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 skills add Lion-1209/Lion-Skills --skill lion-writing-skillsgit clone --depth 1 https://github.com/Lion-1209/Lion-SkillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/lion-1209/lion-skills/lion-writing-skills)<a href="https://agentmods.dev/skills/lion-1209/lion-skills/lion-writing-skills"><img src="https://agentmods.dev/badge/skills/lion-1209/lion-skills/lion-writing-skills/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/lion-1209/lion-skills/lion-writing-skills"><img src="https://agentmods.dev/badge/skills/lion-1209/lion-skills/lion-writing-skills.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00018 | $0.01695 |
| Opus 5 | $0.00009 | $0.00847 |
| Sonnet 5 | $0.00004 | $0.00339 |
| Haiku 4.5 | $0.00002 | $0.00169 |
Grade A, and why
lion-writing-skills 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 12d 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.
This is a copy
100% identical to lion-writing-skills — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Lion Writing Skills
概述
Lion-Skills 的"造 skill 流水线"：按本仓库规范，把一个重复的工作流沉淀成可复制、经验证的 skill。
核心原则：skill 是给未来 Claude 读的"操作手册"——它的价值不在于你写了什么，而在于未来的 Claude 在触发它时，能照着做出正确的事。
何时使用
- 用户想新增一个 skill（"帮我加个 X 的 skill"）
- 用户想修改/优化现有 skill
- 用户想检查某个 skill 写得是否符合规范
- 想把对话里反复出现的工作流沉淀成 skill
不该做成 skill 的情况：一次性的、项目特定的约定（放 CLAUDE.md）、能用简单校验自动化的（写成校验脚本而不是文档）。
只是审查/优化现有 skill 时：直接对照下文相关规则做合规判断即可，不必每次重走第 1 步"值不值得做"四问——那是新增 skill 的决策；现有 skill 要不要继续存在，是另一个问题。
核心内容
第 1 步：判断值不值得做
回答四个问题（都"是"才值得做）：
- 高频吗？（反复出现，不是一次性的）
- 跨项目吗？（不止一个代码库用得到）
- 有判断空间吗？（需要决策/经验，不是机械操作——机械操作写成脚本）
- 未来 Claude 不读这个 skill，会做错或做差吗？
任何一个答"否"，就别做成独立 skill：项目特定的约定放 CLAUDE.md，能机械自动化的写成校验脚本，一次性的直接在对话里处理。
第 2 步：复制模板，填 frontmatter
新 skill 建在 skills/<name>/SKILL.md（同名目录，里面放 SKILL.md，可选再放 evals/ 存验证用例）。复制 template/SKILL.md 过去，填两个字段：
name：全小写、连字符，用 skill 的核心动作或概念命名（如commit-message、error-handling、onboarding-unknown-codebase）。不要下划线或驼峰（commit_message、CommitMessage都错）description：只写"何时触发"，第三人称，中文，用三段式——①触发场景（"当用户……时使用"）+ ②典型信号（把用户实际会说的原话尽量列全）+ ③涉及关键词（中文说法 + 常见英文术语）。这样覆盖面广、不易漏触发。上限 1024 字符
关键：description 绝不能写工作流（"先做 A 再做 B"）。原因——测试发现 Claude 会偷懒只读 description 跳过正文。把流程留给正文。
第 3 步：写正文
按这个骨架：概述 / 何时使用 / 核心内容 / 常见错误（参考 template/SKILL.md）。
写作约定：
- 解释 why，少用全大写 MUST（讲道理比下命令管用）
- 一个优秀例子 > 多语言版本；例子尽量覆盖该 skill 最核心的 2–3 类场景，而非只示范单类
- 正文 < 500 行；超了拆
references/ - 中文为主，工具名/术语保留英文
第 4 步：轻量验证
前置：先确认目标 SKILL.md 在手（文件路径或正文）。用户只说"帮我验证"却没给内容时，先向用户要；skill 还在草稿态没落盘时，把全文直接贴进 subagent 的 prompt 即可，效果等同落盘。
写 2–3 个真实测试 prompt，用 subagent 带着新 skill 跑，看产出对不对。这一步最容易被跳过，但也最能发现问题，别省。
怎么算"真实" prompt：要像真实用户会说的、带具体细节——好的如"我把组件状态从 useState 换成 useReducer，还修了个内存泄漏，写个 commit message"；坏的如"测一下你的能力"（太抽象，既测不出触发、也测不出指引力）。
范式：派一个 general-purpose subagent（让它只读 skill、把产出放进报告，不要改动仓库——除非任务就是要它落地文件），prompt 写「读取 skills/<name>/SKILL.md，然后按其指引处理这个需求：<测试 prompt>。完成后报告：你走了哪些步骤、产出什么、哪里卡壳」。多个 prompt 可以并行派。
通过标准：subagent 的产出 (a) 解决了用户问题，且 (b) 遵循 skill 的设计意图。把该 skill 正文里"该走的流程""该遵循的约定"抽成几条可勾选项来核（如 description 没写工作流、正文解释了 why、例子覆盖核心场景）。跑偏长这样：该走五步的跳过了验证、该三段式的 description 写成了能力清单、该按维度系统的退化成逐条枚举——出现这些就改正文重跑。
What ships with it
1 file 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.
- 12d ago First seen · 86 lines · 18 tokens per session scan A 7c036c454ee0
lion-writing-skills is a skill published in the GitHub repository Lion-1209/Lion-Skills (5 stars, last pushed 2mo ago), licensed MIT. It adds 18 tokens to every session and 1,695 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to lion-writing-skills, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
cosmosdb-datamodeling
Step-by-step guide for capturing key application requirements for NoSQL use-case and produce Azure Cosmos DB Data NoSQL Model design using best practices and common patterns, artifactsproduced: "cosmosdbrequirements.md" file and "cosmosdbdatamodel.md" file.
geofeed-tuner
Use this skill whenever the user mentions IP geolocation feeds, RFC 8805, geofeeds, or wants help creating, tuning, validating, or publishing a self-published IP geolocation feed in CSV format. Intended user audience is a network operator, ISP, mobile carrier, cloud provider, hosting company, IXP, or satellite…
arize-evaluator
INVOKE THIS SKILL for LLM-as-judge evaluation workflows on Arize: creating/updating evaluators, running evaluations on spans or experiments, tasks, trigger-run, column mapping, and continuous monitoring. Use when the user says: create an evaluator, LLM judge, hallucination/faithfulness/correctness/relevance, run eval…
copilot-cli-quickstart
Use this skill when someone wants to learn GitHub Copilot CLI from scratch. Offers interactive step-by-step tutorials with separate Developer and Non-Developer tracks, plus on-demand Q&A. Just say "start tutorial" or ask a question! Note: This skill targets GitHub Copilot CLI specifically and uses CLI-specific tools…
fireworks-tech-graph
A generator for technical diagrams that exports them as SVG and PNG images. It is intended for architecture, data-flow, flowchart, sequence, agent, memory, and concept-map diagrams.
adobe-illustrator-scripting
Write, debug, and optimize Adobe Illustrator automation scripts using ExtendScript (JavaScript/JSX). Use when creating or modifying scripts that manipulate documents, layers, paths, text frames, colors, symbols, artboards, or any Illustrator DOM objects. Covers the complete JavaScript object model, coordinate system…