using-superpowers
npx machina-cli add skill parthalon025/autonomous-coding-toolkit/using-superpowers --openclawIF A SKILL APPLIES TO YOUR TASK, YOU DO NOT HAVE A CHOICE. YOU MUST USE IT.
This is not negotiable. This is not optional. You cannot rationalize your way out of this. </EXTREMELY-IMPORTANT>
How to Access Skills
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.
In other environments: Check your platform's documentation for how skills are loaded.
Using Skills
The Rule
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.
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. |
| "This doesn't need a formal skill" | If a skill exists, use it. |
| "I remember this skill" | Skills evolve. Read current version. |
| "The skill is overkill" | Simple things become complex. Use it. |
Skill Priority
When multiple skills could apply, use this order:
- Process skills first (brainstorming, debugging) - these determine HOW to approach the task
- Implementation skills second (frontend-design, mcp-builder) - these guide execution
Skill Types
Rigid (TDD, debugging): Follow exactly. Don't adapt away discipline. Flexible (patterns): Adapt principles to context.
User Instructions
Instructions say WHAT, not HOW. "Add X" or "Fix Y" doesn't mean skip workflows.
Source
git clone https://github.com/parthalon025/autonomous-coding-toolkit/blob/main/skills/using-superpowers/SKILL.mdView on GitHub Overview
This skill enforces checking and invoking any relevant skill before you respond. It explains how to locate, load, and follow skill content so responses are tool-driven from the start. This matters because it ensures consistent behavior and access to defined workflows for every conversation.
How This Skill Works
When a task begins, invoke the Skill tool to load applicable skills. The loaded content is presented and must be followed directly; never use the Read tool on skill files. If multiple skills apply, apply process skills first, then implementation skills, and always check for skills before answering.
When to Use It
- At the very start of any conversation to determine applicable skills
- When a user asks something that may require a skill check
- Before clarifying questions to ensure a skills-driven approach
- During debugging or feature exploration to decide HOW to proceed
- When learning how skills are accessed or referenced in the environment
Quick Start
- Step 1: Invoke the Skill tool to locate applicable skills
- Step 2: Read the loaded skill content and follow its instructions exactly
- Step 3: Proceed to respond only after aligning with the skill guidance
Best Practices
- Always invoke a skill before any reply, even if the chance of applicability is small
- Follow the loaded skill content exactly; do not improvise
- Prioritize process skills first, then implementation skills
- Never use the Read tool on skill files; rely on Skill content
- Re-check for updated skills at the start of each task
Example Use Cases
- An agent begins a chat and immediately invokes the Skill tool to load applicable rules
- During a debugging session, the assistant uses a skill to determine the correct approach
- In Claude Code, the agent loads usage guidelines from a skill and adheres to them
- If multiple skills apply, the agent uses the priority order to select the top one and act on it
- The assistant demonstrates how to access skills in the environment per the skill instructions
