1,660 free skills
Debugging skills
Skills for systematic debugging — reproducing bugs, reading stack traces, bisecting regressions, and diagnosing flaky failures.
Sourced from real, public repositories — synced daily, never invented.
1,660 free skills
Skills for systematic debugging — reproducing bugs, reading stack traces, bisecting regressions, and diagnosing flaky failures.
Sourced from real, public repositories — synced daily, never invented.
15 tools across six categories
13 of them never send your data anywhere
Free · No signup · No trial clock
SEE THE DIRECTORY
Ansible Playbook Debugger
agentskillexchange/skills
Diagnoses Ansible playbook failures using ansible-playbook –check –diff mode, ansible-lint, and the Ansible callback plugin API. Parses task execution results and suggests fixes for common module errors in ansible.builtin and community collections.
debug
ibm-self-serve-assets/building-blocks
Use when playbooks fail with UNREACHABLE, permission denied, MODULE FAILURE, or undefined variable errors. Use when SSH connections fail or sudo password is missing.
opentofu-skill-gcp
jpalley/opentofu-gcp-skill
Use when working with OpenTofu for GCP - creating modules, writing tests (native test framework, Terratest), setting up CI/CD pipelines with Cloud Build, reviewing configurations, state encryption with GCP KMS, debugging state issues, implementing security scanning (trivy, checkov, prowler), or making infrastructure-as-code architecture decisions for Google Cloud Platform
vllm-embedding-server
yenhao-huang/custom_skills
Start, debug, and verify local vLLM embedding servers on this machine, especially Qwen embedding models under /mnt/share_data_78 with the vLLM virtualenv at /tmp2/howard/venv_manager/vllm. Use when the user asks to open/start/serve an embedding model with vLLM, mentions qwen-embedding, Qwen3 embedding, first GPU/card, or needs an OpenAI-compatible /v1/embeddings endpoint.
embedded-debug
shark0304/personal-embeded-debug-skill
Production-oriented Embedded Failure Intelligence Workbench. Use for real firmware, BSP, RTOS, MCU, or embedded Linux projects that need evidence-driven fault triage, board bring-up, runtime/source/kernel identity alignment, module ABI or DTB/DTS verification, driver probe dependencies, DMA/cache analysis, Zephyr/ESP-IDF configuration debugging, field-log analysis, OTA/low-power/TinyML diagnosis, project onboarding, target-operation safety policy, evidence integrity and sanitization, failure handoff, fix verification, or regression preservation. Prefer versioned debug packets, exact target identity, ranked hypotheses, deterministic analyzers, guarded hardware actions, and verified golden cases.
netlify-deployment
monkilabs/opencastle
Deploy sites, configure serverless and edge functions, and verify builds on Netlify. Use when the user mentions: 'deploy preview', 'configure netlify.toml', or 'debug a failed deploy'. Trigger terms: build error, Netlify Functions, deploy logs, deploy preview
embedded-logging
ye-12s/my-ai-agents-explor
Use when implementing printf-style debugging in embedded systems, creating lightweight logging frameworks, or optimizing log output for resource-constrained devices
mongodb-production-query
javeedishaq/ai-workflow-orchestrator
Query Ballee production MongoDB (Meteor app) using .env.local credentials; use when debugging Meteor data, verifying MongoDB documents, investigating sync issues, or exploring legacy data for migration
redis
iam-nazmul/drcr
This skill should be used when working with Redis — writing or reviewing redis-py client code, deciding what to cache and for how long, choosing a Redis data structure (string, hash, list, set, sorted set), setting cache keys/namespacing/TTLs, configuring connection pooling, using Redis for session storage, rate limiting, pub/sub, or debugging Redis timeouts/connection errors. Covers Redis and the redis-py Python client specifically, not Celery task design (see the celery skill for task semantics) — this skill is for Redis-the-datastore underneath it.
sqlite-vec-skilld
harlan-zw/skilld
ALWAYS use when writing code importing \"sqlite-vec\". Consult for debugging, best practices, or modifying sqlite-vec, sqlite vec.
