Using Superpowers
Jesse Vincent (obra)CommunityCreated by Jesse Vincent (obra)
- Skill
- Meta (authoring, orchestration, planning, memory)
- Agent tooling
- MIT
- No issues found
AutoGineer summary
Written by AutoGineer from the skill’s own files, not by the author
The using-superpowers skill establishes a strict operational framework for AI agents. It mandates that agents must check for and invoke applicable skills before taking any action, including asking clarifying questions or performing initial research. This protocol is designed to prevent rationalization and ensure that agents consistently apply established methodologies, workflows, and best practices to every task. It includes specific guidance on skill priority, handling red flags that indicate potential avoidance of established procedures, and platform-specific adaptations for various agent harnesses.
What it does
- Enforces the mandatory invocation of relevant skills before any response or action.
- Requires agents to prioritize process-oriented skills over implementation tasks.
- Provides a checklist of red flags to identify and correct rationalization behaviors.
- Integrates with platform-specific tool mappings for various agent environments.
- Ensures that user instructions take precedence over default skill behaviors.
When to use it
- At the start of every new conversation or user interaction.
- Before initiating any task, including simple questions or information gathering.
- When determining the sequence of operations for complex, multi-step projects.
- Whenever there is a possibility that an existing skill might apply to the current request.
Advantages
- Promotes consistent and disciplined agent behavior across different tasks.
- Reduces the likelihood of skipping critical planning or debugging steps.
- Standardizes the interaction model between the agent and the user.
- Provides clear guidance on how to handle conflicting instructions or complex workflows.
Usage examples
- “Can you help me fix this bug in the login module?”
- The agent identifies the relevant debugging skill, announces 'Using systematic-debugging to address the login bug', and follows the skill's prescribed workflow before touching any code.
- “What is the current status of the project?”
- The agent checks for a project management skill, announces its intent to use it, and proceeds to gather information according to the skill's defined process.
Install
Download the skill as a ZIP:
https://autogineer.com/agent-skills/obra/using-superpowers/downloadUnzip it into the cross-client skills folder of your project:
mkdir -p .agents/skills && unzip using-superpowers.zip -d .agents/skills
Documentation by Jesse Vincent (obra)
<SUBAGENT-STOP> If you were dispatched as a subagent to execute a specific task, ignore this skill. </SUBAGENT-STOP>
<EXTREMELY-IMPORTANT> If you think there is even a 1% chance a skill might apply to what you are doing, you ABSOLUTELY MUST invoke the skill.
IF A SKILL APPLIES TO YOUR TASK, YOU DO NOT HAVE A CHOICE. YOU MUST USE IT.
This is not negotiable. You cannot rationalize your way out of this. </EXTREMELY-IMPORTANT>
The Rule
Invoke relevant or requested skills BEFORE any response or action — including clarifying questions, exploring the codebase, or checking files. If it turns out wrong for the situation, you don't have to use it.
Before entering plan mode: if you haven't already brainstormed, invoke the brainstorming skill first.
Then announce "Using [skill] to [purpose]" and follow the skill exactly. If it has a checklist, create a todo per item.
Skill Priority
When multiple skills apply, process skills come first — they set the approach, then implementation skills (frontend-design, etc.) carry it out. Brainstorming and systematic-debugging are Superpowers' most common process skills, but the rule holds for any of them.
"Let's build X" → superpowers:brainstorming first, then implementation skills.
"Fix this bug" → superpowers:systematic-debugging first, then domain skills.
Red Flags
These thoughts mean STOP—you're rationalizing:
| Thought | Reality |
|---|---|
| "This is just a simple question" | Questions are tasks. Check for skills. |
| "I need more context first" | Skill check comes BEFORE clarifying questions. |
| "Let me explore the codebase first" | Skills tell you HOW to explore. Check first. |
| "I can check git/files quickly" | Files lack conversation context. Check for skills. |
| "Let me gather information first" | Skills tell you HOW to gather information. |
| "This doesn't need a formal skill" | If a skill exists, use it. |
| "I remember this skill" | Skills evolve. Read current version. |
| "This doesn't count as a task" | Action = task. Check for skills. |
| "The skill is overkill" | Simple things become complex. Use it. |
| "I'll just do this one thing first" | Check BEFORE doing anything. |
| "This feels productive" | Undisciplined action wastes time. Skills prevent this. |
| "I know what that means" | Knowing the concept ≠ using the skill. Invoke it. |
Platform Adaptation
If your harness appears here, read its reference file for special instructions:
Claude Code:
references/claude-code-tools.mdCodex:
references/codex-tools.mdPi:
references/pi-tools.mdAntigravity:
references/antigravity-tools.mdHermes Agent:
references/hermes-tools.mdMuse:
references/muse-tools.md
User Instructions
User instructions (CLAUDE.md, AGENTS.md, GEMINI.md, etc, direct requests) take precedence over skills, which in turn override default behavior. Only skip skill workflows or instructions when your human partner has explicitly told you to.
