open source · free for all
Oskis — Open Source Skilskis. Free for all.
Oskis are community-contributed AI skills, free to run via the skill.ski public MCP endpoint. 127 indexed across 6 upstream sources. Attribution required — no paywall, no lock-in.
install · 30 seconds
Get all 127 Oskis into your agent
01
Sign up free
Create a free skil.ski account. No card. Oskis ship with every account.
02
Copy your MCP token
Settings → MCP → Generate token. The free tier scope is the Oski catalog.
03
Add the server
Paste the URL + token into Claude Desktop, Cursor, ChatGPT Custom GPT, Codex, or any MCP client.
Free MCP endpoint
https://skil.ski/api/mcp/freeFree tier · scoped to the Oski catalog. Pro and Elite endpoints unlock the full skill registry.
example config
{
"mcpServers": {
"skil-ski-oskis": {
"url": "https://skil.ski/api/mcp/free",
"headers": {
"Authorization": "Bearer <token>"
}
}
}
}browse oskis
127 Oskis
Anthropic Algorithmic Art
Anthropiccreative
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration.
Apache-2.0Get via MCP →
Anthropic Brand Guidelines
Anthropiccreative
Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel.
Apache-2.0Get via MCP →
Anthropic Canvas Design
Anthropiccreative
Create beautiful visual art in .png and .pdf documents using design philosophy.
Apache-2.0Get via MCP →
Anthropic Claude API
Anthropicengineering
Build, debug, and optimize Claude API / Anthropic SDK apps.
Apache-2.0Get via MCP →
Anthropic Doc Coauthoring
Anthropicwriting
Guide users through a structured workflow for co-authoring documentation.
Apache-2.0Get via MCP →
Anthropic Frontend Design
Anthropicengineering
Create distinctive, production-grade frontend interfaces with high design quality.
Apache-2.0Get via MCP →
Anthropic Internal Comms
Anthropicoperations
A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use.
Apache-2.0Get via MCP →
Anthropic MCP Builder
Anthropicengineering
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools.
Apache-2.0Get via MCP →
Anthropic Skill Creator
Anthropicengineering
Create new skills, modify and improve existing skills, and measure skill performance.
Apache-2.0Get via MCP →
Anthropic Slack Gif Creator
Anthropiccreative
Knowledge and utilities for creating animated GIFs optimized for Slack.
Apache-2.0Get via MCP →
Anthropic Theme Factory
Anthropiccreative
Toolkit for styling artifacts with a theme.
Apache-2.0Get via MCP →
Anthropic Web Artifacts Builder
Anthropicengineering
Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui).
Apache-2.0Get via MCP →
Anthropic Webapp Testing
Anthropicengineering
Toolkit for interacting with and testing local web applications using Playwright.
Apache-2.0Get via MCP →
RAG Pattern (OpenAI Cookbook)
OpenAIengineering
Trigger when a developer asks how to ground an LLM answer in their own corpus, build a basic Retrieval-Augmented Generation flow, embed a knowledge base, or stop hallucinations by retrieving relevant context before generation.
MITGet via MCP →
Function Calling Pattern (OpenAI Cookbook)
OpenAIengineering
Trigger when a developer wants to let a chat model call external tools, define a JSON schema for a function the model should invoke, parse tool_calls back from the response, or build a tool-using agent loop.
MITGet via MCP →
Embeddings Classification (OpenAI Cookbook)
OpenAIengineering
Trigger when a developer needs a cheap, no-finetune classifier for text labels (sentiment, intent, category), wants to use embeddings + a logistic regression / cosine-similarity head, or is comparing embedding models for a downstream classifier.
MITGet via MCP →
Summarize Long Documents (OpenAI Cookbook)
OpenAIengineering
Trigger when a developer needs to summarize a document longer than the context window, wants a map-reduce or recursive summarization pattern, or is hitting token limits on a single-call summary.
