Debugging skills

10,184 tagged Debugging, measured the same way as everything else here.

Browse within: LLM 147cli 98agent 97agents 88skills 81agentic-ai 70javascript 70claude-code-plugin 50ai-coding 46ai-skills 40kubernetes 40metaprogramming 40software-development 40software-engineering 40

debug-protocol

529

curtischoutw/claude-institution

Skill Claude CodeCodex

A step-by-step debugging guide based on reproducing a failure, testing one explanation at a time, making the smallest relevant change, and checking the result. It includes a stopping rule for repeated unsuccessful fixes.

not rated 5 6d ago A 74 tokens original MIT

rca

530

FlorinI/Florians-Claude-Code-Kit

Skill Claude CodeCodex

Disciplined root-cause analysis for diagnosing why something is broken. Use whenever the user is debugging a bug, regression, incident, outage, flaky or intermittent behavior, a failing test, or asks "why is X happening" / "why did this break" / "whats causing this" — even if they never say the words "root cause." It…

not rated 5 8d ago A 174 tokens original MIT

zephex

531

zephexMCP/agent-skills

Skill Claude CodeCodex

Use when the user works in their own codebase with Zephex MCP or the zephex terminal CLI: onboard a repo, find or read code, map architecture, run or diagnose tests, check packages before install, audit a live HTTPS URL, remember project facts, or debug multi-file issues — including when they only say "use Zephex,"…

not rated 5 24d ago B 221 tokens original MIT

debugging

532

Kimyongari/harness-factory

Skill Claude CodeCodex

Use when hunting the cause of a bug, error, or failing test — and before proposing any fix. Triggers - "why doesn't this work", stack traces, flaky failures, regressions ("worked yesterday"). Output is reproduce → root cause → minimal fix → regression test. If you already know the cause and just need the fix, use…

not rated 5 1mo ago A 73 tokens original MIT

Newmcpe/ida-reverse-engineering-skill

Skill Claude CodeCodex

Drive IDA Pro through the IDA Pro MCP like a senior reverse engineer: don't just narrate decompiler output, transform the database. Use this whenever the user is reverse engineering, analyzing malware, working a crackme or CTF, or doing binary/firmware analysis with IDA Pro over an MCP connection (mrexodia/ida-pro-mcp…

not rated 5 2mo ago A 243 tokens WTFPL

harness-audit

534

nnabuuu/harness-engineering-toolkit

Skill Claude CodeCodex

A codebase scan for five common weaknesses in the setup used to guide and check an AI agent. It produces a diagnostic report and can optionally fix the problems it finds.

not rated 5 1mo ago A 87 tokens original MIT

solve-analyze

535

Tenstu/Pass-LLM-with-LLM

Skill Claude CodeCodex

A code-diagnosis tool for a completed solve() function, comparing it with a reference solution and explaining meaningful differences.

not rated 5 2mo ago A 160 tokens original MIT

NFTYoginis/agency-of-one

Skill Claude Code

Aggregate breadcrumbs, escalations, and audit logs from the last 14–30 days to surface recurring correction patterns that should be fixed at the source level (brief template, config/, WORKER-RULES.md) rather than re-fixed each session. Use during weekly maintenance Phase 2, after a redo dispatch, or when the operator…

not rated 5 18d ago A 159 tokens

adversarial-review

537

yunsii/wezdeck

Skill Claude CodeCodex needs its repo

A multi-role code-review process that searches for problems, tries to disprove the proposed changes, and reproduces issues in a sandbox. Different agents or backends can take part in the review.

not rated 5 2d ago A 85 tokens original MIT

agent-in-sync

538

agentinsync/agent-in-sync

Skill Claude Code

Search, submit, and vote on coding solutions via the AgentInSync collaborative knowledge base. Use when encountering errors, stack traces, bugs, crashes, exceptions, "not working" issues, or after fixing a non-trivial bug. Also activates for "how to" questions about debugging workflows.

