skills.rest
cristoslc
cristoslcCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

using-superpowers

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

Updated Dec 20, 2025
Search Tags:#claude code#agent workflow#skill invocation#process discipline#cli agents#prompt protocol
One-click install
npx skills add https://github.com/cristoslc/LLM-personal-agent-patterns --skill using-superpowers-cristoslc
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: using-superpowers
Source: https://github.com/cristoslc/LLM-personal-agent-patterns/tree/main/L3-agents-core/.agents/skills/using-superpowers
Command: npx skills add https://github.com/cristoslc/LLM-personal-agent-patterns --skill using-superpowers-cristoslc

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? AI agents often skip available skills and improvise answers, leading to inconsistent workflows and missed process discipline. This Skill establishes a mandatory protocol that forces the agent to check for and invoke relevant skills before responding to any user message. ## Core Features & Use Cases - Mandatory Skill Check: Requires invoking any potentially relevant skill before responding, even for clarifying questions or simple tasks. - Decision Flowchart: Provides a visual decision graph covering skill invocation, announcement, checklist handling, and TodoWrite task creation. - Priority and Red-Flag Rules: Defines ordering between process skills (brainstorming, debugging) and implementation skills, plus a table of rationalization patterns to avoid. - Use Case: When a user asks an agent to fix a bug, the agent first invokes the debugging skill, announces its use, and follows the skill's checklist instead of jumping straight into code edits. ## Quick Start Ask the agent to start any task and it will check for applicable skills, invoke them, and announce which skill 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 agent always use available skills?▼

Install a skill-enforcement instruction like this one that requires the agent to invoke any potentially relevant skill before responding. It defines a decision flowchart and red-flag list that prevents the agent from rationalizing its way past skill checks.

What is the correct order for invoking multiple agent skills?▼

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

Does this skill work with Claude Code and other CLI agents?▼

Yes. In Claude Code it uses the Skill tool to load skill content directly, and it instructs users on other platforms to follow their platform's skill-loading documentation. It is distributed as part of a cross-CLI agents scaffold.

Should skills be invoked before asking clarifying questions?▼

Yes. The skill explicitly states that skill checks come before clarifying questions, since skills often define how to gather information and explore the codebase. Responding without checking first is listed as a red flag.

What happens if an invoked skill turns out to be irrelevant?▼

The agent may discard it. The rule only requires invoking skills that might apply, even at a 1% chance; if an invoked skill does not fit the situation, the agent is not required to follow it.

Related Skills

Explore More Software Engineering Skills→
grahama1970grahama1970
1

skills-sync

Sync local skills with an upstream agent-skills repository via rsync.

Community
Advanced
makerjackiemakerjackie
1

using-superpowers

Check and invoke relevant skills before responding to user queries.

Community
Intermediate
joanbyjoanby
25

geo-update

Synchronize local GEO-SEO deployments with the latest upstream repository version.

Community
Advanced
axiomanticaxiomantic
8

optimizing-instructions

Compress long instruction files while preserving capabilities and safety constraints.

Official
Advanced