MITGet via MCP →
Structured Outputs Pattern (OpenAI Cookbook)
OpenAIengineering
Trigger when a developer wants the model to return JSON that conforms to a schema, needs guaranteed valid output for downstream parsing, or is replacing brittle regex-extraction with response_format json_schema.
MITGet via MCP →
Prompt Caching 101 (OpenAI Cookbook)
OpenAIengineering
Trigger when a developer wants to cut API cost / latency on long-system-prompt apps, structure prompts so the static prefix is cacheable, or measure cache hit rate and savings.
MITGet via MCP →
Orchestrating Agents (OpenAI Cookbook)
OpenAIengineering
Trigger when a developer wants to build a routine + handoff multi-agent system, hand off control between specialist agents, or implement a router agent that dispatches to sub-agents.
MITGet via MCP →
Batch API Pattern (OpenAI Cookbook)
OpenAIengineering
Trigger when a developer has thousands of independent prompts to run, wants 50% off via Batch API, or needs to process a CSV / bulk dataset asynchronously instead of synchronous calls.
MITGet via MCP →
Rate Limit Handling (OpenAI Cookbook)
OpenAIengineering
Trigger when a developer is hitting 429 errors, needs an exponential backoff with jitter retry wrapper, or wants to throttle parallel API calls to stay under TPM/RPM caps.
MITGet via MCP →
Moderation Pipeline (OpenAI Cookbook)
OpenAIengineering
Trigger when a developer ships user-facing AI text/images and needs a pre-call (input) and post-call (output) moderation gate using the free omni-moderation endpoint.
MITGet via MCP →
Token Counting with tiktoken (OpenAI Cookbook)
OpenAIengineering
Trigger when a developer needs to estimate token count before a call, budget a context window, choose a chunk size for embeddings, or accurately compute the cost of a prompt.
MITGet via MCP →
Hallucination Guardrails (OpenAI Cookbook)
OpenAIengineering
Trigger when a developer needs an output validation gate that flags hallucinated facts, wants a self-consistency / faithfulness check, or is building a critic-pass on top of a generator.
MITGet via MCP →
Parse PDFs for RAG (OpenAI Cookbook)
OpenAIengineering
Trigger when a developer needs to ingest PDFs into a RAG index, extract clean text + tables from a PDF, or chunk a multi-page document for embedding.
MITGet via MCP →
Vision Image Tagging (OpenAI Cookbook)
OpenAIengineering
Trigger when a developer wants to auto-tag, caption, or describe images using a vision-capable model, build an image search index, or extract structured attributes from product photos.
MITGet via MCP →
Agent Native Architecture
Iliaalmeta
Design agent-native applications where agents replace UI users as the primary actor. Use when designing MCP tools, agent-loop architectures, shared-workspace file patterns, or self-modifying agent systems.
MITGet via MCP →
Brainstorming
Iliaalworkflow
Pre-implementation exploration: deep interview, approach comparison, design doc. Use when exploring a vague feature idea, clarifying ambiguous requirements, or comparing approaches before coding. For the full workflow, use `/ia-brainstorm`.
MITGet via MCP →
Code Review
Iliaaldiscipline
Structured code reviews with severity-ranked findings and deep multi-agent mode. Use when performing a code review, auditing code quality, or critiquing PRs, MRs, or diffs.
MITGet via MCP →
Compound Docs
Iliaalworkflow
Document solved problems for team reuse. Provides process knowledge for /ia-compound. Use when documenting a resolved issue, writing up lessons learned, capturing a post-mortem, adding to the knowledge base, or building searchable institutional knowledge after debugging. disable-model-invocation: true
MITGet via MCP →
Debugging
Iliaaldiscipline
Systematic root-cause debugging with verification. Use for errors, stack traces, broken tests, flaky tests, regressions, or anything not working as expected. For validating bug reports before fixing, use bug-reproduction-validator agent.
MITGet via MCP →
Document Review
Iliaalworkflow
Structural review of documents for gaps, clarity, completeness, and organization. Use when a brainstorm, plan, spec, ADR, or any doc needs polish before the next workflow step. For exploring new ideas from scratch, use brainstorming instead.
