Best skills for: Debugging
Debugging is where AI coding assistants truly shine—if you know which skills to invoke. For developers on Claude Code, Cursor, or Copilot, the key is selecting skills that guide the AI to reason about root causes, not just patch symptoms. A skill like WebSocket Engineer is gold for tackling real-time communication issues, teaching the model to inspect message flows and latency. Meanwhile, Domain-Driven Design (DDD) helps the AI align with your domain logic, preventing fixes that break business rules. Pitfall: avoid vague prompts like 'fix this bug.' Instead, ask for a hypothesis-driven analysis—'what could cause this null pointer in this DDD aggregate?' The best debugging skills force a structured approach: isolate the symptom, trace the execution path, and validate assumptions. Remember, AI debugging is iterative; use the skill to drill down on logs and error stacks, not just ask for a one-liner fix.
24 skills selected
ConsoleService Usage Guide
Development
Provides implementation guidance for ConsoleService, an environment-aware console wrapper in Angular. Use for adding console logging with contextConsole, always/never overrides, and visibility rules.
View Shella Logs
Development
View Shella daemon and plugin logs from ~/.local/state/shella/dev.log. Supports filtering by plugin name, error level, or showing recent lines. Useful for debugging issues, checking what happened, or monitoring plugin output.
No Johns Setup Troubleshooter
Development
Diagnoses and fixes common setup issues for No Johns, an AI training framework for Melee. Runs systematic checks on Python 3.12, required packages (libmelee, pyenet), configuration files (Dolphin path, ISO, connect code), Dolphin installation, and arena connectivity. Useful when users encounter errors during initial setup or after updates.
ConnectStats Bug Report Analyzer
Development
Downloads and extracts a ConnectStats bug report from the server, then analyzes the user description, app logs, and associated databases (activities, tracks) to identify errors and diagnose issues. It is invoked when a user provides a bug report ID or mentions a bug report.
Reflexion - Error Documentation
Development
Captures significant errors encountered during development, including root cause analysis and prevention strategies. Helps build a knowledge base to avoid repeating the same mistakes, especially for non-trivial bugs that required meaningful debugging effort.
Log Aggregator
Development
Aggregates logs from systemd services, Docker containers, and application files in known projects. Supports filtering by error/warn levels, tailing, searching, and time ranges. Useful for debugging, monitoring service health, and investigating errors.
Structured debugging with session persistence
Development
Structured debugging workflow that uses subagents for isolated investigation, preventing context pollution. It persists sessions, gathers symptoms systematically, and manages checkpoints to resume long debugging sessions efficiently. Helps when debugging complex issues that require deep, iterative exploration without losing progress.
Dispatching Parallel Agents
Development
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies.
Temporal Python Workflows
Development
Manage Temporal workflows using local dev server and Python SDK. Includes starting, stopping, debugging, and troubleshooting.
Python Functional Bug Debugging
Development
Investigates functional bugs in Python using specifications, logs, and observed behavior. Useful when a feature isn't working as specified, to analyze runtime errors, or to scope a problem before implementing a fix.
Systematic Debugging
Development
Systematically diagnoses and resolves software bugs, test failures, data quality issues, and performance problems using various debugging techniques and tools. Helps when encountering errors, crashes, flaky tests, or unexpected behavior in code, tests, data pipelines, or ML models. Covers strategies like isolation, binary search, git bisect, and specialized debugging for flaky tests and data pipelines.
Systematic Debugging
Development
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
Five Whys Analysis
Development
Five Whys root cause analysis. Iteratively asks 'why' to drill past symptoms to underlying causes. Use for debugging, investigating failures, or understanding why something went wrong.
Systematic Debugging
Development
Systematic debugging with hypothesis-driven investigation. Use when something is broken, tests fail, or errors need investigation. The process includes assessing the issue, isolating the root cause with hypotheses, applying minimal fixes, and adding regression tests to prevent recurrence.
Grove Logging Best Practices
Development
A skill for adding NDJSON debug record events to Grove's Rust TUI. Covers wide event design with rich context, event/kind identity pairs, data fields, timing at boundaries, and zero-cost null logger usage. Use when adding new log events, reviewing logging code, or designing instrumentation for new features.
Bug Fix Workflow
Development
Fixes a specific bug or problem in the codebase by either applying an immediate fix or creating a plan first. It checks for an existing fix plan, investigates using project context and past patches, and always suggests test coverage and adds logging. Use when encountering error messages, unexpected behavior, or when asked to debug.
Systematic Bug Fix Workflow
Development
Executes a systematic bug fix workflow: structured investigation, regression test creation, fix implementation, and a formal report in specs/bugfixes/. Automatically handles Transit tickets and branch management. Useful for bugs requiring thorough analysis and full documentation.
Code Investigation
Development
Investigate codebase issues, debug problems, or analyze patterns using tools like Read, Grep, Glob, and Bash. It helps developers trace data flow, identify root causes of bugs, or understand code structure systematically.
Stripe Testing and Debugging
Development
Test and debug Stripe payment integrations end-to-end. Simulate payment flows, verify webhook handling, diagnose failed charges, and validate subscription lifecycle. Useful when ensuring Stripe integrations work correctly in development or production.
PR Review Pipeline Debugging
Development
Diagnoses why a specific PR review is failing or not triggering in the claude-code-reviewer service. Traces the PR through the full pipeline: state, errors, review history, skip reasons, and simulation of the review gating logic. Useful when a PR is not receiving a review or a review fails unexpectedly.
Diagnosing Hard Bugs and Regressions
Development
Disciplined approach for diagnosing hard bugs and performance regressions, centered on building a tight feedback loop to reproduce and root-cause issues.
Execution Recovery
Development
Diagnoses and fixes common execution errors such as syntax issues, import failures, path problems, permission denials, and connection timeouts. Provides automated recovery strategies tailored to each error type, including dependency installation, permission adjustments, and connectivity tests. Useful when scripts or commands fail during execution.
Systematic Debugging
Development
Provides a structured five-phase debugging workflow: understand, reproduce, isolate, fix, and document. Guides through writing failing tests, binary search isolation, minimal fixes, and regression tests. Most useful when tackling complex or non-obvious bugs that require a systematic approach.
Mermaid Diagrams
Development
Creates, validates, and troubleshoots Mermaid.js diagrams for flowcharts, sequence diagrams, class diagrams, ER diagrams, state diagrams, Gantt charts, and other visualizations. Uses the rp1 CLI tool for syntax validation and provides structured error feedback for automatic repair. Useful when generating diagrams in markdown or debugging diagram syntax errors.
How to choose
- How are these skills selected?
- An algorithm picks them among the published skills that match this page's criteria, such as category, tags or compatible tools. It ranks them by the quality score a language model gave them. On ranking pages, it also weighs GitHub stars and the security rating. Nobody reviews them one by one.
- What do the security ratings mean?
- A language model reads the SKILL.md file, without running it, and gives it a rating. Safe means it sees no meaningful execution risk. Caution means the skill uses powerful tools such as bash, docker or the network for a legitimate purpose. Risky means it asks for destructive actions, for secrets to be sent out, or for obfuscated code to run; a skill rated Risky is never published. The rating does not replace your own reading of the file.
- How do I install a skill?
- Open any skill page and follow its install instructions for your tool — Claude Code, Cursor or Copilot. Each skill lists the exact steps so you can get it running in a couple of minutes.