模式 | 章节 |
|---|---|---|
| 「不知道写什么」「帮我构思」「写游记」「记录 TIL」「写点什么」 | 构思 | 构思模式 |
| 「帮我改文章」「检查一下」「润色」「校对一下」「看看文章」 | 审校 | 审校模式 |
意图不明确时，先询问用户。
构思模式
帮助用户在不知道写什么或如何写下去时，通过启发式提问引导写作。
核心原则
| 原则 | 说明 |
|---|---|
| 一次一个问题 | 先设计问题清单，再逐个提问 |
| 确认后继续 | 用户思考 → 写作 → 修改 → 确认 → 下一个问题 |
| 启发而非代写 | 用问题激发思考，不替用户决定内容方向 |
文章类型判断
| 用户意图 | 类型 | 框架 |
|---|---|---|
| 「写游记」「记录旅行」 | 游记 | 出发 → 过程 → 回望 |
| 「记录 TIL」「今天学到」 | TIL | 背景 → 过程 → 方案 → 收获 |
| 「写点什么」「帮我构思」 | 通用文章 | 触发点 → 观点 → 展开 → 收束 |
流程
判断文章类型 → 列出引导问题 → 逐个提问 → 用户回答 → 确认 → 下一题 → 整理成文
提问节奏
Claude: "Why did you want to visit this place?"
User: [writes answer]
Claude: [confirm/follow-up] -> "OK, next question: what was the first thing you saw when you arrived?"
写作框架
每种类型都有对应的文章结构和引导问题。完整内容见 writing-frameworks.md。
草稿完成后，建议切换到审校模式。
审校模式
文章审校，提供 6 步审校流程，帮助打磨中文文章。
核心原则
| 原则 | 说明 |
|---|---|
| 先讨论再修改 | 提出修改建议供用户选择，不直接改动 |
| 按章节审校 | 以 Markdown 标题为检查点，每次处理 1～2 个章节 |
| 启发而非决定 | 用问题引导内容，不替用户作决定 |
六步审校流程
1. 结构 → 2. 读者语境 → 3. 语言 → 4. 来源核验 → 5. 风格 → 6. Markdown 格式
步骤 1：结构诊断
目标：确保结构清晰、主题集中。
- 拆分段落并识别主题。
- 提出 2～3 种重组方案，先讨论再修改。
- 将删除的内容移入独立的
material.md文件。
步骤 2：读者语境检查
核心问题：「读者会在这里感到困惑吗？」
| 问题 | 表现 | 处理方式 |
|---|---|---|
| 背景假设 | 使用术语或缩写但没有解释 | 补充说明或脚注 |
| 自我指涉 | 使用「就像那个……」但不解释 | 改成具体描述 |
| 逻辑跳跃 | 从 A 直接跳到 C | 补充过渡说明 |
| 情绪缺少铺垫 | 使用「实在太……」但没有上下文 | 先补充背景 |
| 信息缺口 | 默认读者知道前因后果 | 简要补充背景 |
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 201 lines · 113 tokens per session scan A 6ef5b38c2f04
writing-assistant is a skill published in the GitHub repository niracler/skill (11 stars, last pushed 1mo ago), licensed MIT. It adds 113 tokens to every session and 2,003 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.