using-superpowers
starsforks
How to install using-superpowers?
mvschwarz/openrig/using-superpowers
$npx -y skills add mvschwarz/openrig --skill using-superpowersUse when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions
SKILL.md
| 1 | <EXTREMELY-IMPORTANT> |
| 2 | If you think there is even a 1% chance a skill might apply to what you are doing, you ABSOLUTELY MUST invoke the skill. |
| 3 | |
| 4 | IF A SKILL APPLIES TO YOUR TASK, YOU DO NOT HAVE A CHOICE. YOU MUST USE IT. |
| 5 | |
| 6 | This is not negotiable. This is not optional. You cannot rationalize your way out of this. |
| 7 | </EXTREMELY-IMPORTANT> |
| 8 | |
| 9 | ## How to Access Skills |
| 10 | |
| 11 | **In Claude Code:** Use the `Skill` tool. When you invoke a skill, its content is loaded and presented to you—follow it directly. Never use the Read tool on skill files. |
| 12 | |
| 13 | **In other environments:** Check your platform's documentation for how skills are loaded. |
| 14 | |
| 15 | # Using Skills |
| 16 | |
| 17 | ## The Rule |
| 18 | |
| 19 | **Invoke relevant or requested skills BEFORE any response or action.** Even a 1% chance a skill might apply means that you should invoke the skill to check. If an invoked skill turns out to be wrong for the situation, you don't need to use it. |
| 20 | |
| 21 | ```dot |
| 22 | digraph skill_flow { |
| 23 | "User message received" [shape=doublecircle]; |
| 24 | "About to EnterPlanMode?" [shape=doublecircle]; |
| 25 | "Already brainstormed?" [shape=diamond]; |
| 26 | "Invoke brainstorming skill" [shape=box]; |
| 27 | "Might any skill apply?" [shape=diamond]; |
| 28 | "Invoke Skill tool" [shape=box]; |
| 29 | "Announce: 'Using [skill] to [purpose]'" [shape=box]; |
| 30 | "Has checklist?" [shape=diamond]; |
| 31 | "Create TodoWrite todo per item" [shape=box]; |
| 32 | "Follow skill exactly" [shape=box]; |
| 33 | "Respond (including clarifications)" [shape=doublecircle]; |
| 34 | |
| 35 | "About to EnterPlanMode?" -> "Already brainstormed?"; |
| 36 | "Already brainstormed?" -> "Invoke brainstorming skill" [label="no"]; |
| 37 | "Already brainstormed?" -> "Might any skill apply?" [label="yes"]; |
| 38 | "Invoke brainstorming skill" -> "Might any skill apply?"; |
| 39 | |
| 40 | "User message received" -> "Might any skill apply?"; |
| 41 | "Might any skill apply?" -> "Invoke Skill tool" [label="yes, even 1%"]; |
| 42 | "Might any skill apply?" -> "Respond (including clarifications)" [label="definitely not"]; |
| 43 | "Invoke Skill tool" -> "Announce: 'Using [skill] to [purpose]'"; |
| 44 | "Announce: 'Using [skill] to [purpose]'" -> "Has checklist?"; |
| 45 | "Has checklist?" -> "Create TodoWrite todo per item" [label="yes"]; |
| 46 | "Has checklist?" -> "Follow skill exactly" [label="no"]; |
| 47 | "Create TodoWrite todo per item" -> "Follow skill exactly"; |
| 48 | } |
| 49 | ``` |
| 50 | |
| 51 | ## Red Flags |
| 52 | |
| 53 | These thoughts mean STOP—you're rationalizing: |
| 54 | |
| 55 | | Thought | Reality | |
| 56 | |---------|---------| |
| 57 | | "This is just a simple question" | Questions are tasks. Check for skills. | |
| 58 | | "I need more context first" | Skill check comes BEFORE clarifying questions. | |
| 59 | | "Let me explore the codebase first" | Skills tell you HOW to explore. Check first. | |
| 60 | | "I can check git/files quickly" | Files lack conversation context. Check for skills. | |
| 61 | | "Let me gather information first" | Skills tell you HOW to gather information. | |
| 62 | | "This doesn't need a formal skill" | If a skill exists, use it. | |
| 63 | | "I remember this skill" | Skills evolve. Read current version. | |
| 64 | | "This doesn't count as a task" | Action = task. Check for skills. | |
| 65 | | "The skill is overkill" | Simple things become complex. Use it. | |
| 66 | | "I'll just do this one thing first" | Check BEFORE doing anything. | |
| 67 | | "This feels productive" | Undisciplined action wastes time. Skills prevent this. | |
| 68 | | "I know what that means" | Knowing the concept ≠ using the skill. Invoke it. | |
| 69 | |
| 70 | ## Skill Priority |
| 71 | |
| 72 | When multiple skills could apply, use this order: |
| 73 | |
| 74 | 1. **Process skills first** (brainstorming, debugging) - these determine HOW to approach the task |
| 75 | 2. **Implementation skills second** (frontend-design, mcp-builder) - these guide execution |
| 76 | |
| 77 | "Let's build X" → brainstorming first, then implementation skills. |
| 78 | "Fix this bug" → debugging first, then domain-specific skills. |
| 79 | |
| 80 | ## Skill Types |
| 81 | |
| 82 | **Rigid** (TDD, debugging): Follow exactly. Don't adapt away discipline. |
| 83 | |
| 84 | **Flexible** (patterns): Adapt principles to context. |
| 85 | |
| 86 | The skill itself tells you which. |
| 87 | |
| 88 | ## User Instructions |
| 89 | |
| 90 | Instructions say WHAT, not HOW. "Add X" or "Fix Y" doesn't mean skip workflows. |
People who liked this also viewed
6 picksType
- find-skillsHelps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skSkillsJul 2026
- grill-meA relentless interview to sharpen a plan or design.SkillsJul 2026
- vercel-react-best-practicesVercel's official collection of agent skillsSkillsJul 2026
- improve-codebase-architectureScan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.SkillsJul 2026
- setup-matt-pocock-skillsConfigure this repo for the engineering skills — set up its issue tracker, triage label vocabulary, and domain doc layout. Run once before first use of the other engineering skills.SkillsJul 2026
- triageMove issues and external PRs through a state machine of triage roles — categorise, verify, grill if needed, and write agent-ready briefs.SkillsJul 2026