MITGet via MCP →
File Todos
Iliaaltool
File-based todo and task tracking in the todos/ directory. Use when creating, triaging, listing, or managing todo files, tracking work items, managing the backlog, converting PR comments to tracked tasks, or checking todo status and dependencies. disable-model-invocation: true
MITGet via MCP →
Frontend Design
Iliaalmeta
Visual design and aesthetic direction for frontend interfaces. Use when building web pages, landing pages, dashboards, or applications where visual identity matters. For React patterns and testing, use react-frontend.
MITGet via MCP →
Git Worktree
Iliaaltool
Manage Git worktrees for isolated parallel development. Use when creating, listing, switching, or cleaning up git worktrees, or when needing isolated branches for concurrent reviews or feature work.
MITGet via MCP →
Linux Bash Scripting
Iliaallanguage
Defensive Bash scripting for Linux: safe foundations, argument parsing, production patterns, ShellCheck compliance. Use when writing bash scripts, shell scripts, cron jobs, or CLI tools in bash.
MITGet via MCP →
Md Docs
Iliaalworkflow
Manages project documentation: CLAUDE.md, AGENTS.md, README.md, CONTRIBUTING.md. Use when asked to update, create, or init these context files. Not for general markdown editing.
MITGet via MCP →
Meta Prompting
Iliaalmeta
Structured reasoning modifiers (/think, /verify, /adversarial, /edge, /confidence, /assumptions, etc.) to stress-test decisions, surface assumptions, or enumerate edge cases. Use when validating an important design, architecture decision, or ambiguous plan before committing.
MITGet via MCP →
Nodejs Backend
Iliaallanguage
Node.js backend patterns: layered architecture, TypeScript, validation, error handling, security, deployment. Use when building REST APIs, REST endpoints, middleware, Express/Fastify/Hono/NestJS/Koa servers, tRPC procedures, Bun servers, or server-side TypeScript.
MITGet via MCP →
Orchestrating Swarms
Iliaalworkflow
Coordinate multi-agent swarms for parallel and pipeline workflows. Use when coordinating multiple agents, running parallel reviews, building pipeline workflows, or implementing divide-and-conquer patterns with subagents.
MITGet via MCP →
Php Laravel
Iliaallanguage
Modern PHP 8.4 and Laravel patterns: architecture, Eloquent, queues, testing. Use when working with Laravel, Eloquent, Blade, artisan, PHPUnit, PHPStan, or building/testing PHP applications with frameworks. Not for PHP internals (php-src) or general PHP language discussion.
MITGet via MCP →
Pinescript
Iliaallanguage
Pine Script v6: syntax, performance, error diagnosis, backtesting, visualization. Use when writing or debugging `.pine` files or TradingView Pine indicators/strategies.
MITGet via MCP →
Planning
Iliaalworkflow
Software implementation planning with file-based persistence (.plan/). Use when planning code changes touching 3+ files or with ambiguous scope. Skip for typos, single-file fixes, and research/scanning/audit work that produces reports rather than code.
MITGet via MCP →
Postgresql
Iliaallanguage
PostgreSQL schema design, query optimization, indexing, and administration. Use when working with PostgreSQL, JSONB, partitioning, RLS, CTEs, window functions, or EXPLAIN ANALYZE.
MITGet via MCP →
Python Services
Iliaallanguage
Python patterns for CLI tools, async concurrency, and backend services. Use when working with Python code, building CLI apps, FastAPI services, async with asyncio, background jobs, or configuring uv, ruff, ty, pytest, or pyproject.toml.
MITGet via MCP →
React Frontend
Iliaallanguage
React architecture patterns, TypeScript, Next.js, hooks, and testing. Use when working with React component structure, state management, Next.js routing, Vitest, React Testing Library, or reviewing React code. For visual design and aesthetic direction, use frontend-design instead.
