Debug to Fix

When debugging frustration appears ("why isn't this working?", "it should work", "I don't understand"), orchestrate the full debug cycle: clarify → investigate → fix → verify. Prevents the common failure of jumping to fixes before understanding the problem. An elixir that chains rubber-duck and prove-it with investigation.

62 stars 2 forksSoftware Development

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add ElliotJLT/Claude-Skill-Potions --skill debug-to-fix
Manual install
git clone --depth 1 https://github.com/ElliotJLT/Claude-Skill-Potions.git /tmp/Claude-Skill-Potions
mkdir -p ~/.claude/skills
cp -r /tmp/Claude-Skill-Potions/skills/debug-to-fix ~/.claude/skills/debug-to-fix

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Debug to Fix

<purpose>
An elixir for debugging. The #1 debugging mistake: jumping to fixes before
understanding the problem. This chains clarification → investigation → fix →
verification, with gates that prevent skipping steps. Uses rubber-duck to clarify,
built-in investigation phase, and prove-it to verify.
</purpose>

## Prerequisites

This elixir works best with these skills installed:

| Skill | Purpose | If Missing |
|-------|---------|------------|
| rubber-duck | Structured problem clarification | Falls back to built-in questions |
| prove-it | Verification enforcement | Falls back to built-in verification |
| retrospective | Document learnings | Skipped (optional phase) |

The elixir degrades gracefully - it will use built-in fallbacks for missing skills.

## When To Activate

<triggers>
- "Why isn't this working?"
- "It should work but..."
- "I don't understand why..."
- "This doesn't make sense"
- User expresses debugging frustration
- Bug that persists after initial fix attempts
- User has been stuck on same issue for multiple messages
</triggers>

## Instructions

### Phase 1: Clarify

<phase_clarify>
**If rubber-duck skill installed:** Invoke it now.

**If not installed, ask:**

Before we debug, let me understand the problem:

1. **Expected:** What should happen?
2. **Actual:** What actually happens?
3. **Tried:** What have you already attempted?
4. **Changed:** What changed before this broke?
Read the full skill on GitHub

Details

Skill name
debug-to-fix
Path
skills/debug-to-fix/SKILL.md
License
MIT
Repo updated
12 February 2026

FAQ

What does the Debug to Fix skill do?

When debugging frustration appears ("why isn't this working?", "it should work", "I don't understand"), orchestrate the full debug cycle: clarify → investigate → fix → verify. Prevents the common failure of jumping to fixes before understanding the problem. An elixir that chains rubber-duck and prove-it with investigation.

How do I install the Debug to Fix skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add ElliotJLT/Claude-Skill-Potions --skill debug-to-fix. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Debug to Fix popular?

It lives in ElliotJLT/Claude-Skill-Potions, which has 62 GitHub stars and 2 forks.

Related skills

Agent Audit

62

ElliotJLT/Claude-Skill-Potions

When reviewing, optimizing, or inheriting an LLM agent, systematically identify what's actually load-bearing vs. cruft. Instruments usage, ablates components, and strips the agent to minimum viable form. Answers: "What can we remove without degrading quality?" The goal is the leanest agent that still works.

AI, LLMs & Agents

Battle Plan

62

ElliotJLT/Claude-Skill-Potions

Before ANY significant development task (new feature, refactor, integration, migration), run a complete planning ritual by orchestrating other skills in sequence: rubber-duck (clarify scope) -> pre-mortem (assess risks) -> eta (estimate time) -> final confirmation. Do not start coding until the battle plan is approved.

Software Development

Breadcrumbs

62

ElliotJLT/Claude-Skill-Potions

Leaves notes for future Claude sessions in .claude/breadcrumbs.md. At session end or after significant work, records what was tried, what worked, what failed, and context for next time. On session start, reads breadcrumbs to understand history. Session-to-session memory without manual updates.

Productivity & Notes

Designing Before Coding

43

obra/clank

Design in pseudocode first, iterate approaches, then translate to code

Software Development26

Commenting Intent

43

obra/clank

Comment WHY code exists and non-obvious decisions, not WHAT code does (mechanics)

Software Development26

Domain Focused Naming

43

obra/clank

Name code by what it does in the domain, not how it's implemented or its history

Software Development26

Browse the most popular Claude skills, all software development skills, or write your own with the skills generator.