Index of every page on this site: llms.txt
All skills
obra avatar

/using-superpowers

@22f0b46 official
by Jesse Vincentobra/superpowers312k stars
27,751
Run it yourself

Use when starting any conversation - establishes how to find and use skills, requiring skill invocation before ANY response including clarifying questions

Use this Skill: https://skilld.dev/gh/obra/superpowers/using-superpowers

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

SKILL.md

≈43 tokens for metadata: the name and description. ≈748 when used: this file. ≈4.4k more on demand in 7 files.

Description uses 2.2% of example budget

Before choosing a Skill, your Agent reads its name and description. All available Skills share that space.

  • A shorter description leaves more room for other Skills. This entry exceeds our 1% size suggestion.

In our Claude Code example, all Skill names and descriptions share 8,000 characters. This Skill uses ≈174 characters, or 2.2%.

The 1% threshold is a size suggestion. Longer descriptions can still fit.

Your model, settings, and other Skills decide how much text your Agent can read.

Example settings and source

The example uses a 200k-token context and default Claude Code settings. The count includes the name, description, separators, and when_to_use when present. Codex also counts local file paths.

Skit's source and limits: Codex 0.160.1, Claude Code 2.1.292.

<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.md
  • Codex: references/codex-tools.md
  • Pi: references/pi-tools.md
  • Antigravity: references/antigravity-tools.md
  • Hermes Agent: references/hermes-tools.md
  • Muse: 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.

Source: SKILL.md on GitHub

Skill behaviors

No rule matched.

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

Third-party checks

1 warning1mo5 checks · Risk MEDIUM
  • Gen Agent Trust Hub1mo

    The skill uses imperative framing and aggressive instructions to force the agent to prioritize skill invocation over its own internal reasoning and safety filters. It also provides instructions for modifying local configuration files to enable specific platform features.

  • Socket1mo

    No alerts

  • Snyk1mo

    Risk: LOW · No issues

  • Runlayer8mo

    2 files scanned · No issues

  • ZeroLeaks6mo

    Score: 93/100 · 2 sections analyzed

Provenance

Signed by skilld at 22f0b46. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 5 days ago.

Activeupdated 2 months ago

Topics

  • skills
  • meta
  • agent-setup
  • workflow
  • claude

README badge

README badge for obra/superpowers/using-superpowers

What it does

Establishes the foundational rule for skill-driven agent behavior: invoke relevant skills before any response or action, even with minimal confidence. Clarifies priority hierarchy (user instructions > skills > default system prompt) and provides decision frameworks for when and how to load skills across Claude Code, Copilot CLI, and other platforms.

Generated from the current SKILL.md.

Frequently asked

When should I invoke this skill?
Invoke it at the start of any conversation before responding to the user, even if you think there's only a 1% chance a skill might apply to the task. Skill checking happens before clarifying questions or exploration.
Does this skill override my own instructions?
No. User instructions (in CLAUDE.md, GEMINI.md, AGENTS.md, or direct requests) always take precedence over skills. Skills override default system prompt behavior only where they don't conflict with explicit user direction.
What happens if I invoke a skill and it turns out not to apply?
That's fine. You don't need to use it. The point is to check first before taking action, not to force every skill into every task.
How do I load a skill once I've decided to use it?
Use the Skill tool (Claude Code), skill tool (Copilot CLI), or activate_skill tool (Gemini CLI). Never use Read to access skill files directly—the tool loads and presents the content to you.
If multiple skills could apply, which should I use first?
Process skills (brainstorming, debugging) come before implementation skills. Use them to determine your approach, then invoke domain-specific skills to guide execution.

Generated from the current SKILL.md. These answers refresh after source changes.