Files
- ATTRIBUTION.mdAdded by AutoGineer867 B
- LICENSELicence file added by AutoGineer1.0 KiB
- SKILL.md3.1 KiB
- references/antigravity-tools.md1.5 KiB
- references/claude-code-tools.md1.4 KiB
- references/codex-tools.md4.7 KiB
- references/gemini-tools.md4.5 KiB
- references/hermes-tools.md1.9 KiB
- references/muse-tools.md1.9 KiB
- references/pi-tools.md1.2 KiB
references/claude-code-tools.md
Claude Code Tool Notes
Claude Code is the reference harness: skills speak its vocabulary
(Agent for a subagent dispatch, todos, Skill). These notes cover the
one place Claude Code can run a plan cheaper than the skills' default
shape. It is opt-in by your human partner and changes nothing the skills
require.
Cheaper orchestration for subagent-driven development
The controller session is the most expensive seat in a
superpowers:subagent-driven-development run: it reads every dispatch
result and every report, and it usually runs on the session's most
capable model. Claude Code supports nested subagents (three layers below
the main conversation by default; CLAUDE_CODE_MAX_SUBAGENT_SPAWN_DEPTH
adjusts it), so the whole loop can run one layer down.
When your human partner asks for it — or has said the session model is too expensive to spend on coordination — dispatch ONE orchestrator subagent on a mid-tier model with the plan path and the instruction to use superpowers:subagent-driven-development end to end. The orchestrator dispatches its own implementers and reviewers per that skill's Model Selection; the workspace and ledger live on disk, so nothing is lost to the extra layer. Its final message must carry the "Rulings I made" list verbatim — that list is how the decisions reach your human partner, and you relay it, not summarize it.
Do this only for a whole plan. Nesting a single task's dispatch buys nothing and adds a seat.
Requirements and compatibility
Works with: Claude Code, Claude apps, OpenAI Codex, GitHub Copilot, Cursor, Gemini CLI, Kiro, OpenCode, Goose, Amp, Roo Code, JetBrains Junie, Factory Droid, Devin (ex-Windsurf), Mistral Vibe, OpenHands, Letta
“Works with” means the tool reads the open Agent Skills format; a skill written for one tool may use features others lack.
Security
No issues found by our static scan· No issues found
A static scan is not a guarantee. Skills are third-party content: review a skill before you let an agent use it.
Attribution and licence
- Created by
- Jesse Vincent (obra)
- Publisher
- Jesse Vincent (obra) (Community)
- Source
- obra/superpowers · skills/using-superpowers · commit 22f0b46
- Licence
- MIT License (redistribution allowed)
- LICENSE (added by AutoGineer from LICENSE)
- ATTRIBUTION.md (written by AutoGineer)
- Synced
AutoGineer is not affiliated with or endorsed by Jesse Vincent (obra) or Jesse Vincent (obra).
Related skills
Handoff
Matt Pocock· Community
Generates a concise handoff document to facilitate seamless transitions between AI agents.
Agent toolingClaude CodeClaude appsOpenAI Codex+14 moreMITGitHub stars of the source repository317.5k
Chief Of Staff
Matt Pocock· Community
A strategic orchestration agent that manages long-term goals by coordinating subagents and maintaining a persistent knowledge wiki.
Agent toolingClaude CodeClaude appsOpenAI Codex+14 moreMITGitHub stars of the source repository317.5k
Ask Matt
Matt Pocock· Community
A central routing skill that helps you identify the correct agent skill or workflow for your current situation.
Agent toolingClaude CodeClaude appsOpenAI Codex+14 moreMITGitHub stars of the source repository317.5k
Claude Handoff
Matt Pocock· Community
Seamlessly transfer your current conversation context to a new background agent.
Agent toolingClaude CodeClaude appsOpenAI Codex+14 moreMITGitHub stars of the source repository317.5k
Executing Plans
Jesse Vincent (obra)· Community
Execute implementation plans inline without subagents, maintaining rigorous progress tracking and verification.
Agent toolingClaude CodeClaude appsOpenAI Codex+14 moreMITLow riskHas scriptsGitHub stars of the source repository314k
Subagent Driven Development
Jesse Vincent (obra)· Community
A structured workflow for executing complex implementation plans by delegating tasks to isolated, specialized subagents with rigorous review gates.
Agent toolingClaude CodeClaude appsOpenAI Codex+14 moreMITLow riskHas scriptsGitHub stars of the source repository314k
Download ZIP
The ZIP holds the skill’s files, its licence files and an ATTRIBUTION.md. Download using-superpowers.zip