skills.rest
Tgoldi
TgoldiCOMMUNITY
Explore all skills by this author →
GitHub

using-superpowers

Enforces skill discovery and invocation before any AI response.

1|Updated May 10, 2026
Search Tags:#workflow enforcement#skill discovery#ai assistant#skill invocation#prompt instructions#process priority
One-click install
npx skills add https://github.com/Tgoldi/claude-skills --skill using-superpowers-tgoldi
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: using-superpowers
Source: https://github.com/Tgoldi/claude-skills/tree/main/using-superpowers
Command: npx skills add https://github.com/Tgoldi/claude-skills --skill using-superpowers-tgoldi

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? AI assistants often skip available skills and answer directly, missing established workflows and producing inconsistent results. This Skill establishes a mandatory check-then-act rule so relevant skills are always loaded before any response. ## Core Features & Use Cases - Mandatory Skill Check: Requires invoking the Skill tool before any response, including clarifying questions, whenever a skill might apply. - Decision Flowchart: Provides a graph-based flow for deciding when to invoke a skill, announce its use, and convert checklists into TodoWrite todos. - Priority and Red-Flag Rules: Defines ordering between process skills (brainstorming, debugging) and implementation skills, plus a table of rationalizations to reject. - Use Case: When a user asks to fix a bug, the assistant first loads the debugging skill, then any domain-specific skills, instead of improvising a fix. ## Quick Start Ask the assistant to start any task and it will check for applicable skills and announce which one it is using before responding.

Frequently Asked Questions about using-superpowers

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I make an AI assistant always check for skills before responding?▼

Install a skill-enforcement instruction that requires invoking the Skill tool before any response, including clarifying questions. The rule triggers whenever there is even a small chance a skill applies to the task.

What is the correct order when multiple skills apply to one task?▼

Process skills like brainstorming and debugging come first because they determine how to approach the task. Implementation skills such as frontend-design or mcp-builder come second to guide execution.

Should I check for skills before asking clarifying questions?▼

Yes. The skill check happens before any response, including clarifying questions, because skills often define how to gather information and explore the problem.

What are rigid versus flexible skills?▼

Rigid skills like TDD and debugging must be followed exactly without adapting away their discipline. Flexible skills describe patterns that can be adapted to context, and each skill states which type it is.

When is it acceptable to skip using a skill?▼

Only when no skill could possibly apply to the task. Rationalizations like 'this is simple' or 'I remember the skill' are explicitly rejected because skills evolve and simple tasks become complex.

Related Skills

Explore More Software Engineering Skills→
Amna-exeAmna-exe

skill-creator

Create reusable SKILL.md files that capture workflows and instructions for future agent sessions.

Community
Intermediate
DEEPX-AIDEEPX-AI
3

dx-skill-router

Routes agent tasks to matching dx-* skills before any response or action.

Official
Intermediate
GovTechSGGovTechSG
18

agent-skills-writing

Standardize authoring and organizing AI agent skills with frontmatter and folder structure.

Official
Advanced
blucsigma05blucsigma05

tbm-prompt-auditor-pass

Route legacy TBM-prefixed prompt auditor invocations to the global skill.

Community
Basic