MITGet via MCP →
Autoresearch
OrchestraAutoresearch Skill
Orchestrates end-to-end autonomous AI research projects using a two-loop architecture. The inner loop runs rapid experiment iterations with clear optimization targets. The outer loop synthesizes results, identifies patterns, and steers research direction. Routes to domain-specific skills for execution, supports continuous agent operation via Claude Code /loop and OpenClaw heartbeat, and produces r
MITGet via MCP →
Implementing Llms Litgpt
OrchestraModel Architecture
Implements and trains LLMs using Lightning AI's LitGPT with 20+ pretrained architectures (Llama, Gemma, Phi, Qwen, Mistral). Use when need clean model implementations, educational understanding of architectures, or production fine-tuning with LoRA/QLoRA. Single-file implementations, no abstraction layers.
MITGet via MCP →
Mamba Architecture
OrchestraModel Architecture
State-space model with O(n) complexity vs Transformers' O(n²). 5× faster inference, million-token sequences, no KV cache. Selective SSM with hardware-aware design. Mamba-1 (d_state=16) and Mamba-2 (d_state=128, multi-head). Models 130M-2.8B on HuggingFace.
MITGet via MCP →
Nanogpt
OrchestraModel Architecture
Educational GPT implementation in ~300 lines. Reproduces GPT-2 (124M) on OpenWebText. Clean, hackable code for learning transformers. By Andrej Karpathy. Perfect for understanding GPT architecture from scratch. Train on Shakespeare (CPU) or OpenWebText (multi-GPU).
MITGet via MCP →
Rwkv Architecture
OrchestraModel Architecture
RNN+Transformer hybrid with O(n) inference. Linear time, infinite context, no KV cache. Train like GPT (parallel), infer like RNN (sequential). Linux Foundation AI project. Production at Windows, Office, NeMo. RWKV-7 (March 2025). Models up to 14B parameters.
MITGet via MCP →
Distributed Llm Pretraining Torchtitan
OrchestraModel Architecture
Provides PyTorch-native distributed LLM pretraining using torchtitan with 4D parallelism (FSDP2, TP, PP, CP). Use when pretraining Llama 3.1, DeepSeek V3, or custom models at scale from 8 to 512+ GPUs with Float8, torch.compile, and distributed checkpointing.
MITGet via MCP →
Huggingface Tokenizers
OrchestraTokenization
Fast tokenizers optimized for research and production. Rust-based implementation tokenizes 1GB in <20 seconds. Supports BPE, WordPiece, and Unigram algorithms. Train custom vocabularies, track alignments, handle padding/truncation. Integrates seamlessly with transformers. Use when you need high-performance tokenization or custom tokenizer training.
MITGet via MCP →
Sentencepiece
OrchestraTokenization
Language-independent tokenizer treating text as raw Unicode. Supports BPE and Unigram algorithms. Fast (50k sentences/sec), lightweight (6MB memory), deterministic vocabulary. Used by T5, ALBERT, XLNet, mBART. Train on raw text without pre-tokenization. Use when you need multilingual support, CJK languages, or reproducible tokenization.
MITGet via MCP →
Axolotl
OrchestraFine Tuning
Expert guidance for fine-tuning LLMs with Axolotl - YAML configs, 100+ models, LoRA/QLoRA, DPO/KTO/ORPO/GRPO, multimodal support
MITGet via MCP →
Llama Factory
OrchestraFine Tuning
Expert guidance for fine-tuning LLMs with LLaMA-Factory - WebUI no-code, 100+ models, 2/3/4/5/6/8-bit QLoRA, multimodal support
MITGet via MCP →
Peft Fine Tuning
OrchestraFine Tuning
Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when you need to train <1% of parameters with minimal accuracy loss, or for multi-adapter serving. HuggingFace's official library integrated with transformers ecosystem.
MITGet via MCP →
Unsloth
OrchestraFine Tuning
Expert guidance for fast fine-tuning with Unsloth - 2-5x faster training, 50-80% less memory, LoRA/QLoRA optimization
MITGet via MCP →
Nnsight Remote Interpretability
OrchestraMechanistic Interpretability
Provides guidance for interpreting and manipulating neural network internals using nnsight with optional NDIF remote execution. Use when needing to run interpretability experiments on massive models (70B+) without local GPU resources, or when working with any PyTorch architecture.