log-aggregation
aspectrr/deer
ELK Stack deployment, Logstash pipeline building, Filebeat configuration, and Kibana dashboard setup. Use when deploying ES clusters, building logstash pipelines, configuring beats, or debugging log aggregation issues.
kafka
aspectrr/deer
Kafka topic management, consumer group monitoring, message production/consumption, and cluster health diagnostics. Use when working with Kafka brokers, topics, consumer lag, or debugging pipeline issues.
message-queue-debugging
paulpas/agent-skill-router
Debugs Kafka, RabbitMQ, and SQS message queues with consumer lag analysis,
kafka-event-flow
onrcanogul/microservices-starter-template
Use when working with Kafka messaging: defining events, creating topics, producing/consuming EventWrapper messages, configuring DLT/retry, or debugging Kafka deserialization. Covers EventPublisher trace propagation, Consumer/Producer contracts, topicNamer pattern, trusted packages, and DLT configuration.
drogon-cpp-engineer
pk13055/tws-drogon-docker-template
Develops, debugs, and scales high-performance Drogon C++ web apps—PostgreSQL via DbClient/ORM, RabbitMQ (AMQP-CPP) with Trantor event-loop integration, HttpController and WebSocketController, drogon_ctl scaffolding, config.json, HttpFilter middleware. Use when editing Drogon code, Postgres, messaging, drogon::app(), CMake, or C++ web APIs in this repository.
azure-event-hubs
robgibbens/connectionsexplorer
Expert knowledge for Azure Event Hubs development including troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, integrations & coding patterns, and deployment. Use when building, debugging, or optimizing Azure Event Hubs applications. Not for Azure Service Bus (use azure-service-bus), Azure Event Grid (use azure-event-grid), Azure Notification Hubs (use azure-notification-hubs), Azure Stream Analytics (use azure-stream-analytics).
taasim-streaming-debug
mohamedamineelabidi/casamotion
Use this skill when Kafka -> Flink -> Cassandra flow is stale, delayed, missing records, or behavior is inconsistent and you need structured runtime plus code-path debugging.
networking-transport
d-padmanabhan/agent-engineering-handbook
Networking and transport-layer architecture for production services. TCP keepalive, head-of-line blocking, TTFB budget, HTTP/1.1 vs HTTP/2 vs HTTP/3, when to choose gRPC/Protobuf over REST/JSON, connection pooling, long-lived connections (websockets / SSE / gRPC streaming), and CDN-to-origin patterns. Use when designing service-to-service APIs, debugging tail latency, choosing a wire protocol, configuring load balancer idle timeouts, or evaluating HTTP/3 / QUIC for mobile / cross-region workloads.
cmk:sui-sdk
commandosslabs/ai-devkit
This skill should be used when the user asks to "use the Sui SDK", "call a Sui full node", "fetch Sui objects, coins, balances, or transactions", "subscribe to Sui events or checkpoints", "execute or simulate a Sui transaction", or "pick or upgrade @mysten/sui, dapp-kit, or a Rust Sui crate" — and whenever writing, reviewing, or debugging any code that talks to a Sui full node, even if nobody mentions gRPC, JSON-RPC, or a transport at all, because Sui JSON-RPC was switched off in 2026 and models trained on older data still generate it.
debug-grpc-connection
getbindu/bindu
Diagnose gRPC connection issues between the Bindu core and a language SDK. Use when an SDK fails to register, HandleMessages calls time out, "connection refused" on :3774, heartbeats stop arriving, or the core logs "agent silently died".
test-rest-health
deadl1f7/dcs-hivemind
Test REST endpoint health. Use when: verifying REST API availability, debugging REST connection issues, checking gRPC client status via REST, validating proto catalogue via REST API.
terminal-fish
iamfourh2e/rust-skill
Fish shell configuration, aliases, gRPC debugging, PostgreSQL CLI helpers, and dev workflow shortcuts for the Anachak platform.
tailwind
versaprav1/hyperframes
Tailwind CSS v4.2 browser-runtime patterns for HyperFrames compositions. Use when scaffolding or editing projects created with `hyperframes init --tailwind`, writing Tailwind utility classes in composition HTML, adding CSS-first Tailwind v4 theme tokens, debugging v3 vs v4 syntax, or deciding when to compile Tailwind to CSS instead of using the browser runtime.
