Systematic Debugging

Trust Score 88/100

A rigorous 4-phase methodology for gathering evidence, analyzing patterns, formulating hypotheses, and implementing proven fixes for software bugs.

triggers:bugtest failureunexpected behaviorerrorfix faileddebug

GitHub SKILL.md

What it does

This skill transforms an agent from 'guessing' at fixes to a systematic engineer. It enforces a disciplined approach to debugging that prevents regressions and ensures the root cause is truly understood before any code is changed.

When to use it

Use this skill whenever you encounter a bug, test failure, or unexpected behavior. It is particularly critical when initial fix attempts have failed or when dealing with complex, intermittent errors.

What's included

Instructions: A comprehensive 4-phase workflow:
1. Gather Evidence: Read errors, reproduce the bug, and audit recent git changes.
2. Analyze Patterns: Trace execution paths and compare broken vs. working code.
3. Formulate Hypothesis: Rank likely causes and design specific tests.
4. Implement & Prove: Verify the hypothesis with a minimal test and implement a permanent fix.
Safeguards: Includes a 'Three-Strike Rule' to force architectural re-evaluation and an 'Anti-Rationalization' table to prevent common debugging pitfalls.

Compatible agents

Designed for high-capability coding agents such as Claude Code, Cursor, Codex, and other tool-enabled LLM environments.

Audit Summary

A four-phase debugging methodology skill (Gather, Analyze, Formulate, Implement) with clear phase-gating and output templates. No scripts — pure prompt-driven workflow. Well-structured with anti-rationalization table and three-strike rule for failed hypotheses. Clean frontmatter with allowed-tools constraint.

Watch Out

Pure methodology skill with no executable scripts — effectiveness depends entirely on agent following the phases

Notes

No security concerns whatsoever — no network calls, no credentials, no destructive commands. Git commands are standard and safe. The skill is well-designed for its purpose.

Information

Repository: specialist-agent
Stars: 20

Trust Score

Overall88

Security100

Code Quality78

Architecture72

Usefulness75

Related Skills

Starlark Dev

Create, debug, and test Kurtosis Starlark packages — write package structure, run dry-runs, and inspect plan execution for reliable orchestration.

Agent Browser — Core

Core usage guide for agent-browser: snapshot-and-ref browser automation to navigate pages, interact with elements, extract data, take screenshots, manage sessio

Bats Testing Patterns

Practical patterns and examples for writing maintainable unit tests for shell scripts using Bats (Bash Automated Testing System).

Crucible: Build

Orchestrates an end-to-end development pipeline: interactive design, planning, autonomous execution, and quality gates with TDD and iterative reviews.

Datadog Live Debugger (dd-debugger)

Place live log probes on running services to capture runtime arguments and variables without redeploying (Datadog Live Debugger).

Arcana (Technical Mechanism Analysis)

Explain how systems, protocols, or architectures actually work under the hood and surface non-obvious implications and failure modes.

Offload Test Runner

Run and debug large test suites in parallel using Offload; includes invocation patterns, log filtering, flaky-test handling, and config guidance.

Replit — Advanced Troubleshooting

Step-by-step diagnostics and debugging techniques for deep Replit issues: Nix build failures, container crash loops, memory leaks, and platform vs app isolation

Back to Skills