Debugging

15,408 mods in this category, of every kind an agent can take. Each one carries what it costs per session, what the scan found, and whether it is the original.

cobbpeng/fpga-hardware-design-and-review-guide

Skill Claude Code

Comprehensive FPGA hardware design guide based on real-world project experience. Covers pipeline architecture, timing optimization, SystemVerilog coding patterns, CDC handling, and practical debugging techniques. Use this skill when: (1) designing FPGA modules with timing constraints, (2) implementing video processing…

not rated 18 +1 7mo ago A 99 tokens original MIT

ProxymanApp/proxyman-SKILL.md

Skill Codex

Download, install, launch, and prepare Proxyman on macOS, Windows, or Linux. Use when Proxyman is absent or the user asks to install, download, start, or prepare Proxyman before MCP configuration.

not rated 18 +1 17d ago A 53 tokens

diagnose

603

emiliosheinz/agent-skills

Skill Claude CodeCodex needs its repo

Root-causes complex bugs through a structured loop and saves a verified fix proposal — it diagnoses, it never fixes. Builds a fast deterministic feedback loop, reproduces, then probes ranked falsifiable hypotheses with parallel subagents and confirms the cause adversarially before writing the report. Use when a bug…

not rated 18 1mo ago A 102 tokens original MIT

cs-map

604

3D-Tech-Solutions/code-scalpel

Skill Claude Code

Map project architecture: discover modules, build call graphs, visualize structure, trace critical paths. Complete architecture overview with dependency flows.

not rated 18 +1 2mo ago A 28 tokens

conectlens/lenserfight

Skill Claude CodeCodex

Use when designing, auditing, refactoring, or expanding complex repositories where the AI should first discover architecture from the codebase instead of being constrained by premature schemas, rigid YAML definitions, or hardcoded implementation assumptions.

not rated 18 +1 28d ago A 49 tokens original MIT

de-postmortem-writer

606

ivanshamaev/de-agent-skills

Skill Claude CodeCodex

DE blameless postmortem — incident timeline reconstruction, impact quantification, root cause chain (5 Whys), corrective actions (CAPA), postmortem document template, severity classification, SLA breach reporting, communication templates, lessons-learned facilitation, postmortem review checklist.

not rated 18 +1 3mo ago A 65 tokens

extend-skill

607

neat-technologies/neat

Skill Claude CodeCodex

/neat extend is a set of six MCP surgical tools for long-tail instrumentation — three diagnostic (read-only), three operative (file-scope-restricted, idempotent, reversible, observable). The user's MCP agent reasons; NEAT operates. NEAT holds no LLM key and never auto-applies. No standalone CLI variant. Discovery is…

not rated 18 5d ago A 106 tokens original Apache-2.0

sre-skills

608

anyshift-io/sre-skills

Plugin Claude Code

Bundles 5 skills · 1,185 tokens together

Vendor-neutral SRE methodology skills for AI agents: investigate a live incident, analyze change impact, hand over oncall, author a postmortem, audit reliability. Runs offline against fixtures, no credentials required.

not rated 17 10d ago A tokens not measured original Apache-2.0

eyeroll

609

mnvsk97/eyeroll

Plugin Claude Code

Bundles 1 skill, 1 command · 35 tokens together

AI eyes that roll through video footage. Analyze screen recordings, Loom videos, and screenshots to fix bugs and build features.

not rated 17 3mo ago A tokens not measured original MIT

rust-doctor

610

arthjean/rust-doctor

Skill Claude CodeCodex

Use when Rust code just changed and must not regress, when the user asks to scan, audit or health-check a Cargo workspace, says "rust-doctor", or wants one of its findings explained, tuned or switched off.

not rated 17 14d ago A SkillSpector: warn 49 tokens original Apache-2.0

craft-skills

612

alexiolan/craft-skills

Plugin Claude Code

Bundles 18 skills, 1 hook · 914 tokens together

Structured development skills for any project. Provides brainstorming, planning, parallel agent development, browser testing, systematic debugging, and self-improvement workflows.

not rated 17 2mo ago A tokens not measured GPL-3.0

bug-fix

613

bluebear-io/angry-bear

Skill Claude Code needs its repo

Regression-first TDD bug fix workflow with real tests. Use when: fixing bugs, resolving regressions, addressing runtime errors, debugging failures, or when the user reports something broken. Triggers on words like: bug, broken, error, crash, regression, not working, fix.

not rated 17 yesterday A SkillSpector: pass 61 tokens original MIT

fix-failing-tests

614

KnoxOps/agent-runbook

Skill Claude Code

Iteratively fix all failing tests until the test suite is green.

not rated 17 1mo ago A 17 tokens original Apache-2.0

js-reverse-mcp

615

jenn619/JS-reverse-mcp

MCP server Claude CodeCodexCursor +2

A local MCP server for reverse engineering JavaScript, the language used to add behavior to web pages and many applications.

not rated 17 2mo ago A tokens not measured

mcp-code-sandbox

616

chrishayuk/mcp-code-sandbox

MCP server Claude CodeCodexCursor +2

MCP server "mcp-code-sandbox" as configured in chrishayuk/mcp-code-sandbox. Runs locally from the mcp-code-sandbox Python package.

not rated 17 1y ago A tokens not measured

superpowers-mcp

617

erophames/superpowers-mcp

MCP server Claude CodeCodexCursor +2

Superpowers skills library (TDD, debugging, collaboration workflows) as an MCP server for VSCode and Antigravity. Runs locally from the superpowers-mcp npm package.

not rated 17 5mo ago A tokens not measured

systematic-debugging

618

HiAi-gg/hiai-opencode

Skill Claude CodeCodex

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

not rated 17 +1 2d ago A 21 tokens

opengrep

619

opengrep/skills

Skill Claude CodeCodex

Run Opengrep for pattern-based code search and security scanning. Use when grep is insufficient for finding code patterns that require structural understanding (function calls, data flow, nested structures). Also use for security vulnerability detection with custom YAML rules.

not rated 17 7mo ago B 51 tokens original MIT

devharness

621

InDate/devharness

Plugin Claude Code

Bundles 1 skill, 1 hook, 1 MCP server · 148 tokens together

Run and debug a live app from inside Claude Code: breakpoints and variable inspection in Chrome and Node.js, managed dev servers, and replayable call history so setup is never re-driven by hand.

not rated 16 8d ago A tokens not measured original MIT

jahro-logging

622

jahro-console/unity-agent-skills

Skill Claude CodeCodex

Reviews and improves Debug.Log usage in Unity C# projects following structured logging principles: context tags, severity contracts, boundary-based placement, and criticality tiers. Detects common antipatterns (naked Debug.Log, logging in Update, stringly-typed errors), adds missing logs at system/state/error/external…

not rated 16 5mo ago A 111 tokens original MIT

PatrickGallucci/fabric-skills

Skill Claude CodeCodex

Diagnose and resolve Microsoft Fabric Dataflow Gen2 performance issues including slow refresh times, Fast Copy optimization, query folding failures, staging bottlenecks, gateway latency, incremental refresh tuning, capacity throttling, and data destination write performance. Use when troubleshooting dataflow refresh…

not rated 16 3mo ago A 118 tokens original MIT

ssssota/chapplin

Skill Claude CodeCodex

Build and debug MCP App-enabled tools in existing projects scaffolded by create-chapplin. Use when extending tools/.tsx with defineTool and defineApp , wiring structuredContent and meta for UI data flow, handling runtime differences across react/preact/solid/hono targets, or troubleshooting chapplin preview and…

not rated 16 2d ago A 77 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: