Debugging

Use always before codebase exploration, bug fixing, SWE-bench tasks, locating symbols, files, or tests, or before using rg, grep, sed, find, or source-file reads in a repository.

bitloops/bitloops

Evidence-gated diff review for PRs, branches, commit ranges, staged code changes, and merge readiness checks.

lynxlangya/techne

Testing workflow for the Rstest monorepo. An agent skill from web-infra-dev/rstest.

web-infra-dev/rstest

Call this skill when you need to debug CUDA crashes in SGLang using kernel API logging

sgl-project/sglang

Extract reusable patterns from recent sessions, propose framework improvements, and (with approval) update the framework docs.

Pratiyush/llm-wiki

A skill your agent uses when implementing or debugging onetcli SSH connection importers, including OpenSSH config, knownhosts, candidate file manifests, local composite installs, SSH authmethod JSON…

feigeCode/navop

A skill your agent uses when debugging Go errors, test failures, or unexpected behavior — step-by-step diagnosis approach

ZhangShenao/harness9

Makes the smallest code change that fixes one well-scoped problem, such as a CI failure, review comment or typo, without refactoring anything unrelated.

cobusgreyling/loop-engineering

Routes truST behaviour changes from the written specification to a native executable test.

johannesPettersson80/trust-platform

Treats bug-fix pull requests as invasive and untrusted. An agent skill from TanStack/ai.

TanStack/ai

Structured debugging methodology — use before proposing fixes for any error or failure.

sangrokjung/claude-forge

ForgeCAD model authoring, editing, debugging, and execution guidance for .forge.js, SVG-import, assembly, and CLI workflows.

ForgeCAD/forgecad-public-kit

Takes a Coffee GB compatibility issue from reproduction through a tested fix to an isolated pull request, with issue follow-up and screenshot evidence when possible.

trekawek/coffee-gb

A skill your agent uses when a recursive-mode requirement involves debugging a bug, test failure, or unexpected behavior.

try-works/recursive-mode

Systematic approach to diagnosing and fixing errors. An agent skill from vstorm-co/pydantic-deepagents.

vstorm-co/pydantic-deepagents

Guides error handling for async operations and API calls. An agent skill from DanielPodolsky/ownyourcode.

DanielPodolsky/ownyourcode

Fixes a bug from a GitHub issue by reproducing it first with a test-engineer subagent, then fixing, verifying, adding regression tests and reviewing the diff.

QwenLM/qwen-code

Mandatory pre-release deep review for minor/major releases (X.Y.0 / X.0.0).

m4r1k/Eneru

Fetch and analyze Sentry issues, events, transactions, and logs.

mitsuhiko/agent-stuff

Reference for Burla internals: how a remote_parallel_map job flows between services, how clusters and nodes are managed, and where the head keeps its state.

Burla-Cloud/burla

Runs cozempic doctor to check Claude Code configuration and sessions for known problems such as trust-dialog hangs, corrupted tool blocks and zombie teams.

Ruya-AI/cozempic

Review an existing LLM harness for correctness and gameplay-impacting bugs.

Kaggle/kaggle-environments

Guides safe code changes by finding the right file with grep or semantic search, reading before editing, reproducing bugs first, and proving a fix with a real test run.

amd/gaia

Triage failures from the Synnax integration test suite (uv run tc ...).

synnaxlabs/synnax

Diagnoses problems in the PiDeck desktop app from a redacted environment report, matching health checks to known failure patterns with fix steps.

ayuayue/PiDeck

Guides creation of kcli plan files for deploying VMs, networks, and infrastructure.

karmab/kcli

Systematic debugging with Iron Law methodology. An agent skill from catlog22/Claude-Code-Workflow.

catlog22/Claude-Code-Workflow

Comprehensive implementation and profile reference for NullPlayer's visclassic mode (CVisClassicCore, VisClassicBridge, SpectrumAnalyzerView integration, menu/keyboard controls…

ad-repo/nullplayer

This skill guides debugging NKI compilation errors on Neuron hardware.

uw-syfi/vibesys

Bug-fix and refactoring workflow for MacMagazine — root cause analysis, pattern-matching fix, regression verification.

MacMagazine/app-iOS

Debug Java applications in Eclipse — set breakpoints, launch in debug mode, step through code, inspect stack traces, evaluate expressions, and hot-swap code changes.

gradusnikov/eclipse-chatgpt-plugin

Troubleshoot Golang programs systematically - find and fix the root cause.

samber/cc-skills-golang

Consult OpenAI Codex for investigation, debugging, or code review.

umputun/cc-thingz

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

GanyuanRan/Aegis

The single interface for building, improving, and debugging exo workflows.

ghostsecurity/skills

A skill your agent uses when debugging unexpected behavior in Laravel Octane with FrankenPHP - stale data between requests, memory leaks, singleton contamination, static property state, or anything…

AratKruglik/claude-laravel

Reference patterns for goroutines, channels, sync primitives and context in Go, covering worker pools, pipelines, graceful shutdown and race-condition debugging.

wshobson/agents

Correlates a Codex CLI session's local transcript with a model router's production logs to explain why a reply rendered the way it did.

weave-os/router

Shows when to answer a code question through a real language server instead of grep, covering definitions, references, hover, outlines, and errors.

weave-os/router

Diagnoses why a file write failed (permissions, disk space, path length, locks, read-only mounts) before retrying, instead of repeating the same call blindly.

foryourhealth111-pixel/Vibe-Skills

Run the CoDD greenfield autopilot: a requirements document in, a working system out, unattended.

yohey-w/codd-dev

Systematic debugging with persistent state across context resets

SpillwaveSolutions/agent-brain

Debug OpenClaw model, provider, tool-surface, code-mode, streaming, and live/Crabbox behavior by choosing the right logs, probes, and proof path before changing code, including fetching stored…

openclaw/openclaw

Invoke before committing user-facing JET changes such as features, bug fixes, compatibility changes, or deprecations.

aviatesk/JET.jl

A skill your agent uses when debugging agent issues, investigating agent errors, checking agent connectivity, or reviewing agent diagnostic logs.

LanternOps/breeze

Fix bugs, add features to completed plugins. An agent skill from glittercowboy/plugin-freedom-system.

glittercowboy/plugin-freedom-system

Deep debugging of Nix expressions, evaluation, and derivations

r17x/universe

Iterative debugging with targeted logs. An agent skill from adam-s/intercept.

adam-s/intercept