tailwind
malikkaraoui/hyperframesclaude
Tailwind CSS v4.2 browser-runtime patterns for HyperFrames compositions. Use when scaffolding or editing projects created with `hyperframes init --tailwind`, writing Tailwind utility classes in composition HTML, adding CSS-first Tailwind v4 theme tokens, debugging v3 vs v4 syntax, or deciding when to compile Tailwind to CSS instead of using the browser runtime.
tailwind
wushqd/framevideo
Tailwind CSS v4.2 browser-runtime patterns for FrameVideo compositions. Use when scaffolding or editing projects created with `framevideo init --tailwind`, writing Tailwind utility classes in composition HTML, adding CSS-first Tailwind v4 theme tokens, debugging v3 vs v4 syntax, or deciding when to compile Tailwind to CSS instead of using the browser runtime.
tailwind
aiskillstore/marketplace
Tailwind CSS v4.2 browser-runtime patterns for HyperFrames compositions. Use when scaffolding or editing projects created with `hyperframes init --tailwind`, writing Tailwind utility classes in composition HTML, adding CSS-first Tailwind v4 theme tokens, debugging v3 vs v4 syntax, or deciding when to compile Tailwind to CSS instead of using the browser runtime.
tailwind
xiaoqiangtian854-beep/hyperframes
Tailwind CSS v4.2 browser-runtime patterns for HyperFrames compositions. Use when scaffolding or editing projects created with `hyperframes init --tailwind`, writing Tailwind utility classes in composition HTML, adding CSS-first Tailwind v4 theme tokens, debugging v3 vs v4 syntax, or deciding when to compile Tailwind to CSS instead of using the browser runtime.
tailwind
raciel88p/hyperframes
Tailwind CSS v4.2 browser-runtime patterns for HyperFrames compositions. Use when scaffolding or editing projects created with `hyperframes init --tailwind`, writing Tailwind utility classes in composition HTML, adding CSS-first Tailwind v4 theme tokens, debugging v3 vs v4 syntax, or deciding when to compile Tailwind to CSS instead of using the browser runtime.
tailwind
easttxkravmaga/claude
Tailwind CSS v4.2 browser-runtime patterns for HyperFrames compositions. Use when scaffolding or editing projects created with `hyperframes init --tailwind`, writing Tailwind utility classes in composition HTML, adding CSS-first Tailwind v4 theme tokens, debugging v3 vs v4 syntax, or deciding when to compile Tailwind to CSS instead of using the browser runtime.
retrieving-mlflow-traces
panlm/mlflow-skills
Retrieves MLflow traces using CLI or Python API. Use when the user asks to get a trace by ID, find traces, filter traces by status/tags/metadata/execution time, query traces, or debug failed traces. Triggers on "get trace", "search traces", "find failed traces", "filter traces by", "traces slower than", "query MLflow traces".
j6-ucp-perfetto-trace-catcher
horizonrobotics/oe-skills
Capture UCP (Horizon Robotics inference SDK) Perfetto traces from a J6 development board. Use this skill whenever the user wants to grab UCP traces, capture Perfetto traces on a Horizon dev board, debug UCP scheduling issues with trace data, or pull .pftrace files from a remote board. Also trigger when the user mentions UCP performance analysis, UCP trace, hrt_model_exec tracing, or BPU trace capture on J6/S1000 platforms. Do NOT use for DSP trace or Chrome trace.
debug-trace
udecode/better-convex
Use when errors occur deep in execution and you need to trace back to find the original trigger - systematically traces bugs backward through call stack, adding instrumentation when needed, to identify source of invalid data or incorrect behavior
memory-profiler
khaneliman/khanelinix
Diagnose memory inefficiencies, capture high-resolution memory profiles, and execute architectural refactoring across C++, Rust, TypeScript/Node.js, .NET, and Python. Use when troubleshooting memory leaks, out-of-memory (OOM) errors, or heap fragmentation.
css
kswedberg/kswedberg-skills
Use this skill when helping with CSS code. Triggers include writing or debugging code, refactoring code, and improving code readability and maintainability. Trigger this skill when the current project is using CSS.
