Skip to main content

task-parsing

Parses natural language into structured tasks with priority, due date, project, and tags. Use when adding tasks, processing inbox, or when user describes work to be done.

跳到安装

来源信息

仓库
aviz85/claude-tasks
最近来源活动
2026年1月4日 10:02
检测到的 SKILL.md 语言
英语
星标
1
分支
1

安装方式

默认使用会先检查来源的 Prompt;你也可以切换为直接命令,或下载本地副本。

检查来源文件

决定是否安装前,请先阅读 SKILL.md,以及 SkillsMP 当前展示的配套文件。

正在显示 SKILL.md

SKILL.md
来源说明 · 只读预览
name
task-parsing
description
Parses natural language into structured tasks with priority, due date, project, and tags. Use when adding tasks, processing inbox, or when user describes work to be done.
# Task Parsing Convert natural language into structured task format. ## Task Format ``` - [ ] Task description @project #tag !priority ~estimate ``` ## Parsing Rules ### Priority Detection | Input Pattern | Priority | |--------------|----------| | "urgent", "ASAP", "critical", "blocking" | `!high` | | "important", "should", "need to" | `!medium` | | "when possible", "eventually", "nice to have" | `!low` | ### Time Estimation | Input Pattern | Estimate | |--------------|----------| | "quick", "small", "minor" | `~15m` | | "short", "simple" | `~30m` | | "medium", "regular" | `~1h` | | "large", "significant" | `~2h` | | "big", "complex", "deep work" | `~4h` | ### Due Date Extraction | Input Pattern | Action | |--------------|--------| | "today", "EOD" | Add to today.md | | "tomorrow" | Add to today.md with note | | "this week", "by Friday" | Add to backlog, Do First | | "next week", "soon" | Add to backlog, Schedule | | "someday", "eventually" | Add to someday.md | ### Project Detection - Look for explicit `@project-name` mentions - Infer from context: "for the API project" → `@api` - Work-related defaults to `@work` - Personal items get `#personal` tag ### Tag Extraction Common tags to apply: - `#code` - Programming tasks - `#docs` - Documentation - `#meeting` - Meetings and calls - `#research` - Research and learning - `#bug` - Bug fixes - `#feature` - New features - `#review` - Code/document reviews ## Examples **Input:** "Review John's PR for the auth feature, it's blocking the release" **Output:** `- [ ] Review John's PR for auth feature @work #review #code !high ~30m` **Input:** "Eventually learn Kubernetes" **Output:** `- [ ] Learn Kubernetes #learning !low ~4h` → someday.md **Input:** "Need to fix the login bug today" **Output:** `- [ ] Fix login bug @work #bug !high ~1h` → today.md ## Processing Steps 1. Extract the core action (verb + object) 2. Detect priority from urgency words 3. Estimate time from complexity hints 4. Extract or infer project 5. Add relevant tags 6. Determine destination file 7. Format as markdown checkbox
在 GitHub 查看