AgentHubAgentHub

debugging

43 MCP servers and Agent skills related to debugging, each with install commands, source and popularity data, ready to paste into Cursor, Claude Code and other clients.

Docker

v1.0.10

SkillClawHub16.1k

io.clawhub.ivangdavila/docker

Builds, debugs, hardens, and ships Docker containers, images, and Compose stacks. Use when writing or reviewing a Dockerfile, a compose file, or a CI build step; when a container exits instantly, restart-loops, is OOM-killed, hangs on stop, or exits 137/139/127; when a published port is unreachable, containers cannot resolve each other, or requests hang behind a VPN; when the disk fills and `/var/lib/docker` will not prune; when a build is slow, the cache never hits, or fails only in CI; when `exec format error` or a musl-versus-glibc break is the problem; when choosing a base image or a multi-stage layout; when a registry login or pull rate limit fails; when a secret must stay out of image history; and when volumes need backup, restore or a permission fix. Covers Compose traps and Desktop/colima/OrbStack/Podman differences. Not for Kubernetes manifests or cluster scheduling (`k8s`).

source

EasyEDA API Skill

v1.1.24

SkillClawHub11.8k

io.clawhub.yanranxiaoxi/easyeda-api

EasyEDA Pro API skill for AI agents. Use when working with EasyEDA Pro EDA software, including PCB design, schematic editing, footprint/symbol management, and project operations. Supports live debugging in EasyEDA and EasyEDA extension development. Provides complete API reference (120+ classes, 62 enums, 70 interfaces), extension-development documentation, and a WebSocket bridge server to execute code in the running EasyEDA Pro client. Trigger on: "嘉立创EDA,启动!", "立创EDA,启动!", "EDA,启动!", "EasyEDA", "PCB", "schematic", "footprint", "EDA", "circuit board", "嘉立创EDA", "原理图", "PCB设计". **IMPORTANT**: 嘉立创EDA's English name is **EasyEDA**. They are the SAME product. Never use other transliterations like "EasyEDA Pro" (unless specifically versioned), "EASYEDA", "easyeda", etc. Always use "EasyEDA" for English references and "嘉立创EDA" for Chinese references.

source

Code Mentor

v1.0.2

SkillClawHub8k

io.clawhub.samuelkahessay/code-mentor

Comprehensive AI programming tutor for all levels. Teaches programming through interactive lessons, code review, debugging guidance, algorithm practice, project mentoring, and design pattern exploration. Use when the user wants to: learn a programming language, debug code, understand algorithms, review their code, learn design patterns, practice data structures, prepare for coding interviews, understand best practices, build projects, or get help with homework. Supports Python and JavaScript.

source

Sysadmin Toolbox

v1.1.0

SkillClawHub7k

io.clawhub.jdrhyne/sysadmin-toolbox

Tool discovery and shell one-liner reference for sysadmin, DevOps, and security tasks. AUTO-CONSULT this skill when the user is: troubleshooting network issues, debugging processes, analyzing logs, working with SSL/TLS, managing DNS, testing HTTP endpoints, auditing security, working with containers, writing shell scripts, or asks 'what tool should I use for X'. Source: github.com/trimstray/the-book-of-secret-knowledge

source

Smart Model Switching

v1.0.0

SkillClawHub6.9k

io.clawhub.millibus/smart-model-switching

Auto-route tasks to the cheapest Claude model that works correctly. Three-tier progression: Haiku → Sonnet → Opus. Classify before responding. HAIKU (default): factual Q&A, greetings, reminders, status checks, lookups, simple file ops, heartbeats, casual chat, 1-2 sentence tasks. ESCALATE TO SONNET: code >10 lines, analysis, comparisons, planning, reports, multi-step reasoning, tables, long writing >3 paragraphs, summarization, research synthesis, most user conversations. ESCALATE TO OPUS: architecture decisions, complex debugging, multi-file refactoring, strategic planning, nuanced judgment, deep research, critical production decisions. Rule: If a human needs >30 seconds of focused thinking, escalate. If Sonnet struggles with complexity, go to Opus. Save 50-90% on API costs by starting cheap and escalating only when needed.

source

Developer

v1.0.2

SkillClawHub6.2k

io.clawhub.ivangdavila/developer

Works as a software developer day to day: turning a ticket into merged, shipped, supported code inside a codebase someone else wrote. Use when landing in an unfamiliar repo and hunting for where the change goes; when scoping, splitting, or estimating work; when a bug has to go from report to verified fix; when tests are missing, slow, or flaky; when a pull request is too big to review or a review has stalled; when a dependency upgrade breaks the build; when a schema change or backfill must ship without downtime; when something works locally but fails in CI or production; when a release needs a rollback plan or a flag; when on call and mitigation has to come before root cause; or when deciding what is reversible. Covers environment parity, security on your own diff, and new services. Not for isolation technique (`debugging`), the transformation catalog (`refactoring`), review analysis (`review-code`), or Git mechanics (`git`).

source

Causal Inference

v0.2.0

SkillClawHub4k

io.clawhub.oswalpalash/causal-inference

Add causal reasoning to agent actions. Trigger on ANY high-level action with observable outcomes - emails, messages, calendar changes, file operations, API calls, notifications, reminders, purchases, deployments. Use for planning interventions, debugging failures, predicting outcomes, backfilling historical data for analysis, or answering "what happens if I do X?" Also trigger when reviewing past actions to understand what worked/failed and why.

source

Context7 API Documentation Fetcher

v1.0.0

SkillClawHub3.2k

io.clawhub.am-will/context7-api

Fetch up-to-date library documentation via Context7 API. Use PROACTIVELY when: (1) Working with ANY external library (React, Next.js, Supabase, etc.) (2) User asks about library APIs, patterns, or best practices (3) Implementing features that rely on third-party packages (4) Debugging library-specific issues (5) Need current documentation beyond training data cutoff Always prefer this over guessing library APIs or using outdated knowledge.

source

Related tags

debugging MCP Servers & Skills Collection - AgentHub