MITGet via MCP →
Pyvene Interventions
OrchestraMechanistic Interpretability
Provides guidance for performing causal interventions on PyTorch models using pyvene's declarative intervention framework. Use when conducting causal tracing, activation patching, interchange intervention training, or testing causal hypotheses about model behavior.
MITGet via MCP →
Sparse Autoencoder Training
OrchestraMechanistic Interpretability
Provides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable features. Use when discovering interpretable features, analyzing superposition, or studying monosemantic representations in language models.
MITGet via MCP →
Transformer Lens Interpretability
OrchestraMechanistic Interpretability
Provides guidance for mechanistic interpretability research using TransformerLens to inspect and manipulate transformer internals via HookPoints and activation caching. Use when reverse-engineering model algorithms, studying attention patterns, or performing activation patching experiments.
MITGet via MCP →
Nemo Curator
OrchestraData Processing
GPU-accelerated data curation for LLM training. Supports text/image/video/audio. Features fuzzy deduplication (16× faster), quality filtering (30+ heuristics), semantic deduplication, PII redaction, NSFW detection. Scales across GPUs with RAPIDS. Use for preparing high-quality training datasets, cleaning web data, or deduplicating large corpora.
MITGet via MCP →
Ray Data
OrchestraData Processing
Scalable data processing for ML workloads. Streaming execution across CPU/GPU, supports Parquet/CSV/JSON/images. Integrates with Ray Train, PyTorch, TensorFlow. Scales from single machine to 100s of nodes. Use for batch inference, data preprocessing, multi-modal data loading, or distributed ETL pipelines.
MITGet via MCP →
Grpo Rl Training
OrchestraPost Training
Expert guidance for GRPO/RL fine-tuning with TRL for reasoning and task-specific model training
MITGet via MCP →
Miles Rl Training
OrchestraPost Training
Provides guidance for enterprise-grade RL training using miles, a production-ready fork of slime. Use when training large MoE models with FP8/INT4, needing train-inference alignment, or requiring speculative RL for maximum throughput.
MITGet via MCP →
Vercel Composition Patterns
skills.shengineering
React composition patterns that scale: avoid boolean prop bloat, use compound components, lift state, and align with React 19 APIs.
MITGet via MCP →
Vercel React Best Practices
skills.shengineering
React + Next.js performance optimization rulebook from Vercel Engineering: 70 rules across 8 priority categories from waterfalls to advanced patterns.
MITGet via MCP →
Vercel React Native Skills
skills.shengineering
React Native + Expo best practices for performant mobile apps: list virtualization, GPU-accelerated animation, native modules, monorepo hygiene.
MITGet via MCP →
Vercel React View Transitions
skills.shengineering
Smooth, native React View Transition API animations without third-party libraries: shared elements, Suspense reveals, list identity, route changes.
MITGet via MCP →
Microsoft Application Insights (Web)
skills.shengineering
Browser-side Real User Monitoring (RUM) with the Application Insights JavaScript SDK: page views, AJAX traces, exceptions, and OTel GenAI agent spans.
MITGet via MCP →
Microsoft Cloud Solution Architect
skills.shengineering
Azure Architecture Center playbook: 10 design principles, 6 architecture styles, 44 cloud design patterns, and the WAF pillars in one skill.
MITGet via MCP →
Microsoft Continual Learning
skills.shengineering
Continual-learning hooks, memory scoping, and reflection patterns for AI coding agents that should get smarter the longer they work in a codebase.
MITGet via MCP →
Microsoft Copilot SDK
skills.shengineering
Build apps powered by GitHub Copilot via the Copilot SDK: sessions, custom tools, streaming, hooks, MCP servers, and BYOK across Node, Python, Go, .NET.
