GitHub
background-agent-pings
Background Agent Pings
☆ 3,508View skill
research llm ai AI Skills
Discover research llm ai skills, compare source repositories and read the instructions for each workflow.
Categories: research llm ai
research llm ai Clear filters
Browse skills
GitHub
llm-tuning-patterns
LLM Tuning Patterns
☆ 3,508View skill
GitHub
agentica-spawn
Spawn Agentica multi-agent patterns
☆ 3,508View skill
GitHub
agentica-infrastructure
Reference guide for Agentica multi-agent infrastructure APIs
☆ 3,508View skill
GitHub
trace-claude-code
Automatically trace Claude Code conversations to Braintrust for observability. Captures sessions, conversation turns, and tool calls as hierarchical traces.
☆ 3,508View skill
GitHub
agentica-server
Agentica server + Claude proxy setup - architecture, startup sequence, debugging
☆ 3,508View skill
GitHub
agent-context-isolation
Agent Context Isolation
☆ 3,508View skill
GitHub
leann-search
Semantic search across codebase using LEANN vector index
☆ 3,508View skill
GitHub
perplexity-search
AI-powered web search, research, and reasoning via Perplexity
☆ 3,508View skill
GitHub
workflow-router
Goal-based workflow orchestration - routes tasks to specialist agents based on user goals
☆ 3,508View skill
GitHub
agent-orchestration
Agent Orchestration Rules
☆ 3,508View skill
GitHub
skill-developer
Meta-skill for creating and managing Claude Code skills
☆ 3,508View skill
GitHub
agentica-claude-proxy
Guide for integrating Agentica SDK with Claude Code CLI proxy
☆ 3,508View skill
GitHub
math-router
Deterministic router for math cognitive stack - maps user intent to exact CLI commands
☆ 3,508View skill
GitHub
math
Unified math capabilities - computation, solving, and explanation. I route to the right tool.
☆ 3,508View skill
GitHub
explore
Meta-skill for internal codebase exploration at varying depths (quick/deep/architecture)
☆ 3,508View skill
GitHub
parallel-agents
Parallel Agent Orchestration
☆ 3,508View skill
GitHub
compound-learnings
Transform session learnings into permanent capabilities (skills, rules, agents). Use when asked to "improve setup", "learn from sessions", "compound learnings", or "what patterns should become skills".
☆ 3,508View skill
GitHub
slash-commands
Create and use Claude Code slash commands - quick prompts, bash execution, file references
☆ 3,508View skill
GitHub
agentica-prompts
Write reliable prompts for Agentica/REPL agents that avoid LLM instruction ambiguity
☆ 3,508View skill
GitHub
help
Interactive workspace discovery - learn what tools, workflows, agents, and hooks are available
☆ 3,508View skill
GitHub
humanizer
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fi...
☆ 3,339View skill
GitHub
linux-production-shell-scripts
This skill should be used when the user asks to "create bash scripts", "automate Linux tasks", "monitor system resources", "backup files", "manage users", or "write production shell scripts". It provides ready-...
☆ 3,287View skill
GitHub
create-pattern
Analyze sources (blog posts, PDFs, YouTube videos, codebases, pasted text) for agentic patterns, match against 105+ existing patterns, create new patterns or update existing with new sources and insights.
☆ 3,256View skill
The default order uses GitHub repository stars from our indexed data. Stars belong to the source repository and may be shared by multiple skills. They indicate repository interest, not skill installs or an independent quality score.