bmad-os-gh-triage

38.8k

bmad-code-org

Fetch all GitHub issues via gh CLI and use AI agents to deeply analyze, cluster, and prioritize issues

voice-ai-development

21.8k

davila7

Expert in building voice AI applications - from real-time voice agents to voice-enabled apps. Covers OpenAI Realtime API, Vapi for voice agents, Deepgram for transcription, ElevenLabs for synthesis, LiveKit for real-time infrastructure, and WebRTC fundamentals. Knows how to build low-latency, production-ready voice experiences. Use when: voice ai, voice agent, speech to text, text to speech, realtime voice.

stable-baselines3

21.8k

davila7

Use this skill for reinforcement learning tasks including training RL agents (PPO, SAC, DQN, TD3, DDPG, A2C, etc.), creating custom Gym environments, implementing callbacks for monitoring and control, using vectorized environments for parallel training, and integrating with deep RL workflows. This skill should be used when users request RL algorithm implementation, agent training, environment design, or RL experimentation.

deepinit

8.0k

Yeachan-Heo

Deep codebase initialization with hierarchical AGENTS.md documentation

deep-research

1.8k

openclaw

Deep Research Agent specializes in complex, multi-step research tasks that require planning, decomposition, and long-context reasoning across tools and files by we-crafted.com/agents/deep-research

lindy-migration-deep-dive

1.5k

Jeremylongshore Claude Code Plugins Plus Skills Lindy Migration Deep Dive

Advanced migration strategies for Lindy AI integrations. Use when migrating from other platforms, consolidating agents, or performing major architecture changes. Trigger with phrases like "lindy migration", "migrate to lindy", "lindy platform migration", "switch to lindy".

microsoft-skill-creator

1.4k

MicrosoftDocs

Create agent skills for Microsoft technologies using Learn MCP tools. Use when users want to create a skill that teaches agents about any Microsoft technology, library, framework, or service (Azure, .NET, M365, VS Code, Bicep, etc.). Investigates topics deeply, then generates a hybrid skill storing essential knowledge locally while enabling dynamic deeper investigation.

deep-debug

572

jezweb

Multi-agent investigation for stubborn bugs. Use when: going in circles debugging, need to investigate browser/API interactions, complex bugs resisting normal debugging, or when symptoms don't match expectations. Launches parallel agents with different perspectives and uses Chrome tools for evidence gathering.

openclaw-audit-watchdog

557

prompt-security

Automated daily security audits for OpenClaw agents with email reporting. Runs deep audits and sends formatted reports.

orchestrate-review

509

agent-sh

Use when user asks to "deep review the code", "thorough code review", "multi-pass review", or when orchestrating the Phase 9 review loop. Provides review pass definitions (code quality, security, performance, test coverage), signal detection patterns, and iteration algorithms.

profiling-tables

258

astronomer

Deep-dive data profiling for a specific table. Use when the user asks to profile a table, wants statistics about a dataset, asks about data quality, or needs to understand a table's structure and content. Requires a table name.

debugging-dags

258

astronomer

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.

foreman-spec

243

Mylukin Agent Foreman Foreman Spec

Multi-role requirement analysis and task breakdown workflow using 4 specialized AI agents (PM, UX, Tech, QA). Each agent conducts web research before analysis to gather industry best practices, case studies, and current trends. Supports Quick Mode (parallel, ~3 min, one Q&A session) and Deep Mode (serial, ~8 min, Q&A after EACH agent so answers inform subsequent analysis). Triggers on 'foreman-spec', 'spec feature', 'break down requirement', 'define tasks', 'spec this'.

council

196

ryoppippi

Spawns multiple parallel task agents to deeply explore and analyse a codebase area of interest. Gathers comprehensive insights by combining diverse perspectives from multiple agents.

metacognitive-guard

188

aiskillstore

Monitors Claude's responses for struggle signals and suggests escalation to deep-thinking agents when complexity exceeds comfortable reasoning capacity.

ring:using-dev-team

122

LerianStudio

9 specialist developer agents for backend (Go/TypeScript), DevOps, frontend, design, UI implementation, QA (backend + frontend), and SRE. Dispatch when you need deep technology expertise.

using-finance-team

122

LerianStudio

6 specialist financial agents for analysis, budgeting, modeling, treasury, accounting, and metrics. Dispatch when you need deep financial expertise.

explore

97

yonatangross

explore — Deep codebase exploration with parallel agents. Use when exploring a repo, discovering architecture, finding files, or analyzing design patterns.

deep-context

64

arpitnath

Build deep codebase understanding using Capsule context, progressive-reader, and specialist agents instead of overwhelming main context. Triggers on: don't have context, understand codebase, learn about, need background. Implements progressive context building.

flutter-navigation

64

MADTeacher

Comprehensive guide for Flutter navigation and routing including Navigator API, go_router, deep linking, passing/returning data, and web-specific navigation. Use when implementing screen transitions, configuring routing systems, setting up deep links, handling browser history, or managing navigation state in Flutter applications.

morph-warpgrep

62

letta-ai

Integration guide for Morph's WarpGrep (fast agentic code search) and Fast Apply (10,500 tok/s code editing). Use when building coding agents that need fast, accurate code search or need to apply AI-generated edits to code efficiently. Particularly useful for large codebases, deep logic queries, bug tracing, and code path analysis.