MITGet via MCP →
Microsoft Entra Agent ID
skills.shengineering
OAuth2-capable identities for AI agents via Microsoft Graph beta: Agent Identity Blueprints, BlueprintPrincipals, and Workload Identity Federation.
MITGet via MCP →
Microsoft Frontend Design Review
skills.shdesign
Production-grade frontend review and creation across three pillars (frictionless, quality craft, trustworthy) — design system compliance plus distinctive UI.
MITGet via MCP →
Microsoft GitHub Issue Creator
skills.shengineering
Turn unstructured input — error logs, voice dictation, screenshots — into clean, severity-classified GitHub issues with reproduction steps.
MITGet via MCP →
React Flow Node (TypeScript)
skills.shengineering
Build node-based UIs (graphs, agent flows, pipelines) with React Flow in TypeScript — custom nodes, edges, layouts, and persistence.
MITGet via MCP →
Microsoft KQL Mastery
skills.shdata
Kusto Query Language playbook for ADX, Sentinel, and Log Analytics: syntax gotchas, joins, dynamic types, datetime, regex, geo, vector, graph.
MITGet via MCP →
Microsoft MCP Builder
skills.shengineering
Production-grade MCP (Model Context Protocol) servers across Python (FastMCP), TypeScript, and C#/.NET — Microsoft-hardened patterns for Azure + Foundry.
MITGet via MCP →
Microsoft Docs Search
skills.shengineering
Pull live answers from Microsoft Learn — concepts, tutorials, configuration, limits — across Azure, .NET, M365, Windows, never relying on stale priors.
MITGet via MCP →
Microsoft Podcast Generation
skills.shdesign-creative
Generate podcast-style audio narratives via Azure OpenAI GPT Realtime Mini over WebSocket: full-stack React + FastAPI + streaming PCM playback.
MITGet via MCP →
Microsoft Skill Creator
skills.shengineering
Build effective agent skills for Azure SDKs and Microsoft Foundry: progressive disclosure, degrees-of-freedom matching, and the SKILL.md contract.
MITGet via MCP →
Azure AI Content Safety (TypeScript)
skills.shengineering
Detect harmful content (text, image, jailbreak, protected material) with Azure AI Content Safety in TypeScript — moderation pipeline ready.
MITGet via MCP →
Azure AI Document Intelligence (TypeScript)
skills.shengineering
Extract structured data from PDFs, forms, invoices, and receipts with Azure AI Document Intelligence in TypeScript.
MITGet via MCP →
Azure AI Projects (TypeScript)
skills.shengineering
Build and run Azure AI Foundry projects from TypeScript: agents, threads, runs, evaluations, and connections to Azure data sources.
MITGet via MCP →
Azure Cosmos DB (TypeScript)
skills.shdata
Cosmos DB SQL API in TypeScript: container creation, partition key strategy, point reads, queries, change feed, and bulk operations.
MITGet via MCP →
Azure Event Hubs (TypeScript)
skills.shdata
High-throughput event streaming with Azure Event Hubs in TypeScript — producers, consumers, partitions, checkpointing, and Event Hubs Schema Registry.
MITGet via MCP →
Azure Identity (TypeScript)
skills.shengineering
Authenticate to Azure from TypeScript with DefaultAzureCredential, managed identity, and federated tokens — no secrets in code, ever.
MITGet via MCP →
Azure Key Vault Secrets (TypeScript)
skills.shengineering
Manage application secrets with Azure Key Vault from TypeScript — set, retrieve, rotate, and audit, with managed-identity auth.
MITGet via MCP →
Azure Monitor OpenTelemetry (TypeScript)
skills.shengineering
Wire OpenTelemetry traces, metrics, and logs to Azure Monitor from TypeScript apps — auto-instrumentation, distributed tracing, GenAI semantics.
MITGet via MCP →
Azure Postgres (TypeScript)
skills.shdata
Connect to Azure Database for PostgreSQL from TypeScript with managed identity, connection pooling, pgvector, and HA failover patterns.
MITGet via MCP →
Azure AI Search (TypeScript)
skills.shengineering
Build hybrid (vector + keyword) search experiences with Azure AI Search in TypeScript — indexes, semantic ranking, and RAG retrieval.
