javascript-sdk
JavaScript/TypeScript SDK for inference.sh - run AI apps, build agents, integrate with all models. Package: @inferencesh/sdk (npm install). Full TypeScript…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-01 00:15
Agents & models
25,390 results
llm-models
Access Claude, Gemini, Kimi, GLM and 100+ LLMs via inference.sh CLI using OpenRouter. Models: Claude Opus 4.5, Claude Sonnet 4.5, Claude Haiku 4.5, Gemini 3…
source-to-skill-distiller
Convert source material into reusable Agent Skill packages by extracting evidence boundaries, mechanisms, workflows, output contracts, multilingual handling,…
architecture-design
Develop evidence-backed alternatives for one expensive-to-reverse architecture question and return its decision frontier to the Coordinator. Use architect when…
team-assemble
Analyze tasks and dynamically assemble expert agent teams using Claude Code's TeamCreate API. Scouts your codebase, designs optimal agents, and executes with…
manage-local-skills
Analyze, standardize, validate, and sync locally maintained skills into agent skill directories with a `skills` CLI-aligned workflow. Use this skill when Codex…
karpathy-agentic-guidelines-q8
Compact q8 Karpathy-inspired agentic coding guidance. Use when you need bounded autonomy, verification discipline, and context control without loading the full…
eventmodeling-applying-conways-law
Step 6 of Event Modeling - Apply Conway's Law with swimlanes. Organize events into autonomous system parts that different teams can independently own. Use…
tmux
Remote-control tmux sessions for interactive CLIs by sending keystrokes and scraping pane output.
skill-creator
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's…
wayfinder
Plan a huge chunk of work — more than one agent session can hold — as a shared map of decision tickets on your issue tracker, and resolve them one at a time…
agent-orchestration
Orchestrate AI agents using Claude Flow, swarm coordination, and multi-agent workflows. Use for complex tasks requiring multiple specialized agents, parallel…
core-researcher
Deep research and information gathering specialist for thorough investigation, pattern analysis, and knowledge synthesis
langchain
Build production-ready LLM applications with chains, agents, memory, tools, and RAG pipelines using the LangChain framework
skill-learner
Post-commit skill that reviews completed work, identifies reusable patterns, and creates/enhances skills for continual learning. Auto-executes after commits to…
sparc-specification
SPARC Specification phase specialist for requirements analysis, constraint identification, use case definition, and acceptance criteria creation
subagent-driven
Execute implementation plans with structured subagent dispatch and two-stage review (spec compliance, then code quality). Based on obra/superpowers.
model-routing-patterns
Model routing configuration templates and strategies for cost optimization, speed optimization, quality optimization, and intelligent fallback chains. Use when…
ai-pretraining
Builds a GPT and BPE tokenizer from scratch. Use when implementing autograd, attention, a nanoGPT loop, muP hyperparameter transfer, WSD annealing, loss…
ai-voice-bots
Builds production voice bots and IVR with Python STT/TTS pipelines. Use when designing telephony, streaming audio, latency budgets, or voice quality monitoring.
session-peers
Messages between Claude Code sessions and Codex CLI threads on one machine, including correlated request/reply without stale queued turns, blocking (ask) or…
multi-agent coordinator
Spawn 10-20 parallel agents for Leavn codebase audits, systematic fixes, comprehensive analysis across multiple domains simultaneously
ie-generate-insight
Transform reasoning analysis results into readable insight text, generate suggestions for the next step of exploration, and show the evolution path of ideas. Use this skill when the user mentions "generate insights," "give me inspiration," "inspire me," "what to explore next," "how did the idea evolve," and other scenarios that require extracting inspiring content from analysis results. This skill belongs to the insight layer of the Inspiration Engine (ie-) and is specifically responsible for transforming structured reasoning results into human-readable inspirational content; it does not involve note retrieval...
handoff
Compact the current conversation into a handoff document for another agent to pick up.