Skip to content
Skills Library
AI & agents · Planning

using-superpowers

/using-superpowers

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

Licence
MIT
Last repository change
27.07.2026

Assessment and security

90/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content25 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
7
Scripts
0
HTML comments
0
URLs in SKILL.md
0
Deprecation

No signals detected. Repository changed on 27.07.2026, without references to retired models or APIs.

Licence

MIT, open: use and modify while retaining author attribution.

What it does and when to use it

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

Original author description

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

How it works

  1. The Rule
  2. Skill Priority
  3. Red Flags
  4. Production-Grade Doctrine
  5. Capturing Decisions
  6. Beads
  7. Skill Name Resolution
  8. Platform Adaptation
  9. Asking the User
  10. User Instructions
Original SKILL.md headings · 82 lines, 798 words
SKILL.md preview
---
name: using-superpowers
description: Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions
---

<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, track it with beads (see Beads below) — TodoWrite is forbidden.

## Skill Priority

Process skills come first — they set the approach, implementation skills carry it out. Implementation is **spec-backed**: it starts from an approved spec or plan, and you state the file you are working from before the first edit.

- "Let's build X" → beads-superpowers:brainstorming first, then implementation skills.
- "Fix this bug" → beads-superpowers:systematic-debugging first, then domain skills.
- No spec or plan file yet, and it's more than a typo? Brainstorm before you edit.

## Red Flags

These thoughts mean STOP—you're rationalizing:

| Thought | Reality |
|---------|---------|
| "I need more context first" / "let me explore the codebase first" / "I can check git/files quickly" / "let me gather information first" / "I'll just do this one thing first" | Skills tell you HOW. Check BEFORE doing anything. |
| "This is just a simple question" / "this doesn't need a formal skill" / "this doesn't count as a task" / "the skill is overkill" | Action = task. If a skill exists, use it. Simple things become complex. |
| "I remember this skill" | Skills evolve. Read current version. |
| "This feels productive" | Undisciplined action wastes time. Skills prevent this. |
| "I know what that means" | Knowing the concept ≠ using the skill. Invoke it. |
| "This bead is specified enough — I'll just implement it" | **Spec-backed**: name the spec/plan file, or brainstorm first. |

## Production-Grade Doctrine

Treat every project as a production system with real users, no matter how small it looks. You MUST NOT silently take a shortcut, descope a required behavior/edge-case, or accept a material-risk trade-off — surface it and let your human partner decide. You MUST NOT weaken, bypass, or remove a security control or introduce a vulnerability; a security regression is never acceptable, even for a deadline.

## Capturing Decisions

When a decision is hard to reverse, surprising without context, and a genuine trade-off, you MUST offer to record an ADR in `docs/decisions/` (the user confirms; never auto-create). Bias toward offering rather than skipping. Routine clarifications and scope questions don't qualify.

## Beads

`bd` (beads) is the task tracker for ALL work — TodoWrite is forbidden, as are TaskCreate and markdown TODOs. Only the orchestrating agent manages beads — subagents never touch them. Include bead IDs in commit messages. If beads context wasn't injected this session, run `bd prime`. Session close = land the plane: `bd close` → `bd dolt push` → `git push`.

## Skill Name Resolution

Skill references in these skills use the canonical namespaced form
`beads-superpowers:<skill>`. Depending on install channel, your skill list may
show them bare (`brainstorming`) or namespaced (`beads-superpowers:brainstorming`)
— they are the same skills. Invoke whichever form your skill list shows; if a
reference errors as unknown, match it to the closest name in your list and
retry with that.

## Platform Adaptation

If your harness appears here, read its reference file for special instructions:

- Codex: `references/codex-tools.md`
- OpenCode: `references/opencode-tools.md`
- Copilot CLI: `references/copilot-tools.md`
- Pi: `references/pi-tools.md`
- Antigravity: `references/antigravity-tools.md`
- Gemini: `references/gemini-tools.md`

## Asking the User

When a skill says to ask the user or present options: use your harness's structured question tool if it has one (multiple-choice with an "Other" escape); if it doesn't, print the options as a numbered list in plain text and STOP for the user's reply. If the tool errors, or an answer comes back skipped, dismissed, or auto-resolved (headless and auto modes do this), treat it as NO answer — never as consent: fall back to numbered plain text and stop. JSON question blocks in skills show Claude Code's schema — render the same content through your tool's shape.

## User Instructions

User instructions (CLAUDE.md, AGENTS.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 in this package (7)
  • SKILL.md 5 KB
  • references/antigravity-tools.md 1 KB
  • references/codex-tools.md 2 KB
  • references/copilot-tools.md 1 KB
  • references/gemini-tools.md 5 KB
  • references/opencode-tools.md 2 KB
  • references/pi-tools.md 1 KB

Versions

RepositoryScoreLicence
This page · dollardill/beads-superpowers90MIT
coco-research/coco100MIT
osmontero/opencode-skills100MIT
seaworld008/commonly-used-high-value-skills100MIT
chinkan/RustFox100MIT
VoDaiLocz/kilo-kit-mcp100Apache-2.0
sickn33/agentic-awesome-skills100MIT
liyunxuanyu/dsh-zcode-port100MIT
LiHongwei-cn/lihongwei-cn100MIT

Database snapshot: 13.11.2026 · package version 2011cfbd4aa5 (SHA-256 digest of the entire package)

Downloads in the last 30 days: 0 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 90using-kisune
    Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions
  • 100using-science-superpowers
    Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions
  • 90next-level-agent
    Use when starting any conversation - establishes how to find and use skills, requiring skill invocation before ANY response including clarifying questions
  • 100using-werkstatt
    Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions
  • 100using-ultraship
    Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions
  • 100using-systematic
    Use when starting any conversation - establishes how to find and use skills, requiring skill tool invocation before ANY response including clarifying questions

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.