css-debug
lionad-morotar/local-tools
>-
atproto-oauth
zentered/atproto-skills
This skill should be used when the user asks to "implement ATProto OAuth", "add Bluesky login", "debug DPoP proofs", "set up pushed authorization requests", "configure PKCE for ATProto", "fix ATProto OAuth errors", "set up client metadata", "debug token exchange", "authenticate with Bluesky", "refresh token keeps invalidating", or mentions DPoP nonce issues, client assertions, base64url padding errors, OAuth callback verification, confidential client setup, or OAuth for Bluesky/AT Protocol apps. Covers the full OAuth flow — for identity resolution and handle lookups, see atproto-domain instead.
debug-ci
materializeinc/materialize
Investigate CI failures on a PR using gh and bk CLI tools. Triggers when asked about failing checks, Buildkite failures, or CI issues on a PR.
azure-payment-hsm
robgibbens/connectionsexplorer
Expert knowledge for Azure Payment Hsm development including troubleshooting, best practices, decision making, architecture & design patterns, security, and configuration. Use when building, debugging, or optimizing Azure Payment Hsm applications. Not for Azure Dedicated HSM (use azure-dedicated-hsm), Azure Key Vault (use azure-key-vault), Azure Cloud Hsm (use azure-cloud-hsm).
vscode-debug-fullstack
jlpbiuma/agent-skills
>-
etl-debugger
sunnyyeahboiii/unicornsedu-etl-pipeline
Use when an ETL pipeline is failing or producing incorrect data. Triggers include count mismatches, duplicate rows, missing rows, broken retries, bad incremental cursors, transform regressions, batch replay issues, and Supabase/Postgres loads that succeed partially or drift from source data.
jupyter
anntnzrb/agents
Work with Jupyter notebooks without leaving Claude Code. Execute cells, inspect outputs, validate structure, and convert formats. Activate when working with .ipynb files, user mentions notebooks, Jupyter, or needs to run/debug notebook code.
jupyter
ming-kai-lc/fyp-project
Specialized assistant for working with Jupyter notebooks (.ipynb files). Use for analyzing, editing, debugging, or executing code in notebooks. Helps with data analysis, machine learning, deep learning, data visualization, and scientific computing workflows. Can read notebook contents, modify cells, execute Python code in the kernel, add documentation, and troubleshoot errors.
spark-engineer
polip/opencode-skills
Use when writing Spark jobs, debugging performance issues, or configuring cluster settings for Apache Spark applications, distributed data processing pipelines, or big data workloads. Invoke to write DataFrame transformations, optimize Spark SQL queries, implement RDD pipelines, tune shuffle operations, configure executor memory, process .parquet files, handle data partitioning, or build structured streaming analytics.
spark-optimization
henryhawke/skills
Optimize Apache Spark jobs with partitioning, caching, shuffle optimization, and memory tuning. Use when improving Spark performance, debugging slow jobs, or scaling data processing pipelines.
spark-optimization
shahin1717/ai-skills
Optimize Apache Spark jobs with partitioning, caching, shuffle optimization, and memory tuning. Use when improving Spark performance, debugging slow jobs, or scaling data processing pipelines.
spark-optimization
mowgliph/everything-agents-skills
Optimize Apache Spark jobs with partitioning, caching, shuffle optimization, and memory tuning. Use when improving Spark performance, debugging slow jobs, or scaling data processing pipelines.
debugging-dags
420company/artemis
Comprehensive DAG failure diagnosis and root cause analysis. Use for complex debugging requests requiring deep investigation like "diagnose and fix the pipeline", "full root cause analysis", "why is this failing and how to prevent it". For simple debugging ("why did dag fail", "show logs"), the airflow entrypoint skill handles it directly. This skill provides structured investigation and prevention recommendations.
debugging-dbt-errors
miptah21/skills
|
debugging-dags
miptah21/skills
Comprehensive DAG failure diagnosis and root cause analysis. Use for complex debugging requests requiring deep investigation like "diagnose and fix the pipeline", "full root cause analysis", "why is this failing and how to prevent it". For simple debugging ("why did dag fail", "show logs"), the airflow entrypoint skill handles it directly. This skill provides structured investigation and prevention recommendations.
