fix_skill

Overview

This skill always activates before fixing any bug, error, test failure, CI/CD issue, type error, lint, log error, UI issue, or code problem. It provides an end-to-end, disciplined workflow that selects an operating mode, performs deep debugging, assesses complexity, implements fixes, verifies impact, and finalizes changes with a confidence score. The skill coordinates specialized subagents and parallel exploration to reduce blind spots and speed resolution.

How this skill works

On invocation the skill selects a mode (autonomous, human-in-the-loop review, or quick) and runs a mandatory debug phase that enumerates and tests root-cause hypotheses. It classifies issue complexity (simple, moderate, complex, or parallel) to choose an appropriate workflow and activates required subagents (debugger, researcher, planner, code-reviewer, tester, Bash, and parallel Explore agents). After implementing fixes it runs verification, searches for related risks, produces a summary with confidence score, and can request commits or documentation updates.

When to use it

• Before attempting any fix to ensure consistent, auditable workflow
• When a failing test, CI job, or lint/type error appears
• For production or critical code where human review may be required
• On multi-file or system-wide bugs that need coordinated investigation
• When you want automated verification and a confidence score

Best practices

• Always run in autonomous mode for trivial issues and quick mode for type/lint fixes
• Choose human-in-the-loop for production-impacting or safety-critical changes
• Use parallel Explore/Bash agents to validate multiple hypotheses simultaneously
• Require full verification and related-code scouting before finalizing changes
• Report confidence, files changed, and test results in the unified step format

Example use cases

• A failing CI pipeline due to a recent dependency upgrade — detect, isolate, and propose rollback or patch
• A unit test regression after refactor — find root cause, implement minimal fix, and re-run tests
• Type errors from static analysis — quick mode to correct annotations and rerun type checks
• Flaky production logs showing intermittent exceptions — deep investigation and preventative validation
• UI rendering bug affecting multiple components — classify as complex and coordinate design-aware fixes