MITGet via MCP →
Azure Service Bus (TypeScript)
skills.shengineering
Reliable enterprise messaging with Azure Service Bus in TypeScript: queues, topics, sessions, dead-letter handling, and transactions.
MITGet via MCP →
Azure Storage Blob (TypeScript)
skills.shengineering
Upload, download, stream, and manage blobs in Azure Storage from TypeScript — block blobs, SAS, lifecycle, and large-file resumable upload.
MITGet via MCP →
Zustand Store (TypeScript)
skills.shengineering
Build typed, performant state stores with Zustand in TypeScript: slices, selectors, persistence middleware, and React 19 concurrent patterns.
MITGet via MCP →
Letta Agent Development
Lettaengineering
Comprehensive guide for developing Letta agents, including architecture selection, memory design, model selection, and tool configuration. Use when building or troubleshooting Letta agents.
MITGet via MCP →
Letta Conversations API
Lettaengineering
Guide for using the Letta Conversations API to manage isolated message threads on agents. Use when building multi-user chat applications, session management, or any scenario requiring separate conversation contexts on a single agent.
MITGet via MCP →
Letta Fleet Management
Lettaoperations
Manage Letta AI agent fleets declaratively with kubectl-style CLI. Use when creating, updating, or managing multiple Letta agents with shared configurations, memory blocks, tools, folders, canary deployments, multi-tenancy, and bulk operations.
MITGet via MCP →
Letta Import ChatGPT Memory
Lettaengineering
Clone ChatGPT saved memory into Letta, then optionally enrich it with broader conversation history. Designed for a slick onboarding flow that extracts hidden saved-memory/context blocks, builds Letta-ready previews, and only asks questions at meaningful checkpoints.
MITGet via MCP →
Letta API Client
Lettaengineering
Build applications with the Letta API — a model-agnostic, stateful API for building persistent agents with memory and long-term learning. Covers SDK patterns for Python and TypeScript. Includes 24 working code examples.
MITGet via MCP →
Letta Configuration
Lettaengineering
Configure LLM models and providers for Letta agents and servers. Use when setting model handles, adjusting temperature/tokens, configuring provider-specific settings, setting up BYOK providers, or configuring self-hosted deployments with environment variables.
MITGet via MCP →
Letta 1Password CLI
Lettaoperations
Set up and use 1Password CLI (op). Use when installing the CLI, enabling desktop app integration, signing in (single or multi-account), or reading/injecting/running secrets via op.
MITGet via MCP →
Letta AI News Digest
Lettawriting
Fetch and summarize recent AI news from curated RSS feeds (Hugging Face, VentureBeat, The Verge, OpenAI, Anthropic, DeepMind, etc.) and YouTube channels (Yannic Kilcher, Two Minute Papers, AI Explained, etc.). Also fetches full transcripts for specific YouTube videos. Use when the user asks about recent AI news, what's happened in AI lately, summaries of AI research or product announcements, or wants a digest of what's going on in the AI space.
MITGet via MCP →
Letta Datadog
Lettaoperations
Query Datadog observability data (logs, metrics, monitors, dashboards, hosts) via direct API. Use when investigating production issues, checking monitors, searching logs, or accessing Datadog data.
MITGet via MCP →
Letta Discord CLI
Lettaoperations
Discord automation CLI — send/read/search messages, manage channels and servers, react, create threads, pin messages, and look up users.
MITGet via MCP →
Letta DOCX Editor
Lettawriting
Use when the task involves reading, creating, or editing `.docx` documents, especially when formatting or layout fidelity matters; prefer `python-docx` plus the bundled `scripts/render_docx.py` for visual checks.
Apache-2.0Get via MCP →
Letta Figma Bridge
Lettacreative
Use the Figma MCP server to fetch design context, screenshots, variables, and assets from Figma, and to translate Figma nodes into production code. Trigger when a task involves Figma URLs, node IDs, design-to-code implementation, or Figma MCP setup and troubleshooting.
