skills.rest
alex-jordan547
alex-jordan547COMMUNITY
Explore all skills by this author →
GitHub

using-superpowers

Enforces skill discovery and invocation before any agent response or action.

Updated Jul 3, 2026
Search Tags:#claude code#agent workflow#meta-skill#skill discovery#process enforcement#skill invocation
One-click install
npx skills add https://github.com/alex-jordan547/agent-setup --skill using-superpowers-alex-jordan547
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: using-superpowers
Source: https://github.com/alex-jordan547/agent-setup/tree/main/archive/using-superpowers
Command: npx skills add https://github.com/alex-jordan547/agent-setup --skill using-superpowers-alex-jordan547

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Agents 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 invoked before any response, including clarifying questions. ## Core Features & Use Cases - Mandatory Skill Check: Requires invoking any potentially relevant skill (even at 1% likelihood) before responding or acting. - Decision Flowchart: Provides a graphviz flow from user message through skill invocation, checklist handling, and final response. - Rationalization Detection: Lists twelve red-flag thoughts that signal an agent is skipping the skill check. - Priority Ordering: Defines that process skills (brainstorming, debugging) run before implementation skills. - Use Case: When a user asks to fix a bug, the agent invokes the debugging skill first rather than jumping straight into code edits. ## Quick Start Invoke this skill at the start of any conversation to enforce checking and using relevant skills 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 agent always check available skills before answering?▼

Use a meta-skill that mandates skill invocation before any response, including clarifying questions. This skill establishes the rule that even a 1% chance of relevance requires invoking the skill first.

What order should skills be invoked when multiple apply?▼

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 follow to guide execution.

How are skills invoked in Claude Code?▼

In Claude Code, skills are invoked through the Skill tool, which loads the skill content directly into context. The skill instructions warn against using the Read tool on skill files instead.

When should a skill not be used after being invoked?▼

If an invoked skill turns out to be wrong for the situation, it does not need to be followed. The invocation check is mandatory, but applying the skill's content remains conditional on actual relevance.

What are signs an agent is rationalizing skipping a skill check?▼

Common rationalizations include treating questions as non-tasks, gathering context first, or assuming a remembered skill is current. The skill lists twelve red-flag thoughts that indicate the check is being skipped.

Related Skills

Explore More Software Engineering Skills→
Leonardo-CorteLeonardo-Corte
1

maestro-skill-author

Create or repair Maestro built-in skill definitions with validated SKILL.md frontmatter and registry rebuilding.

Community
Intermediate
sadie100sadie100

spec-pipeline

Execute a requirement-to-implementation pipeline using sequential subagents for brainstorming, grilling, planning, and execution.

Community
Advanced
endorlabsendorlabs
4

endor-author-agent-skill

Author and update agent skills with portable SKILL.md frontmatter and sync validation.

Official
Advanced
Yoodaddy0311Yoodaddy0311
3

prompt-caching-strategy

Optimizes prompt cache hit rates by separating static and dynamic instruction content.

Community
Intermediate