Debugging skills

10,952 tagged Debugging, measured the same way as everything else here.

Browse within: LLM 142agent 114skills 109cli 106agents 91agentic-ai 81javascript 81cursor 69ai-coding 51claude-code-plugin 44ab-testing 42antigravity 41copilot 40mcp-server 38

network-troubleshoot

505

CacinieP/network-troubleshoot-skill

Skill Claude CodeCodex

Systematic network troubleshooting for developers. Diagnoses connectivity, DNS, proxy, SSL/TLS, HTTP, firewall, and package manager issues with automated diagnostic commands and resolution steps. Includes proxy layer mismatch detection for multi-process apps (Electron+Go, Docker Desktop, VS Code+extensions).

not rated 8 4d ago C 62 tokens original MIT

line-locator

506

unkluco/line-locator

Skill Claude CodeCodex

Định vị dòng trước khi đọc file hoặc tìm file trong cây thư mục — tránh đọc mù, tiết kiệm token. Dùng khi cần tìm hàm, class, symbol, hoặc bất kỳ pattern nào trong source code trước khi gọi viewrange. Hai công cụ: findtree.py (tìm file nào có chứa pattern) và findtool.py (tìm dòng nào trong một file).

not rated 7 6mo ago A 85 tokens original MIT

cuda-kernel-optimizer

507

troycheng/cuda-kernel-optimizer

Skill Codex

Use when optimizing or diagnosing GPU workload performance with CUDA, CUTLASS, Triton, PyTorch, vLLM or TensorRT-LLM; interpreting NCU, Nsys or PyTorch Profiler evidence; or preparing the workload and correctness checks for such optimization. General coding, skill maintenance and conceptual GPU questions do not…

not rated 7 changed 16d ago A 77 tokens original MIT

systematic-debugging

508

bh-rat/steer

Skill Claude CodeCodex

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

not rated 7 3mo ago A 21 tokens original MIT

rigor3

509

MaySudo/rigor3

Skill Codex

Audit, score, remediate, and verify repositories across code hygiene, architecture hygiene, and engineering hygiene. Use for an explicit Rigor3 or three-hygiene request, a strict repository-wide quality audit, a cross-dimensional cleanup plan, or before-and-after verification. Do not use for an ordinary focused review…

not rated 7 2mo ago A 78 tokens original MIT

save-bugfix

510

hifriendbot/cogmemai-mcp

Skill Claude CodeCodex

After resolving any bug, save what broke, the root cause, and the fix as a CogmemAi memory so the same problem never has to be debugged twice. Use immediately after a bug is fixed, after diagnosing a flaky test, after recovering from a production incident, or after the user says "got it working", "that fixed it"…

not rated 7 12d ago A 97 tokens original MIT

codebase-intelligence

512

bntvllnt/codebase-intelligence

Skill Claude CodeCodex

Query the codebase-intelligence CLI to understand TypeScript architecture, dependencies, blast radius, and risk before reading files. Use for any "how is this structured", "what breaks if I change X", "where is the complexity" question.

not rated 7 3d ago A 54 tokens original MIT

debug-agent

513

ReSkin-Games/memorybank-plus

Skill Claude CodeCodex

Systematic evidence-based debugging using runtime logs. Generates hypotheses, instruments code with NDJSON logs, guides reproduction, analyzes log evidence, and iterates until root cause is proven with cited log lines. Use when the user reports a bug, unexpected behavior, or asks to debug an issue.

not rated 7 5mo ago A 60 tokens copy · 88% MIT

safelint

514

shelkesays/safelint

Skill Claude CodeCodex

Run safelint static analysis on the user's project and present Holzmann Power-of-Ten safety violations grouped by file. Supports any language registered with safelint (Python, JavaScript, TypeScript including TSX / AssemblyScript, Java, Rust, Go, PHP, C, and C++ today; more can be added). Use this for "safelint…

not rated 7 2d ago B 129 tokens original MIT

recursive-dep-trace

515

gyy0592/claude-config

Skill Claude CodeCodex

Recursive first-principles static dependency tracing for a single code entry point, producing a real-time stream-of-consciousness trace markdown that embodies the AI's reading process as a call-stack of TODOs. Given one entry script (e.g. train.py, minimalgenerateimagev3.py, main.py), the AI reads the code…

not rated 7 5mo ago A 270 tokens

ui-click-debug

516

yangfch3/Unity-MCP-Server

Skill Claude CodeCodex

A Unity troubleshooting skill for UI elements that do not respond to clicks. It uses a runtime raycast, a test that shows which object receives a pointer event, to find obstructions or interaction settings.

