About using-superpowers
An OpenClaw skill that directs agents to check available skills at the start of each task and follow any relevant one. It emphasizes proactive skill use and explains priority and announcement practices.
Key features
- 01Check available skills for each task
- 02Load and follow relevant skills
- 03Apply an instruction priority order
- 04Announce invoked skills
- 05Recheck skills in persistent sessions
Use cases
- 01Determine whether a skill applies before starting work
- 02Guide skill use across tasks in persistent sessions
Install
Copy the command and run it in a terminal.
npx skills add https:/ / github.com/ archieindian/ openclaw-superpowers --skill using-superpowersAfter installing, type/using-superpowersin Claude Code to confirm it loaded.
Details
From the project READMEUsing Superpowers
The Core Rule
If there is even a 1% chance a skill applies to the current task, invoke it.
Skills are cheap to load. Failing to use an applicable skill is expensive.
How to Find Skills
At the start of every new task:
- Review available skills (check
~/.openclaw/extensions/superpowers/skills/) - Ask: "Does any skill match what I'm about to do?"
- If yes → load and follow the skill exactly
- If no → proceed with default behavior
In OpenClaw's persistent agent context, check skills at the start of every new task, not just new conversations. A long-running session may handle many different task types.
Decision Flowchart
New task received
↓
Does any skill apply? (even 1% chance → YES)
↓
YES → Announce: "Using [skill-name] to [purpose]"
Load skill file
Follow instructions exactly
↓
Complete or hand off cleanly
NO → Proceed with default agent behavior
Priority Hierarchy
- User instructions — always highest priority
- Skills — override default behavior when applicable
- Default behavior — fallback when no skill applies
Announcing Skill Usage
When you invoke a skill, say so:
"Using
brainstormingto explore approaches before writing code." "Usingsystematic-debuggingto diagnose this error."
This keeps the human informed and lets them redirect if needed.
OpenClaw-Specific Notes
- In persistent sessions, skills should be checked at the start of each new task, not just session start
- Skills around
task-handoffandagent-self-recoverymatter more in OpenClaw than in session-based tools — don't skip them - If a task will take more than ~20 minutes, check
long-running-task-managementfirst