url-scraping
jez500/pricebuddy
This skill should be used when the user asks to "scrape a URL", "fix scraping", "debug scraping", "add a store", "configure selectors", "extract price", "extract data from a page", discusses scraping strategies, store configuration, price extraction, availability detection, or troubleshoots why a URL is not returning data.
debug-crawler
opensanctions/opensanctions
Investigate a failing crawler from an issues.json artifact URL and propose a fix. Covers fetching error details, inspecting source data via Zyte, and common failure patterns including sources that are blocked, geo-blocked, 403/429-throttled, or behind a JavaScript challenge or anti-bot protection.
writing-crawler-specs
chamirusenarath96/crawler
Guide for writing new crawler spec files in YAML/JSON format. Use when creating, editing, or debugging crawler specs, or when the user wants to add a new crawl target.
crawler-reverse
ice-a/muzi_skills
Use this skill for authorized web traffic analysis, JS obfuscation troubleshooting, request-signature tracing, replay debugging, anti-bot workflow inspection, cookie/token/header origin analysis, and browser-assisted reverse engineering. Refuse or redirect high-risk unauthorized misuse such as bypassing access controls, abusive scraping, credential abuse, or evasion for harmful purposes.
metal-shader-expert
curiositech/windags-skills
20 years Weta/Pixar experience in real-time graphics, Metal shaders, and visual effects. Expert in MSL shaders, PBR rendering, tile-based deferred rendering (TBDR), and GPU debugging. Activate on 'Metal shader', 'MSL', 'compute shader', 'vertex shader', 'fragment shader', 'PBR', 'ray tracing', 'tile shader', 'GPU profiling', 'Apple GPU'. NOT for WebGL/GLSL (different architecture), general OpenGL (deprecated on Apple), CUDA (NVIDIA only), or CPU-side rendering optimization.
metal-shader-expert
afolkest/metal-lic
20 years Weta/Pixar experience in real-time graphics, Metal shaders, and visual effects. Expert in MSL shaders, PBR rendering, tile-based deferred rendering (TBDR), and GPU debugging. Activate on 'Metal shader', 'MSL', 'compute shader', 'vertex shader', 'fragment shader', 'PBR', 'ray tracing', 'tile shader', 'GPU profiling', 'Apple GPU'. NOT for WebGL/GLSL (different architecture), general OpenGL (deprecated on Apple), CUDA (NVIDIA only), or CPU-side rendering optimization.
shader-debug
pthm/soup
This skill should be used when debugging GLSL shaders, when shader output looks wrong, when the user mentions "shader not working", "debug shader", "test shader", or when troubleshooting GPU rendering issues in this project.
shader-dev
hhu3637kr/skills
Use when the user asks to create, debug, review, or explain GLSL/Shadertoy shader code or real-time visual effects such as ray marching, SDFs, procedural noise, lighting, particles, fluids, or post-processing. Do not use for general frontend animation, CSS effects, image editing, or non-shader graphics tasks.
ue-bug-debugging
zetaaaaaaaaaaa/taagent
This skill should be used when debugging rendering issues in Unreal Engine, including visual artifacts, missing features, or unexpected behavior in shaders, materials, or lighting. Trigger when the user asks about "why something looks wrong", "debugging a rendering bug", or analyzing GPU captures from RenderDoc.
webgl-3d-architect
saidabror552-dev/webgl-3d-architect
Comprehensive expert guide for architecting, building, and optimizing interactive 3D WebGL, Three.js, and GLSL web experiences. Use this skill whenever the user asks to build, modify, debug, or optimize 3D web applications, scrollytelling camera rigs, procedural shaders, particle systems, physics simulations, HDR post-processing pipelines, or award-winning creative web animations (e.g. ThreeUI, Awwwards, FWA caliber experiences).
threejs
sfrmrc/skills
Use when building or debugging interactive 3D scenes on the web with Three.js (scene/camera/renderer, lights/materials, GLTF loading, controls, performance). Helpful for designers shipping 3D UI moments.