Skill 生成器

Skill 生成器 is a skill for Claude Code, Codex from CavinHuang/lume. It costs 25 tokens per session (816 once invoked), scanned A, original, MIT.

A Chinese-language guide for creating, improving, or evaluating a Lume Skill, which is a reusable instruction file that tells an agent when and how to perform a task. It covers the file format, available tools, and evaluation references.

In plain words
What is it for?
Use it to create a new SKILL.md, refine an existing skill, choose allowed tools, add argument placeholders, or prepare evaluation files for testing the skill.
Why use it?
It helps turn an informal task into a repeatable skill with clear triggers, inputs, tools, steps, and output expectations. This makes the skill easier for an agent to select and follow consistently.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/cavinhuang/lume/skill-creator
Any agent
npx skills add CavinHuang/lume --skill skill-creator
Clone the repo
git clone --depth 1 https://github.com/CavinHuang/lume

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for Skill 生成器

README.md
[![agentmods](https://agentmods.dev/badge/skills/cavinhuang/lume/skill-creator.svg)](https://agentmods.dev/skills/cavinhuang/lume/skill-creator)
Your own site
<a href="https://agentmods.dev/skills/cavinhuang/lume/skill-creator"><img src="https://agentmods.dev/badge/skills/cavinhuang/lume/skill-creator.svg" alt="Measured on agentmods" height="20"></a>
Per session 25 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 816 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00025 $0.00816
Opus 5 $0.00013 $0.00408
Sonnet 5 $0.00005 $0.00163
Haiku 4.5 $0.00003 $0.00082

Measured 5d ago against content hash 0a5adff6840e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

Skill 生成器 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 5d 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.

apps/sidecar/default-skills/skill-creator/SKILL.md · 81 lines

What it actually says

你是 Lume 的 Skill 生成专家。Skill 是存储在 SKILL.md 文件中的可重用提示词模板,模型根据触发条件自动调用。

Skill 文件格式

每个 skill 是一个独立目录,包含 SKILL.md

~/.alice/skills/<skill-name>/SKILL.md   # 用户全局 skill
{workdir}/.alice/skills/<skill-name>/SKILL.md  # 项目级 skill

SKILL.md 结构

---
name: "展示名称"
description: "一句话描述 skill 的作用(模型靠这句话判断是否调用)"
allowed_tools: ["read_file", "bash"]  # 可选,限制 skill 执行时可用的工具
version: "1.0"
disable_model_invocation: false  # true 则只允许用户在 / 面板选择 lume-skill://skill 触发
argument_hint: "请告诉我要分析的文件路径"  # 可选,提示用户传什么参数
---

这里是提示词正文,支持 ${ARG} 占位符接收用户传入的参数。

可用工具列表(allowed_tools 填写参考)

  • read_file — 读取文件
  • list_dir — 列出目录
  • write_file — 写入文件
  • edit_file — 编辑文件
  • bash — 执行命令
  • grep — 文件内搜索
  • glob — 文件路径匹配
  • web_fetch — 抓取网页
  • web_search — 网络搜索
  • personalize_ui — 读取或调整已支持的 Lume 界面状态
  • lume_reading_snapshot — 读取 Lume Reading 书架与笔记摘要
  • lume_generate_share_card — 为 Reading 笔记生成本地分享卡
  • agent — 启动子 Agent

Skill 评测 Schema 参考

如需生成评测数据(evals.json / grading.json 等),读取参考文档:

~/.alice/skills/references/schemas.md

工作流程

创建新 Skill

  1. 明确用途:询问用户这个 skill 的使用场景、触发条件、期望输出
  2. 确定 allowed_tools:根据 skill 需要做什么操作选择工具
  3. 撰写提示词正文:清晰的角色定位、分步骤操作流程、期望输出格式、边界情况处理
  4. 写入文件:用 write_file 创建 ~/.alice/skills/<name>/SKILL.md
  5. 告知用户:说明 skill 已创建,触发条件是什么

优化已有 Skill

  1. read_file 读取现有 SKILL.md
  2. 分析问题(描述不清晰?提示词歧义?)
  3. 给出改进建议并征求用户确认
  4. edit_file 更新文件

好 Skill 的标准

  • description 精准:模型靠 description 决定是否调用,要一句话说清楚做什么
  • allowed_tools 最小化:只开放 skill 真正需要的工具
  • 提示词结构化:用标题、列表、代码块让 AI 更容易遵循
  • 处理无参数情况:用户没传参时,主动询问或用工具读取上下文
Changes

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.

  1. 5d ago First seen · 81 lines · 25 tokens per session scan A 0a5adff6840e

Subscribe to this mod's changes

Skill 生成器 is a skill published in the GitHub repository CavinHuang/lume (3 stars, last pushed 5d ago), licensed MIT. It adds 25 tokens to every session and 816 once invoked, about $0.0001 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 2026-08-31.

Related

Other skills, from other repositories

guizang-ppt-skill

生成横向翻页网页 PPT(单 HTML 文件),含 WebGL 背景、章节幕封、数据大字报、图片网格等模板。提供两种风格:① "电子杂志 × 电子墨水"(衬线 + 流体背景 + 暖色) ② "瑞士国际主义"(无衬线 + 网格点阵 + IKB/柠檬黄/柠檬绿/安全橙高亮)。当用户需要制作分享 / 演讲 / 发布会风格的网页 PPT,或提到"杂志风 PPT"、"瑞士风 PPT"、"Swiss Style"、"horizontal swipe deck"时使用。.

proma-ai/Proma · 161 tokens

proma-coach

Proma 使用顾问,主动把用户在 Proma/Agent/Skill/Chat 工具/项目里的摩擦、疑惑、重复解释和低效流程,转成更顺手的使用方式或合适的知识维护动作。触发要积极:用户表达不满、困惑、重复提醒、"为什么没用/不会自动/又要我说"、"算了,我自己来"、"你上次不是说..."、"你又忘了"、"以后都这样/能不能记住/少让我选/下次自动"、询问 Proma 怎么用更好、某事能不能固化、该用 Agent 还是 Chat 工具、有没有现成 Skill、Skill 为什么没触发、想优化已有 Skill description、想减少步骤/降低认知负担/让 Proma…

proma-ai/Proma · 386 tokens

skill-creator

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

proma-ai/Proma · 64 tokens

automation

Proma 内嵌自动任务与定时任务 Skill,属于 Proma 自带能力而不是用户临时安装的外部 Skill。触发要非常宽泛、非常冗余:只要用户的话里出现任何“未来还要做”“以后继续看”“重复做”“再跑一次也有价值”“定期/周期/每天/每周/每月/每隔一段时间”“持续关注/持续观察/长期跟进/长期监控”“自动检查/自动汇总/自动生成/自动复盘/自动维护”“无人值守”“有变化告诉我”“异常时提醒我”“结果不好就调整”“查看运行记录”“优化已有任务”“暂停/恢复/删除/立即运行任务”等迹象,就应该触发此 Skill,先判断是否适合 Proma 定时任务。也要覆盖一次性与有限次的延时执行信号:“X…

proma-ai/Proma · 390 tokens

agent-collaboration

Proma 协作子 Agent Skill。当需要并行探索多个方向(多样性探索)、对抗性审查验证已有方案、或多个长耗时独立任务需要真实可见的子会话时触发。用于判断是否以及如何调用 Proma 内置 collaboration 工具创建协作子会话。简单搜索、短调研、单文件修改、一次性代码审查由父会话直接使用普通工具完成。.

proma-ai/Proma · 101 tokens

docx

Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when…

proma-ai/Proma · 168 tokens