Best debugging skills, page 11

Works with Physical AI Studio datasets and Lightning datamodules built on the LeRobot format.

open-edge-platform/physical-ai-studio

Start and interact with the Boundless localnet (docker compose-based local development network).

boundless-xyz/boundless

Systematic debugging with root cause investigation. An agent skill from mr-daedalium/ostack-saas.

mr-daedalium/ostack-saas

Captures and filters Windows user-mode and kernel debug output from the command line with the Sysinternals DebugView CLI, including bounded runs suited to agents.

microsoft/skills

Walks the agent through a fixed loop for failing tests and build errors: reproduce, isolate, hypothesize, instrument, fix, verify, then add a regression test.

Totoro-jam/battle-tested-patterns

Investigate and fix a specific Honeybadger exception in the Bike Index app — pull the fault, read its backtrace, find the offending code, write the fix.

bikeindex/bike_index

Feature and bug-fix development checklist for the Rstest monorepo.

web-infra-dev/rstest

Debug GenLayer Studio deployments via ArgoCD CLI. An agent skill from genlayerlabs/genlayer-studio.

genlayerlabs/genlayer-studio

Systematically QA test any application — web apps, native macOS apps, Electron apps, CLI tools, interactive REPLs, or anything on screen.

team-attention/hoyeon

Drive the running Obsidian instance to verify plugin changes — build, reload, eval, screenshot.

aidenlx/zotlit

Explains which build step writes each asset directory in the Tabler repo and how to fix missing, stale or duplicated CSS and JS files.

tabler/tabler

Find bugs, security holes, and maintainability issues in a diff or file.

antonbabenko/deliberation

A skill your agent uses to find which Jetpack Compose composables are recomposing and why, using Android Studio Layout Inspector recomposition counts and skip counts, the per-parameter Argument…

rosuH/EasyWatermark

Investigate native React Native crashes (Fabric/Hermes/iOS) in ledger-live-mobile when JS error logs are missing or unhelpful.

LedgerHQ/ledger-live

Traces a reported dotnet/maui issue back to the commit or pull request that introduced it, separating confirmed causes from likely candidates.

dotnet/maui

Attempts one alternative fix for a bug, runs the given test command against it and reports what happened, always differing from existing PR fixes.

dotnet/maui

Google Cast Protocol v2, message framing, debugging, and test scripts.

ad-repo/nullplayer

Codebase reconnaissance agent for Bug Hunter. An agent skill from codexstar69/bug-hunter.

codexstar69/bug-hunter

Hypothesis-driven debugging methodology for hard bugs. An agent skill from QwenLM/qwen-code.

QwenLM/qwen-code

Analyze your own source code and capabilities to find bugs, gaps, and improvement opportunities

yologdev/yoyo-evolve

Audit whether an AI agent can autonomously close the loop on problems in a given area — from discovering a symptom to verifying a fix — without human intervention.

deepklarity/harness-kit

Debug errors systematically by searching first, then analyzing, then proposing verified solutions.

Aedelon/claude-code-blueprint

Clicks through every flow of an app clone and tests it for bugs: a test plan generated from the recon flows with happy paths and edge cases, Playwright end-to-end tests where possible, a browser…

Jakeschincariol/replica-skill

面向 SurveyController 的日志、配置与报错排查技能。用于根据用户提供的日志、截图、配置文件、调用栈、运行环境和最近改动定位根因，修复 software/app/、software/io/、software/logging/、software/network/、software/ui/…

SurveyController/SurveyController

Bug fix workflow that proves test validity with a red-then-green CI sequence.

Comfy-Org/ComfyUI_frontend

Instruments programs to capture execution traces specifically for reproducing reported bugs, enabling consistent replay and diagnosis of failures.

ArabelaTso/Skills-4-SE

Trace every user-facing button/touchpoint through its full state change sequence to find bugs where functions individually work but cancel each other out, produce wrong final state, or leave the UI…

affaan-m/ECC

Replaces trial-and-error fixing with an observe, hypothesize, experiment and conclude loop kept in DEBUG.md, where no fix is allowed before evidence supports a cause.

LichAmnesia/lich-skills

Troubleshooting guide for NanoClaw's containerized agents: where the logs are, how the two session databases show message flow, and how to raise the log level.

nanocoai/nanoclaw

Debug and fix any non-trivial issue end-to-end, OR triage a GitHub bug issue read-only.

ossappscollective/oss-weather

Inspect and analyze uniclipboard's local JSONL logs on a SINGLE machine — query, filter, and time-merge the per-role (gui/daemon/cli) log files to answer "what just happened" or trace a symptom…

UniClipboard/UniClipboard

Use this skill ALWAYS whenever the user asks you to write code, modify files, fix bugs, plan features, or do any software development task.

KINGSTAR-OMEGA/claude-token-optimizer

Council critique mode - agents find bugs and flaws in each other's answers

agentic-box/owlex

ALWAYS use before attempting any fix. An agent skill from heyitsnoah/claudesidian.

heyitsnoah/claudesidian

Add a new component to the CORAL framework itself — a new agent runtime under coral/agent/builtin/ (claudecode/codex/cursoragent style), a new CLI command in coral/cli/, a new bundled skill or…

Human-Agent-Society/CORAL

Versioning, branch, and release policy (semantic versioning, branch-per-minor, tag-per-patch).

relytcloud/pg_ducklake

Forge (锻造坊) — Engineering & architecture deliberation room. An agent skill from geekjourneyx/agora.

geekjourneyx/agora

Catalog of Flowfile's environment variables and runtime flags: what each does, where the code reads it, its default, and where the docs disagree with the code.

Edwardvaneechoud/Flowfile

Expert guidance for Django REST Framework class-based views using Classy DRF (https://www.cdrf.co).

vintasoftware/django-ai-plugins

Transform an AI agent into a disciplined software development partner with strong judgment, transparent decisions, proportionate verification, and craftsmanship.

shareAI-lab/lab-skills

Systematic debugging with structured reproduction and root cause analysis.

nth5693/gemini-kit

Quality gates for finishing work in this repository — dead-code cleanup, Roslynator and dotnet format fixes, markdownlint, build, unit tests, documentation, and Obsolete migration shims — with the…

facioquo/stock-indicators-dotnet

Reproduces a Medusa Cloud build on your machine with mcloud local build, to debug build-failed deployments without pushing or waiting on Cloud.

medusajs/medusa-agent-skills

Find bugs in the Stitch SDK using a real API key. An agent skill from google-labs-code/stitch-sdk.

google-labs-code/stitch-sdk

Firewall and Vercel AI Gateway debugging for vercel-openclaw: network policy allowlists, OIDC token refresh, AI Gateway transform rules, firewall learning/enforcement, and sandbox.update…

vercel-labs/vercel-openclaw-archived

Stress-tests a fuzzy or vague feature idea before any PRD, spec, or ticket is written.

opsmill/infrahub

Debug IntelliJ IDE failures with repository-specific techniques.

JetBrains/intellij-community

Explains why something happened by generating competing hypotheses, gathering evidence in parallel, ranking explanations and proposing the next discriminating probe.

Yeachan-Heo/oh-my-claudecode