llm-ai
7
dspy-framework
DSPy declarative framework for automatic prompt optimization treating prompts as code with systematic evaluation and compilers
bobmatnyc
data-ai
sorting
stars
current ordering strategy
query
all entries
refine the visible subset
llm-ai
7
agent-recovery
Recovery protocols when agent is stuck—escalate to new agent, migrate context to new session, or reset mid-conversation.
JStaRFilms
data-ai
llm-ai
7
recall
Semantic memory recall using FTS5 and Chroma. Use PROACTIVELY whenever the user asks about past events, themes, conversations, or when historical context would enrich a response. Trigger words: remember, when did we, what did we talk about, last time, before, previously, that conversation, that time, history, past, recall.
claudeaceae
data-ai
llm-ai
7
openrouter
OpenRouter unified AI API - Access 200+ LLMs through single interface with intelligent routing, streaming, cost optimization, and model fallbacks
bobmatnyc
data-ai
llm-ai
7
project-init-memory
Automatically remember and apply skillset configuration when first running a project. Use when initializing projects in .skills-template or any project requiring consistent AI agent setup. Handles CLAUDE.md generation, skill loading, and environment persistence.
supercent-io
data-ai
machine-learning
7
fal-model-guide
Complete fal.ai model selection system. PROACTIVELY activate for: (1) Choosing image generation models (FLUX, SDXL), (2) Choosing video models (Kling, Sora, LTX), (3) Choosing audio models (Whisper, ElevenLabs), (4) Model quality vs speed comparison, (5) Cost optimization by model tier, (6) 3D generation models, (7) Model-specific parameters, (8) Development vs production model selection. Provides: Model comparison tables, decision trees, pricing tiers, performance benchmarks. Ensures optimal model selection for quality, speed, and cost.
JosiahSiegel
data-ai
llm-ai
7
session-recovery
Troubleshoot Claude Code session issues. Use when encountering "No conversations found" errors, missing sessions, or session file corruption problems.
terrylica
data-ai
llm-ai
7
local-llm-ops
Local LLM operations with Ollama on Apple Silicon, including setup, model pulls, chat launchers, benchmarks, and diagnostics.
bobmatnyc
data-ai
llm-ai
7
langchain-framework
LangChain LLM application framework with chains, agents, RAG, and memory for building AI-powered applications
bobmatnyc
data-ai
llm-ai
7
agent-evaluation
Design and implement comprehensive evaluation systems for AI agents. Use when building evals for coding agents, conversational agents, research agents, or computer-use agents. Covers grader types, benchmarks, 8-step roadmap, and production integration.
supercent-io
data-ai
llm-ai
7
character-naming
Break LLM name defaults with external entropy. Use when character names cluster around statistical medians (Chen, Patel, Maya, Marcus), when cast has collision risks, or when fantasy cultures need phonologically consistent naming.
jwynia
data-ai
llm-ai
7
azure-ai-voicelive
Build real-time voice AI applications using Azure AI Voice Live SDK (azure-ai-voicelive). Use this skill when creating Python applications that need real-time bidirectional audio communication with Azure AI, including voice assistants, voice-enabled chatbots, real-time speech-to-speech translation, voice-driven avatars, or any WebSocket-based audio streaming with AI models. Supports Server VAD (Voice Activity Detection), turn-based conversation, function calling, MCP tools, avatar integration, and transcription.
microsoft
data-ai
llm-ai
7
model-mediated-development
Use when building any system that involves AI/model calls - integrates with brainstorming, planning, and TDD to ensure model agency over hardcoded rules
dbmcco
data-ai
llm-ai
7
telegram-bot-management
Telegram bot production management, monitoring, and troubleshooting. Use when user mentions telegram bot, claude-orchestrator, bot status, bot restart, or bot monitoring.
terrylica
data-ai
llm-ai
7
update-agents-md
Update AGENTS.md with new rules to prevent AI misbehavior or add operational guidelines. Use when the user says "update AGENTS.md", "add this rule", "change AI behavior", or "don't do X automatically".
nozomi-koborinai
data-ai
machine-learning
7
using-ai-engineering
Route AI/ML tasks to correct Yzmir pack - frameworks, training, RL, LLMs, architectures, production
tachyon-beep
data-ai
llm-ai
7
azure-ai-search-python
Clean code patterns for Azure AI Search Python SDK (azure-search-documents). Use when building search applications, creating/managing indexes, implementing agentic retrieval with knowledge bases, or working with vector/hybrid search. Covers SearchClient, SearchIndexClient, SearchIndexerClient, and KnowledgeBaseRetrievalClient.
microsoft
data-ai
llm-ai
7
creating-skills
Creates new Agent Skills (SKILL.md + optional scripts/references) that follow the Agent Skills spec. Use when the user asks to create, structure, validate, or improve an agent skill.
acasto
data-ai
llm-ai
7
tzurot-council-mcp
Best practices for using the Council MCP server in Tzurot v3 development - When to consult external AI, how to structure prompts, model selection, and multi-turn conversations. Use when planning major changes or needing a second opinion.
lbds137
data-ai
llm-ai
7
ultrathink-multiagent-workflow
Design principles for ultrathink multi-agent workflows using the Ralph Wiggum technique. Use when orchestrating multiple AI agents (Opus/Sonnet/Gemini/Codex) for complex autonomous development tasks with extended thinking and iterative improvement loops.
supercent-io
data-ai
llm-ai
7
subagent-creation
Create and configure Claude Code subagents for specialized task delegation. Use when defining expert AI assistants with focused responsibilities, custom prompts, and specific tool permissions.
supercent-io
data-ai