Catalog
obra/using-superpowers

obra

using-superpowers

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

NewUpdated Sep 9, 2026

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.

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:

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

Files6
6 files · 14.8 KB

Select a file to preview

Overall Score

88/100

Grade

A

Excellent

Grades are signals, not a certification. Always review a skill yourself before use.

Safety

92

Quality

87

Clarity

92

Completeness

81

Summary

This is a meta-skill that instructs AI agents to check for and invoke relevant skills before responding to any user request. It establishes a mandatory workflow: skill lookup → skill invocation → action. The skill includes platform-specific tool mappings for Codex, Pi, Hermes Agent, Gemini CLI, and Antigravity, enabling agents to adapt skill instructions to available capabilities on different harnesses.

Detected Capabilities

skill lookup and invocationplatform detectionreference file readingtool mapping lookupsubagent dispatch (via referenced skills)task tracking (via referenced skills)

Trigger Keywords

Phrases that agents use to match this skill to user intent.

invoke skillskill workflowmulti-agent setupplatform integrationagent best practices

Use Cases

  • Establish skill-first workflow discipline across conversation startups
  • Enable agents to discover and invoke applicable skills automatically
  • Provide platform-specific tool mappings for multi-harness environments
  • Prevent agents from skipping skills through rationalization or overlooking
  • Route agents to correct task-execution skills (brainstorming, debugging) before implementation

Quality Notes

  • Excellent clarity — red flags table explicitly lists rationalization patterns agents commonly use to avoid skill invocation; this makes the instruction unambiguous
  • Strong pedagogical structure: establishes the rule, explains priority (process skills first), flags rationalization traps, provides platform-specific mappings
  • Frontmatter appropriately scoped with `<SUBAGENT-STOP>` tag to prevent accidental misuse in sandboxed contexts
  • Platform mappings are comprehensive and well-organized by harness (Codex, Pi, Hermes, Gemini, Antigravity); each reference file is self-contained and actionable
  • All referenced support files are present in the manifest (6 reference files: pi-tools.md, codex-tools.md, gemini-tools.md, hermes-tools.md, antigravity-tools.md, plus LICENSE)
  • Instruction priority hierarchy clearly stated: user instructions > skills > default behavior
  • Edge case handling: covers subagent detection, detached HEAD state (Codex reference), fallback mechanisms for missing tools (Hermes reference)
Model: claude-haiku-4-5-20251001Analyzed: Sep 9, 2026

Reviews

Add this skill to your library to leave a review.

No reviews yet

Be the first to share your experience.

Version History

  1. v2.1

    Content updated

    ✦ AIRemoves priority hierarchy documentation and simplifies skill invocation rule; reorganizes platform references and reduces enforcement language.

    2026-09-09

    LATEST
  2. v2.0

    Contract changed: description

    ✦ AIAdds multi-platform tool reference files (Codex, Gemini, PI, Antigravity) and shifts from naming tools by platform to action-oriented language. Documentation and flowchart refined for clarity.

    triggering2026-06-28

    View This Version
  3. v1.0

    2026-05-02

    View This VersionInitial version

Use obra/using-superpowers in your dev environment

Command Palette

Search for a command to run...