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/cavinhuang/lume/release-notesnpx skills add CavinHuang/lume --skill release-notesgit clone --depth 1 https://github.com/CavinHuang/lumeWhat 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 | $0.00074 | $0.01806 |
| Opus 5 | $0.00037 | $0.00903 |
| Sonnet 5 | $0.00015 | $0.00361 |
| Haiku 4.5 | $0.00007 | $0.00181 |
Grade A, and why
release-notes 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 — 216 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Release Notes Generator
生成用户可读的版本发布说明，CI 直接读取发布。
Core Principle
Release notes are not a formatted changelog. They explain to users what changed and why it matters to them — written as if the team is walking them through the update.
commit 原始信息 → 用户视角翻译 → 发布说明
禁止： 将 raw commits 直接填入发布说明（如 feat(ci): read release notes from file）。每条都必须翻译为用户能理解的语言。
Flow
确定版本 → 读取 commit → 分类 + 用户价值翻译 → 生成 Markdown → 写入 docs/release/vX.Y.Z.md → 预览确认
Step 1: 确定版本
git describe --tags --abbrev=0 # 上一个 tag
cat package.json | grep '"version"' # 当前版本
- 用户指定版本号（如
v0.2.0）→ 直接使用 - 用户说 "patch/minor/major" → 按 semver 递增
- 不确定 → 问用户
Step 2: 读取 Commit 历史
git log <lastTag>..HEAD --oneline # 有 tag 时
git log --oneline # 无 tag 时
Step 3: 分类 + 用户价值翻译
分类
| 分类 | emoji | 前缀 | 是否面向用户 |
|---|---|---|---|
| Features | 🚀 | feat |
✅ 是 |
| Bug Fixes | 🐛 | fix |
✅ 是 |
| Breaking Changes | ⚠️ | BREAKING: |
✅ 是（独立 section） |
| Refactoring | ♻️ | refactor |
❌ 内部 |
| Documentation | 📝 | docs |
❌ 内部 |
| Maintenance | 🔧 | chore |
❌ 内部 |
| Performance | ⚡ | perf |
✅ 是（如用户感知加速） |
未匹配 → 🔔 Other
用户价值翻译（关键）
每条面向用户的 commit 翻译为 用户能理解的语言：
| 原始 commit | 用户视角翻译 |
|---|---|
feat(ci): read release notes from file |
发布流程改进 — 发布说明现在自动生成 |
fix(desktop): tauri.conf.json pubkey |
修复桌面端自动更新签名验证 |
chore: release script main flow |
新的版本发布脚本，支持自动 bump + tag + push |
规则：
- 保留 scope 括号，补充一句中文解释变更范围
- 内部实现细节（如 "extract function", "use readFileSync"）→ 一句话概括目的，不列技术点
- 同类合并 — 同一 scope 下 3+ 相似 commit → 合并为一条，注明数量
- scope 信息必须保留，便于读者理解变更范围
破坏性变更（BREAKING）
- 提取
BREAKING:前缀的 commit → 放入 独立 section## ⚠️ Breaking Changes - 说明影响范围 + 迁移建议
- 放在 Highlights 之后，Features 之前
语言处理
commit message 可能混合中英文：
- 面向用户的部分 → 统一为 中文说明
- 保留技术术语原文（如
tauri-action,bun,N-API）
Step 4: 生成发布说明
文件路径
docs/release/vX.Y.Z.md # 必须有 v 前缀 — CI 读取 github.ref_name (如 v0.2.0)
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 · 216 lines · 0 tokens per session scan A 977aff0e640d
release-notes is a skill published in the GitHub repository CavinHuang/lume (2 stars, last pushed 2d ago), licensed MIT. It adds 74 tokens to every session and 1,806 once invoked, about $0.0004 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.
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-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…
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.
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…
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…
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。.