not rated 5 3mo ago A 63 tokens AGPL-3.0

glyphtrail

539

glyphtrail/glyphtrail

Skill Claude CodeCodex

Query this repo's code graph instead of ls/grep/reading files blindly. Use whenever you are understanding the codebase or its architecture, tracing how something works, or searching for a symbol or term; before changing a symbol, to get its blast radius (dependent symbols, tests to run, API surface, and other indexed…

not rated 6 20d ago A 151 tokens EUPL-1.2

pkgseek-linux

540

web-casa/pkgseek-skills

Skill Codex

Investigate Linux package, build, command, vulnerability, distribution migration, ELF/ABI, shared-library, and container issues with distro-aware PkgSeek evidence. Use for apt, apt-get, dpkg, yum, dnf, rpm, apk or pacman errors; missing commands, headers and .so files; CVE/CNNVD and backport checks; Debian, Ubuntu…

not rated 5 20d ago A 120 tokens original MIT

temporal-debug

541

MeherBhaskar/temporal-debug-skill

Skill Claude CodeCodex

Use this skill when the user is debugging a bug, error, crash, or issue that might be tied to a specific point in time (e.g., "crash from 3 hours ago", "bug in v2.4.1", "last night's deploy"). It guides the agent to reconstruct the historical code state and analyze the bug in that context.

not rated 5 1mo ago A 77 tokens original MIT

bet-on-it

542

Lum1104/bet-on-it

Skill Claude CodeCodex

Use when debugging or changing behavior based on an uncertain causal hypothesis that the next action can test.

not rated 5 1mo ago A 23 tokens original MIT

trust-guard

543

sdcrd/trust-guard

Skill Claude Code

Post-edit verification that prevents silent edit failures. After every Write, Edit, or MultiEdit, re-reads files to confirm changes actually saved to disk across all call sites. Assigns a 0-100 trust score per edit. Catches: silent failures (tool reports success but file unchanged), partial application (some call…

not rated 5 3mo ago A 0 tokens

finfocus-routing

544

rshade/finfocus

Skill Claude CodeCodex

Configure and debug FinFocus intelligent plugin routing. Use when setting up multi-plugin routing, configuring priority and fallback rules, writing pattern matching for resource types, testing route selection, or debugging why a plugin isn't receiving cost queries. Triggers on: "configure routing", "plugin priority"…

not rated 5 6d ago A 101 tokens original Apache-2.0

ghidra-agent-cli

545

ByteLandTechnology/headless-ghidra

Skill Claude CodeCodex

Rust CLI reference for the headless-ghidra pipeline. Covers command syntax, flags, output contract, artifact paths, and workspace layout for all ghidra-agent-cli subcommands. Load when: constructing a ghidra-agent-cli command, interpreting its output, resolving a flag or artifact path question, or debugging CLI…

not rated 5 4mo ago A 95 tokens

dsh-autofix

546

cyanseek/dsh-autofix

Skill Codex

A recovery guide for common DeepSeek Harness failures, such as missing commands, stale text, unavailable history, or failed installation. It examines the current error and applies a small, matching recovery step.

not rated 5 14d ago A 66 tokens original MIT

video-debug

547

vladzima/video-debug

Skill Claude Code

Use when the user references a video, screencast, screen recording, or any path ending in .mp4, .mov, .webm, .mkv, or .gif — especially when asking to debug a UI bug, visual glitch, or reproduction recording. Extracts key frames via ffmpeg scene detection so the agent can visually inspect what went wrong.

not rated 5 3mo ago A 77 tokens original MIT

openocd-mcu-debug

548

royforlinux/openocd-mcu-mcp

Skill Codex

OpenOCD-based MCU probing, CMSIS-SVD register decoding, and embedded debug diagnosis for Cortex-M/RISC-V targets. Use when working with connected MCU hardware, OpenOCD, JTAG/SWD, SVD files, chip identification, register decoding, HardFault/crash/hang diagnosis, peripheral/clock/memory debugging, or ELF symbol/source…

not rated 5 3mo ago A 81 tokens original MIT

system-inspect

549

webdevelopers-eu/zolinga

Skill Claude Code

How to query the Zolinga system's runtime state — merged manifest cache, API service stubs, configuration layers, and log files — using jq, grep, tail, and PHP.

not rated 5 2d ago A 42 tokens

agentic-debug-mode

550

Toubat/agentic-debug-mode

Skill Claude CodeCodex

Use when a bug, regression, race condition, or unexpected behavior has no proven root cause and you must confirm the cause with runtime evidence instead of guessing from source code.

not rated 5 1mo ago C 39 tokens original MIT

ludamo-anli

551

Leobai03/ludamo-codex-skills

Skill Codex

An internal Chinese-language case-search module for finding a matching example from 71 real troubleshooting cases based on the problem and its context.

not rated 5 2mo ago A 82 tokens

use-peek

552

alexmx/peek

Skill Claude Code

Use the peek CLI to inspect, debug, and interact with native macOS app windows. Use when the user asks to debug a macOS app, inspect UI elements, take screenshots, click buttons, or automate interactions with native apps.

not rated 5 changed today A 51 tokens original MIT

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: