ZJU-REAL/Easel / skills/builtin/skill-record-card
skill-record-card
Verified项目内容记录卡片:以访谈方式陪用户把"当天真做成的一件事"沉淀成四段卡片(核心要点/机理/具体方法/使用范围)。以用户亲口表达为底稿——AI 一次只问一个问题、追问到具体,并补充观点、提炼拔高、指出认知盲点;AI 补充显式标注、经用户确认采纳后才落盘。卡片是用户心里"看不见的稿子",登记为 general 层产物供分享消费,可随新理解迭代版本。当用户说"写卡片"、"记录卡片"、"记录今天做的事"、"帮我沉淀今天做的事"、"经验卡片"、"每日记录"时触发。边界:已发布内容数据分析用 skill-content-postmortem;画像偏好沉淀用 skill-profile-manager。
| File | Kind | Size |
|---|---|---|
| EASEL-META.md | markdown | 1.5 KB |
| SKILL.md | skill md | 7.1 KB |
| references/interview-guide.md | markdown | 6.2 KB |
| scripts/card.py | script | 21.2 KB |
| tests/test1.expected | other | 95 B |
| tests/test1.prompt | other | 79 B |
EASEL-META.md
View on GitHub# Easel SKILL 元数据
| 字段 | 值 |
|------|-----|
| **SKILL 名称** | skill-record-card |
| **所属层** | general |
| **来源类型** | 自研(来自用户提出的创作方法论) |
| **原始来源** | Easel 自研;方法论来自用户阐述的"做事→思考→记录→分享→改进"循环:背稿讲不好的原因、网红追流量 2-3 年耗尽的原因、记录卡片四段结构(核心要点/机理/具体方法/使用范围) |
| **参考项目** | 无 |
| **许可** | 项目内自研 |
## 确定性脚本
| 脚本 | 用途 | 依赖 |
|------|------|------|
| `scripts/card.py` | 卡片的确定性落盘与版本管理:new(新建 v1)/ revise(追加新版本、旧版保留)/ list / show / selftest。不生成内容,只存档用户确认稿 | 复用 `skills/shared/scripts/output_paths.py` 的 `validate_output_path`,纯标准库 |
写入使用主题卡片目录独占锁和原子替换;竞争写入报错而不覆盖历史。读取仅接受卡片编号,
拒绝符号链接和目录外文件。字段、日期及 JSON 类型在写入前校验;多行摘录与字段内
Markdown 结构在版本升级中保留。未确认访谈草稿不由脚本持久化。
> 2026-10-21 新增。关键设计约束:卡片以用户亲口表达为底稿,AI 主动补充观点、
> 提炼拔高、指出认知盲点,但所有 AI 贡献显式记录于"AI 补充与提炼"区、
> 经用户确认采纳后才落盘,用户是内容终审;脚本强制五字段非空,拒绝空壳卡片。
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |