Openclaw-superpowers long-running-task-management

Breaks multi-hour tasks into checkpointed stages with resume capability. Use when a task is expected to take more than 30 minutes or multiple sessions.

install

source · Clone the upstream repo

git clone https://github.com/ArchieIndian/openclaw-superpowers

Claude Code · Install into ~/.claude/skills/

T=$(mktemp -d) && git clone --depth=1 https://github.com/ArchieIndian/openclaw-superpowers "$T" && mkdir -p ~/.claude/skills && cp -r "$T/skills/openclaw-native/long-running-task-management" ~/.claude/skills/archieindian-openclaw-superpowers-long-running-task-management && rm -rf "$T"

OpenClaw · Install into ~/.openclaw/skills/

T=$(mktemp -d) && git clone --depth=1 https://github.com/ArchieIndian/openclaw-superpowers "$T" && mkdir -p ~/.openclaw/skills && cp -r "$T/skills/openclaw-native/long-running-task-management" ~/.openclaw/skills/archieindian-openclaw-superpowers-long-running-task-management && rm -rf "$T"

manifest: skills/openclaw-native/long-running-task-management/SKILL.md

source content

Long-Running Task Management

State file:

~/.openclaw/skill-state/long-running-task-management/state.yaml

When to Use

Task estimated at more than 30 minutes
Task will span multiple sessions
Task modifies many files across multiple directories

Starting a Task

Write initial state to the state file:
- ```
task_id
```
  : short kebab-case name
- ```
status: in_progress
```
- ```
description
```
  : one-sentence goal
- ```
stages
```
  : ordered list with
```
status: pending
```
  for each
- ```
started_at
```
  : current timestamp
Begin the first stage

At Each Checkpoint

Complete the stage
Run tests/verification
Update state file: mark stage
```
status: complete
```
, write
```
checkpoint
```
(what's stable now), write
```
next_action
```
(first thing to do on resume), update
```
last_updated
```
Commit progress to git if applicable

Resume After Interruption

Read the state file
Check
```
status
```
and
```
next_action
```
Continue from the next
```
pending
```
stage — do NOT start over

Completion

Update state:
```
status: complete
```
, final
```
checkpoint
```
Run full verification

Cron Wakeup Behavior

On each 15-minute wakeup:

Read state file
If
```
status: in_progress
```
and
```
last_updated
```
is stale (>30 min ago): log a checkpoint update to daily memory
If
```
status: complete
```
or no active task: skip