not rated 7 1mo ago A 54 tokens original MIT

claude-3p-parity

517

kingcharleslzy-ai/claude-code-deepseek-3p-parity-skill

Skill Codex

Diagnose and repair Claude Desktop Mac third-party inference / 3p / DeepSeek-style Claude Code setups for best-effort parity with first-party Claude Code. Use when users mention Claude Code Mac app developer mode, Claude Desktop 3p, third-party API providers, DeepSeek V4 Pro/Flash, bypassPermissions not working…

not rated 7 5mo ago B 122 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 7 4mo ago A 243 tokens WTFPL

代码调试

519

jianchen08/Agent-os-open

Skill Claude CodeCodex

A debugging workflow that reproduces a problem with a failing test, collects evidence, finds the underlying cause, applies a fix, and runs regression checks. Regression checks verify that the fix does not break behavior that already worked.

not rated 7 changed 1mo ago A SkillSpector: pass 82 tokens original Apache-2.0

rebound

520

aldefy/rebound-skill

Skill Claude CodeCodex

Rebound recomposition budget monitor skill for Compose performance analysis. Guides budget class interpretation, violation diagnosis, skip rate analysis, stability optimization, CLI usage, and IDE plugin workflow. Use this skill whenever the user mentions recomposition, budget, violation, Rebound, skip rate, jank…

not rated 7 7mo ago A 145 tokens original Apache-2.0

evaluate-bug

521

zhoushoujianwork/clawflow

Skill Claude CodeCodex

Evaluate a bug-labeled issue for reproducibility, root cause, and fix difficulty; post a structured assessment comment.

not rated 7 +1 changed 1mo ago A 27 tokens

dantotsu

522

bsene/skills

Skill Claude CodeCodex

Use this skill when the user wants to investigate a bug, defect, incident, or quality issue and find its root cause — including requests to run a "5 whys" analysis, write a postmortem, do a root-cause analysis (RCA), figure out why a bug reached production or slipped past code review/QA, set up a recurring…

not rated 7 +1 changed 26d ago A 193 tokens

diffwarden

523

jperocho/diffwarden

Skill Claude CodeCodex

Review deeply. Fix safely. Report briefly. Work anywhere — PRs, git workspaces, non-git folders, and documents. Inspect diffs or files, classify findings, fix safe issues, verify, and loop until ready. Supports /diffwarden and /dw slash commands in Claude Code, Cursor, and Pi Agent; Codex CLI uses $diffwarden or…

not rated 7 2mo ago A 80 tokens original MIT

a1-evo-audio-engineer

524

daredoole/evoburrow-mcp

Skill Codex

Analyze, troubleshoot, and operate A1 Evo AcoustiX workflows and Denon/Marantz LAN control using measured artifacts, conservative audio-engineering reasoning, and explicit confirmation for receiver changes.

not rated 7 4d ago A 48 tokens original MIT

aiqsa-troubleshooting

525

insciqq/AIQSA

Skill Claude CodeCodex

Diagnose an AIQSA installation from its read-only health telemetry, then bounded logs and process state. Use for failed or stuck runs, errors users hit, sign-in failures, timeouts, provider/tool errors, background jobs, startup failures, slow answers, users' problem reports, and preparing a sanitized summary. Collect…

not rated 7 changed yesterday A 78 tokens AGPL-3.0

dyCuong03/unity-agent-team

Skill Claude Code

ECB playback failure debugger for Unity DOTS/ECS. Load when you see: "EntityCommandBuffer playback failed", "entityExists=False", "Buffer does not exist on entity", "Component does not exist on entity", "AppendDestroyedEntityRecordError", "Invalid deferred entity", "Duplicate AddComponent during playback"…

not rated 7 3mo ago A 120 tokens original MIT

docs

527

DivyamTalwar/Structorium

Skill Claude CodeCodex

Skill "docs" from DivyamTalwar/Structorium, covering structorium, 1. your job, 2. the workflow, outer loop — scan and check and inner loop — fix issues.

not rated 6 +5 2mo ago A SkillSpector: warn 0 tokens original MIT

idapython

528

fantay0312/ida-pro-mcp-plus

Skill Claude CodeCodex

IDA Pro Python scripting for reverse engineering. Use when writing IDAPython scripts, analyzing binaries, working with IDA's API for disassembly, decompilation (Hex-Rays), type systems, cross-references, functions, segments, or any IDA database manipulation. Covers ida modules (50+), idautils iterators, and common…

not rated 6 6mo ago A 77 tokens copy · 100% 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: