Agent Skill
Using Superpowers skill
using-superpowersSuperpowersskills/using-superpowers/SKILL.md
Use when starting any conversation - establishes how to find and use skills, requiring skill invocation before ANY response including clarifying questions
always on
28 tokname + description
once used
700 tokSKILL.md body
bundled files
717 KB
installs
269kskills.sh
Install the Using Superpowers skill
Skills CLI (Claude Code, Codex, Cursor and others)
npx skills add https://github.com/obra/superpowers --skill using-superpowers
Claude Code, by hand (all projects)
git clone --depth 1 https://github.com/obra/superpowers.git /tmp/superpowers mkdir -p ~/.claude/skills cp -R /tmp/superpowers/skills/using-superpowers ~/.claude/skills/using-superpowers
For one project only, copy the folder into .claude/skills/ in that project instead. The agent picks it up when a task matches its description.
What it costs your context
Agent Skills load in three steps. Tokens counted with the o200k tokenizer; your model's count will differ a little.
| When | What loads | Cost |
|---|---|---|
| Every session | Name and description | 28 tok |
| When the agent uses it | The SKILL.md instructions | 700 tok |
| Only if opened | 7 bundled files (17 KB) | varies |
Until it is used, using-superpowers costs about 49× less than the median MCP server we measured (1,362 tokens on every turn). Installing all 15 skills from obra/superpowers would load 489 tokens of descriptions. Skills vs MCP study
Checks
Our checks found nothing to flag: it follows the Agent Skills specification's naming and size guidelines and doesn't pipe downloads into a shell.
Checked 2026-10-22 · method
What's inside
The headings of its SKILL.md. Read the full file on GitHub.
- The Rule
- Skill Priority
- Red Flags
- Platform Adaptation
- User Instructions
More skills from obra/superpowers
- brainstormingobra/superpowers
You MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or planning anything new, in software or out of it (a talk, a business, a renovation).
401k446 tok idle · 3,062 in use - systematic-debuggingobra/superpowers
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes
303k221 tok idle · 2,175 in use - writing-plansobra/superpowers
Use when you have a spec or requirements for a multi-step task, before touching code
281k21 tok idle · 2,284 in use - requesting-code-reviewobra/superpowers
Use when completing tasks, implementing major features, or before merging to verify work meets requirements
260k22 tok idle · 660 in use - test-driven-developmentobra/superpowers
Use when implementing any feature or bugfix, before writing implementation code
257k17 tok idle · 2,316 in use - verification-before-completionobra/superpowers
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always
249k43 tok idle · 803 in use - executing-plansobra/superpowers
Use when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available
241k35 tok idle · 4,228 in use - subagent-driven-developmentobra/superpowers
Use when executing implementation plans with independent tasks in the current session
235k17 tok idle · 4,404 in use