using-superpowers
This skill teaches agents to systematically discover and invoke specialized skills from a local repository at the start of each new task. Use it to ensure an agent applies the most appropriate skill to any problem, reducing errors and improving execution quality by following the principle that missing an applicable skill is costlier than loading unnecessary ones.
git clone --depth 1 https://github.com/ArchieIndian/openclaw-superpowers /tmp/using-superpowers && cp -r /tmp/using-superpowers/skills/core/using-superpowers ~/.claude/skills/using-superpowersSKILL.md
# Using 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:
1. Review available skills (check `~/.openclaw/extensions/superpowers/skills/`)
2. Ask: "Does any skill match what I'm about to do?"
3. If yes → load and follow the skill exactly
4. 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
1. **User instructions** — always highest priority
2. **Skills** — override default behavior when applicable
3. **Default behavior** — fallback when no skill applies
## Announcing Skill Usage
When you invoke a skill, say so:
> "Using `brainstorming` to explore approaches before writing code."
> "Using `systematic-debugging` to 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-handoff` and `agent-self-recovery` matter 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-management` firstSyncs agent daily memory and MEMORY.md to an Obsidian vault so notes are human-browsable. Use nightly or on demand.
Structured ideation before any implementation. Use when starting any non-trivial task.
Scaffolds and validates new superpowers skills. Use when creating a new skill for this repository.
Executes plans task-by-task with verification. Use when implementing a plan.
Triggers a secondary verification pass for any agent output containing factual claims, numbers, dates, or named entities before the output is acted on
Crawls a new codebase to infer stack, conventions, and key invariants, then generates a PROJECT.md context file for the agent
Handles PR review feedback by fetching comments, grouping issues, fixing one group at a time, and verifying before replies.
Detects skill name shadowing and description-overlap conflicts that cause OpenClaw to trigger the wrong skill or silently ignore one when two skills compete for the same intent.