LLM Data Automation

46

datadrivenconstruction

Automate construction data processing using LLMs (ChatGPT, Claude, LLaMA). Generate Python/Pandas scripts, extract data from documents and tables, and build automated pipelines without deep programming expertise.

competitive-analysis-templates

45

slgoodrich

Master competitive analysis templates including competitor deep-dives, battle cards, feature comparison matrices, and win/loss analysis. Use when analyzing competitors, creating battle cards for sales, positioning against alternatives, tracking competitive moves, or preparing for competitive threats. Covers competitive intelligence frameworks, positioning strategies, and templates from Crayon, Klue, and April Dunford.

dialectic

45

NeverSight

An Electric Monk engine — two subagents believe fully committed positions on the user's behalf while the orchestrator performs structural contradiction analysis and synthesis. By outsourcing belief work to agents, the user operates from a belief-free position where they can analyze the structure of the contradiction rather than being inside either side. Use when the user wants to stress-test an idea, resolve a genuine tension, build a deeper mental model, or make a high-stakes decision where the tradeoffs are unclear. Works across any domain — technical architecture, product strategy, philosophy, personal decisions, risk analysis, policy, creative direction.

data-synthesis

44

HyunjunJeon

Synthesize findings from multiple research sources into coherent insights. Use when combining data from different sub-agents or research threads.

langchain_patterns

39

vuralserhat86

Implement Retrieval-Augmented Generation (RAG) systems with LangChain4j. Build document ingestion pipelines, embedding stores, vector search strategies, and knowledge-enhanced AI applications. Use when creating question-answering systems over document collections or AI assistants with external knowledge bases.

model_finetuning

39

vuralserhat86

Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF, align model with preferences, or train from human feedback. Works with HuggingFace Transformers.

ai-ml-timeseries

34

vasilyu1983

Operational patterns, templates, and decision rules for time series forecasting (modern best practices): tree-based methods (LightGBM), deep learning (Transformers, RNNs), future-guided learning, temporal validation, feature engineering, generative TS (Chronos), and production deployment. Emphasizes explainability, long-term dependency handling, and adaptive forecasting.

deepagents-code-review

33

existential-birds

Reviews Deep Agents code for bugs, anti-patterns, and improvements. Use when reviewing code that uses create_deep_agent, backends, subagents, middleware, or human-in-the-loop patterns. Catches common configuration and usage mistakes.

deepagents-implementation

33

existential-birds

Implements agents using Deep Agents. Use when building agents with create_deep_agent, configuring backends, defining subagents, adding middleware, or setting up human-in-the-loop workflows.

check-your-work

30

enbyaugust

Orchestrates 6 quality agents in parallel (duplicate-detector, jenny, deep-bug-hunter, security, performance, correctness) with severity validation. Use when user says "check your work", "review what we wrote", "quality check", or after writing new features.

deep-research

30

mcouthon

Exhaustive investigation with citations and structured findings. Use when thorough coverage is needed, all sources must be cited, or research will inform critical decisions. Triggers on: 'use deep-research mode', 'deep research', 'exhaustive investigation', 'thorough research', 'cite all sources', 'comprehensive analysis', 'leave no stone unturned', 'research everything'. Read-only mode - investigates and documents but doesn't modify code.

voice-ai-development

29

omer-metin

Expert in building voice AI applications - from real-time voice agents to voice-enabled apps. Covers OpenAI Realtime API, Vapi for voice agents, Deepgram for transcription, ElevenLabs for synthesis, LiveKit for real-time infrastructure, and WebRTC fundamentals. Knows how to build low-latency, production-ready voice experiences. Use when "voice ai, voice agent, speech to text, text to speech, realtime voice, vapi, deepgram, elevenlabs, livekit, openai realtime, voice-ai, speech-to-text, text-to-speech, realtime, openai-realtime, vapi, deepgram, elevenlabs, livekit, webrtc" mentioned.

