task
Scannednpx machina-cli add skill lsnackerman/raw-clauding-skills/task --openclaw/task - Create a Living Task Doc
Create a task doc from natural language. A thinking log that accumulates context, decisions, and observations over time.
What To Do
- Parse the request — understand what work is being described
- Figure out metadata — topic, tags, priority
- Write the file — with the structure below
- Note the connection — this doc is where
/wrapupdates and/sessioncaptures link back to
Task Doc Structure
---
tags: [{tag1}, {tag2}]
priority: {P0|P1|P2|P3}
status: todo
created_date: {YYYY-MM-DD}
---
# {Title}
## WHAT
{Description — why this matters, context, what triggered this}
---
## WHO
{People involved — names, roles, current status}
---
## HOW
### Pending (Execute Next)
- [ ] {First action item}
### Completed (Append in order of completion)
<!-- Move items here when done — newest at bottom -->
---
## OBSERVATIONS (Cumulative)
*Patterns, friction, questions worth keeping — from you or your AI*
<!-- Add observations as they emerge across sessions -->
---
## SESSION INDEX
<!-- Pointers to captured sessions related to this work -->
<!-- Format: **Session N (YYYY-MM-DD)**: [filename] — one-liner of what happened -->
---
Why This Structure
Most task trackers give you a title and a checkbox. This gives you a thinking log.
- WHAT isn't just a description — it's the WHY that keeps you oriented when you pick this up days later
- HOW splits pending from completed so you always know where you left off
- OBSERVATIONS is where the real value accumulates — patterns you noticed, friction you hit, questions that emerged
- SESSION INDEX links to your captured sessions so you can trace how the thinking evolved
When a Task Is Done
Archive completed tasks to tasks/_done/ to preserve the thinking. The task doc is a record of how you got somewhere — decisions, dead ends, observations. That's worth keeping even after the work is finished. /wrap handles this when you mark a task done.
Skill Check (After Every Task Creation)
Quick scan: anything about this task creation that felt off or could be smoother?
- Was the WHAT section clear enough for future you?
- Did the structure feel right for this type of work?
- Was anything missing that you'd want next time you pick this up?
If yes → update this skill now. The improvement compounds.
If no → move on. Not every task teaches something.
Source
git clone https://github.com/lsnackerman/raw-clauding-skills/blob/main/task/SKILL.mdView on GitHub Overview
This skill converts natural language requests into a living task document that tracks work, context, decisions, and observations over time. It supports capturing a new project or turning a request into a thinking log that preserves context across sessions.
How This Skill Works
Process steps: 1) Parse the request to identify the work described. 2) Derive metadata such as topic, tags, and priority, and create the YAML front matter with created_date. 3) Write the task file with the structured sections WHAT, WHO, HOW, OBSERVATIONS, and SESSION INDEX, so progress can be linked with wrap updates and context captured across sessions.
When to Use It
- You want to track work as a living document rather than a static note
- You need to capture a new project from a natural language brief
- You want a thinking log that accumulates context, decisions, and observations across sessions
- You require a clear Pending and Completed flow in HOW to show progress
- You want to link sessions and updates via SESSION INDEX and wrap integration
Quick Start
- Step 1: Parse the natural language request to identify the work to be done
- Step 2: Create the file front matter with tags, priority, status, and created_date, then fill WHAT, WHO, HOW, OBSERVATIONS, and SESSION INDEX
- Step 3: As work proceeds, add sessions via /session, move items in HOW from Pending to Completed, and use /wrap to archive when done
Best Practices
- Parse the request clearly to identify the core work and outcomes
- Fill metadata with topic, relevant tags, and a priority (P0–P3)
- Use the front matter and the WHAT, WHO, HOW, OBSERVATIONS, SESSION INDEX structure consistently
- Update OBSERVATIONS after each session to capture patterns, friction, and questions
- Archive completed tasks to tasks/_done/ when finished and preserve thinking with wrap
Example Use Cases
- A product feature kickoff documented as a living task to track decisions and next actions
- A content campaign or blog series managed as a task doc with ongoing observations
- An experiment or research task recording setup, results, and lessons learned
- A website redesign project with milestones, stakeholders, and decision history
- An internal process improvement task capturing decisions, outcomes, and future steps
