Task Parsing
- 1 installs
- 1 repo stars
- Updated January 12, 2026
- aviz85/claude-tasks
task-parsing is a Claude skill that converts natural-language work descriptions into structured markdown task lines with priority, project, tags, and a time estimate.
About
This skill parses a plain-language description of work into a structured markdown task line with project, tags, priority, and a time estimate. A developer uses it when adding tasks or processing an inbox so free-form notes become trackable items. It also decides which file the task belongs in based on due-date phrases like today, this week, or someday.
- Converts natural-language descriptions into a structured task line with @project, #tag, !priority and ~estimate
- Maps urgency words to high/medium/low priority and complexity hints to time estimates
- Routes tasks to today.md, backlog, or someday.md based on due-date phrases
Task Parsing by the numbers
- 1 all-time installs (skills.sh)
- Ranked #2,473 of 3,280 Productivity & Planning skills by installs in the Skillselion catalog
- Data as of Jul 28, 2026 (Skillselion catalog sync)
task-parsing capabilities & compatibility
- Use cases
- planning · project management
What task-parsing says it does
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.
Convert natural language into structured task format.
npx skills add https://github.com/aviz85/claude-tasks --skill task-parsingAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 1 |
|---|---|
| repo stars | ★ 1 |
| Last updated | January 12, 2026 |
| Repository | aviz85/claude-tasks ↗ |
What it does
Turn a spoken or typed description of work into a structured task with priority, estimate, project, and tags.
Who is it for?
Capturing loose task descriptions into a consistent trackable format
When should I use this skill?
Adding tasks, processing an inbox, or when a user describes work to be done
What you get
A formatted checkbox task with project, tags, priority, and estimate, routed to the right file.
- Structured markdown task line
- Destination-file routing (today/backlog/someday)
By the numbers
- 7-step processing sequence from core action to destination file
- 3 priority tiers (high/medium/low)
Files
Task Parsing
Convert natural language into structured task format.
Task Format
- [ ] Task description @project #tag !priority ~estimateParsing 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-namementions - Infer from context: "for the API project" →
@api - Work-related defaults to
@work - Personal items get
#personaltag
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
Related skills
Grill MeHave an agent relentlessly pressure-test their plan or design until every decision branch is resolved and shared understanding is reached.691k196kGrill With DocsPressure-test architecture decisions against their live codebase and living documentation before writing production code.585k196k
Lark CalendarLet their coding agents read, create, and manage events inside Lark (Feishu) Calendar directly from natural language instructions.493kLark ImLet their coding agent send instant notifications, post updates, and receive commands directly inside Lark (Feishu) workspaces.493kLark ContactLet their AI coding agents read and write contacts, send messages, and manage user data inside Lark (Feishu).493kLark AttendanceAutomatically fetch and report daily attendance data from Lark (Feishu) into their own tools or agents.493kFAQ
What format does task-parsing output?
A markdown checkbox line: '- [ ] Task description @project #tag !priority ~estimate'.
How does it choose priority?
It maps urgency words: 'urgent/ASAP/critical/blocking' become !high, 'important/should/need to' become !medium, and 'when possible/eventually' become !low.