research-workflow

27

jwynia

Guide agents through structured research including planning, multi-query execution, source analysis, and synthesis. Use for comprehensive topic research, deep investigation, or creating research reports. Keywords: research, investigate, deep dive, comprehensive, analysis, synthesis, report.

xml-context-engineering

22

mahidalhan

USE WHEN: writing system prompts, structuring complex instructions, engineering context for Claude agents, optimizing attention efficiency in long prompts. DO NOT USE WHEN: writing regular code, simple messages, or content where Markdown suffices. For optimal context architecture, trigger deep thinking with "think harder" or "ultrathink" to analyze attention economics thoroughly.

plan-driven-agentic-engineering

19

samarv

A workflow for collaborating with AI coding agents (like Codex) on complex, multi-step software tasks. Use this when porting features between platforms, building rapid prototypes ("vibe coding"), or resolving "gnarly" production bugs that require deep context.

langconfig-builder

18

LangConfig

Complete guide for building agents and workflows in LangConfig. Use when users need help configuring nodes, connecting agents, setting up tools, or designing multi-agent systems within the LangConfig platform.

architecture-analysis

16

front-depiction

Architectural dependency analysis and impact assessment. Use for: (1) Blast radius - who depends on a service, what breaks if I change it; (2) Dependency tree - what does a service depend on (ancestors/upstream); (3) Root cause analysis - find shared dependencies when multiple services fail; (4) Architecture metrics - coupling (density), depth (diameter), connectivity; (5) Domain discovery - identify module boundaries via cut vertices; (6) Hot services - critical infrastructure with many dependents; (7) Impact assessment before changes; (8) Debugging cascading failures; (9) Identifying god services, tight coupling, deep hierarchies. Provides graph-based analysis via CLI commands: analyze, blast-radius, ancestors, common-ancestors, metrics, domains, hot-services. All agents can use this for architectural questions.

learn

15

Soul-Brews-Studio

Explore a codebase with parallel Haiku agents. Modes - --fast (1 agent), default (3), --deep (5). Use when user says "learn [repo]", "explore codebase", "study this repo".

analyze

14

rjmurillo

Analyze codebase architecture, security posture, or code quality through guided multi-step investigation. Use when performing architecture reviews, security assessments, quality evaluations, or deep technical investigations. Produces prioritized findings with evidence.

Memory Documentary

14

rjmurillo

Generate evidence-based documentary reports by searching across all four memory systems (Claude-Mem, Forgetful, Serena, DeepWiki), project artifacts (.agents/ artifacts), and GitHub issues. Produces investigative journalism-style analysis with full citation chains.

SkillForge

14

rjmurillo

Intelligent skill router and creator. Analyzes ANY input to recommend existing skills, improve them, or create new ones. Uses deep iterative analysis with 11 thinking models, regression questioning, evolution lens, and multi-agent synthesis panel. Phase 0 triage ensures you never duplicate existing functionality.

exploring-knowledge-graph

14

rjmurillo

Guidance for deep knowledge graph traversal across memories, entities, and relationships. Use when needing comprehensive context before planning, investigating connections between concepts, or answering "what do you know about X" questions.

research-web

10

doodledood

Deep web research with parallel investigators, multi-wave exploration, and structured synthesis. Spawns multiple web-researcher agents to explore different facets of a topic simultaneously, launches additional waves when gaps are identified, then synthesizes findings. Use when asked to research, investigate, compare options, find best practices, or gather comprehensive information from the web.\n\nThoroughness: quick for factual lookups | medium for focused topics | thorough for comparisons/evaluations (waves continue while critical gaps remain) | very-thorough for comprehensive research (waves continue until satisficed). Auto-selects if not specified.

research

10

Colmarius Dot Agents Research

Deep research on technical topics, libraries, APIs, or concepts. Use when asked to research, investigate, explore deeply, or gather comprehensive information on a topic. Saves learnings to .agents/research/.

deepinit

10

materialofair

Deep codebase initialization with hierarchical AGENTS.md documentation

Stable Baselines3（stable-baselines3）

9

jackspace

Use this skill for reinforcement learning tasks including training RL agents (PPO, SAC, DQN, TD3, DDPG, A2C, etc.), creating custom Gym environments, implementing callbacks for monitoring and control, using vectorized environments for parallel training, and integrating with deep RL workflows. This skill should be used when users request RL algorithm implementation, agent training, environment design, or RL experimentation.

teacher

8

fernandobandeira

Guide learning and deep understanding through proven methodologies (Socratic, Feynman, Problem-Based). Use when user says 'help me understand', 'teach me', 'explain this', 'learn about', 'socratic', 'feynman', 'problem-based', 'I don't understand', 'confused about', 'why does', or wants to truly grasp a concept.