Best debugging skills for Claude Code, Codex and other agents.

Investigates a session where Superpowers went wrong, reads the transcripts on disk and produces an evidence-cited report, optionally prepared as a bug report for the maintainers.

obra/superpowers

Reach into past AI conversation history through the trellis mem CLI.

mindfold-ai/Trellis

Bumps the pinned v8 and rusty_v8 versions in Codex, validates the release-candidate path with the v8-canary check, and traces failures to upstream build changes.

openinterpreter/openinterpreter

General Supabase skill for database, auth, Edge Functions, Realtime and storage work, plus client libraries, migrations, security audits, debugging and reading logs.

supabase/agent-skills

Investigates failing Pester tests in PowerShell CI jobs by following a six-step workflow from pull request status to documented fix recommendations.

PowerShell/PowerShell

Checks whether Android hidden-API implementations and system callbacks survive R8 minification, and diagnoses Release-only failures such as AbstractMethodError.

gkd-kit/gkd

A skill your agent uses when implementing or debugging ANY network request, API call, or data fetching.

CherryHQ/cherry-studio-app

Debug AOTInductor (AOTI) errors and crashes. An agent skill from pytorch/pytorch.

pytorch/pytorch

Runs a read-only health check for cmux and explains what it finds, covering the CLI and socket, settings, agent hooks, session restore and notifications.

manaflow-ai/cmux

Runs a disposable, uniquely named Herdr session inside an existing one so runtime, pane, terminal or API bugs can be reproduced without touching the main session.

herdrdev/herdr

A skill your agent uses when encountering any bug, test failure, or unexpected behavior, before proposing fixes

ultralisp/ultralisp

Runs an autonomous modify, verify, keep-or-discard loop against any metric, with subcommands for planning, debugging, fixing, security audits, shipping and more.

uditgoenka/autoresearch

Decides whether an OpenLogi device problem on macOS is a privacy-permission (TCC) problem, using agent log lines, and says which identity needs which grant.

AprilNEA/OpenLogi

Investigates suspected bugs in the daisyUI monorepo through read-only analysis, then writes a decision-ready fix plan in tmp/bugs without changing any product code.

saadeghi/daisyui

Execute read-only Ruby/Rails commands against Gumroad's production database for debugging and investigation.

antiwork/gumroad

Investigates bugs, errors and stack traces in phases and requires a root-cause hypothesis to be confirmed before any fix is written.

garrytan/gstack

Guides building, debugging and testing LangBot plugins: components, SDK calls, README and locale rules, SDK pitfalls and WebSocket-based testing.

langbot-app/LangBot

Gives a systematic process for debugging the forge CLI: build in debug mode, check the latest help output, test with the non-interactive -p flag, and clone conversations before reproducing bugs.

tailcallhq/forgecode

Drives a running OpenWork desktop window over CDP from the shell to evaluate JS, take screenshots, start sessions and send prompts for hand checks.

different-ai/openwork

Resolves .NET runtime frames in Apple .ips crash logs to function names, source files and line numbers using dSYM symbols, atos and the Microsoft symbol server.

dotnet/skills

Debugs LangChain and LangGraph agents by pulling recent execution traces with the langsmith-fetch CLI and reporting errors, tool calls, timings and token use.

ComposioHQ/awesome-claude-skills

Covers debug logging, the Debug menu, profiling rules and runtime pitfalls for working on the cmux macOS terminal app.

manaflow-ai/cmux

Takes a GitHub or YouTrack issue for the Exposed project through reproduction, a failing test, a fix, validation and a pull request.

JetBrains/Exposed

A skill your agent uses when the user is debugging a bug, tracing an error, or asking why something fails.

aws-samples/sample-kolya-br-proxy

Debug hanging issues in SGLang distributed inference (TP/PP/DP/EP).

sgl-project/sglang

Launches, restarts and troubleshoots the real AO Electron desktop app from a checkout, with isolated or real local data and checks for stale processes.

OrchestratorInc/agent-orchestrator

Analyzes V8, Chrome and Electron .heapsnapshot files with Node scripts to find memory leaks, detached DOM nodes and the retainer paths that keep objects alive.

keybase/client

React DevTools CLI for AI agents. An agent skill from sanity-io/sanity.

sanity-io/sanity

Instructions for navigating and debugging BlockNote in a browser.

TypeCellOS/BlockNote

Step-by-step procedure for debugging browser automation failures on complex sites such as LinkedIn, Twitter/X, single-page apps and Shadow DOM pages.

aden-hive/hive

Repairs a broken OpenCLI site adapter after a command fails: collects a trace, patches only the adapter, retries, and files an upstream GitHub issue once fixed.

jackwener/OpenCLI

Traces a bug through a code knowledge graph, following callers, callees and execution flow before opening source files, within a small token budget.

tirth8205/code-review-graph

Answers questions about a past agent run from its recording, using causal graphs and replay, instead of reconstructing events from memory.

iflytek/skillhub

Guide for creating and maintaining outbox-based eventually consistent operations in Sentry.

getsentry/sentry

Operates the `mqttx` command line client to connect, publish, subscribe, benchmark and simulate data against an MQTT broker, with TLS and MQTT 5 support.

emqx/MQTTX

Answers TqSdk Python questions on market data, accounts, orders, margin trials, simulation and backtesting, using the library's own docs and examples.

shinnytech/tqsdk-python

Investigates TiDB plan or test-result diffs that the change does not explain, ruling out failpoint setup and merge effects before expected outputs are updated.

pingcap/tidb

Fix bugs in SkiaSharp C bindings. An agent skill from mono/SkiaSharp.

mono/SkiaSharp

Pushes an agent to exhaust every option, investigate before asking and take initiative beyond the literal request, instead of giving up or waiting passively.

tanweai/pua

Explains why editing CUTLASS fused-MHA headers in ONNX Runtime can leave stale CUDA kernels after an incremental build, and how to force and verify a real rebuild.

microsoft/onnxruntime

Use Trellis channel for live multi-agent collaboration, spawned workers, cross-agent review, progress inspection, forum channels, and channel log debugging.

mindfold-ai/Trellis

Diagnoses surprising LoopX behavior, such as stale recommendations or tiny progress, assigns it to the responsible layer and repairs it at the lowest durable level.

loopx-project/loopx

Guides CPU profiling of PlotJuggler 4 on Linux with perf: count first, record cheaply with LBR, then read per-thread, flat, flamegraph or time-window views.

PlotJuggler/PlotJuggler

WooYun business logic vulnerability methodology — 22,132 real cases across 6 domains (authentication bypass, authorization bypass, payment tampering, information disclosure, logic flaws…

tanweai/wooyun-legacy

Analyzes Chrome or Electron DevTools Performance trace exports with Python scripts to find where render time actually goes, without opening DevTools.

keybase/client

Resolves native crash frames from .NET Android tombstones to function names, source files and line numbers using BuildIds, Microsoft's symbol server and llvm-symbolizer.

dotnet/skills

Fixes a React Router bug reported in a GitHub issue end to end: fetching the issue, validating the reproduction, writing a failing test and implementing the fix on a new branch.

remix-run/react-router

Applies a four-phase debugging routine that finds the root cause of a bug or failing test before any fix is written.

ChrisWiles/claude-code-showcase