Apache-2.0Get via MCP →
Letta Frontend Design
Lettaengineering
Use when the task asks for a visually strong landing page, website, app, prototype, demo, or game UI. This skill enforces restrained composition, image-led hierarchy, cohesive content structure, and tasteful motion while avoiding generic cards, weak branding, and UI clutter.
Apache-2.0Get via MCP →
Letta GitHub CLI
Lettaengineering
GitHub operations via `gh` CLI: issues, PRs, CI runs, code review, API queries. Use when: (1) checking PR status or CI, (2) creating/commenting on issues, (3) listing/filtering PRs or issues, (4) viewing run logs. NOT for: complex web UI interactions requiring manual browser flows (use browser tooling when available), bulk operations across many repos (script with gh api), or when gh auth is not configured.
MITGet via MCP →
Letta Jupyter Notebook
Lettaengineering
Use when the user asks to create, scaffold, or edit Jupyter notebooks (`.ipynb`) for experiments, explorations, or tutorials; prefer the bundled templates and run the helper script `new_notebook.py` to generate a clean starting notebook.
Apache-2.0Get via MCP →
Letta Linear CLI
Lettaoperations
Manage Linear issues from the command line using the linear cli. This skill allows automating linear management.
ISCGet via MCP →
Letta MCP Builder
Lettaengineering
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
Apache-2.0Get via MCP →
Letta Notion API
Lettaoperations
Notion API for creating and managing pages, databases, and blocks.
MITGet via MCP →
Letta Obsidian Vault
Lettawriting
Work with Obsidian vaults (plain Markdown notes) and automate via obsidian-cli.
MITGet via MCP →
Letta PDF Toolkit
Lettawriting
Use when tasks involve reading, creating, or reviewing PDF files where rendering and layout matter; prefer visual checks by rendering pages (Poppler) and use Python tools such as `reportlab`, `pdfplumber`, and `pypdf` for generation and extraction.
Apache-2.0Get via MCP →
Letta Playwright
Lettaengineering
Use when the task requires automating a real browser from the terminal (navigation, form filling, snapshots, screenshots, data extraction, UI-flow debugging) via `playwright-cli` or the bundled wrapper script.
Apache-2.0Get via MCP →
Letta Screenshot CLI
Lettaoperations
Use when the user explicitly asks for a desktop or system screenshot (full screen, specific app or window, or a pixel region), or when tool-specific capture capabilities are unavailable and an OS-level capture is needed.
Apache-2.0Get via MCP →
Letta Sentry
Lettaoperations
Use when the user asks to inspect Sentry issues or events, summarize recent production errors, or pull basic Sentry health data via the Sentry API; perform read-only queries with the bundled script and require `SENTRY_AUTH_TOKEN`.
Apache-2.0Get via MCP →
Letta Slack CLI
Lettaoperations
Slack automation CLI — read/send/search messages, browse threads and channels, manage channels, download attachments, look up users, and run workflows.
MITGet via MCP →
Letta Slides (PPTX)
Lettacreative
Create and edit presentation slide decks (`.pptx`) with PptxGenJS, bundled layout helpers, and render/validation utilities. Use when tasks involve building a new PowerPoint deck, recreating slides from screenshots/PDFs/reference decks, modifying slide content while preserving editable output, adding charts/diagrams/visuals, or diagnosing layout issues such as overflow, overlaps, and font substitution.
Apache-2.0Get via MCP →
Letta Text-to-Speech
Lettacreative
Use when the user asks for text-to-speech narration or voiceover, accessibility reads, audio prompts, or batch speech generation via the OpenAI Audio API; run the bundled CLI (`scripts/text_to_speech.py`) with built-in voices and require `OPENAI_API_KEY` for live calls. Custom voice creation is out of scope.
Apache-2.0Get via MCP →
Letta Spotify Player
Lettacreative
Terminal Spotify playback/search via spogo (preferred) or spotify_player.
MITGet via MCP →
Letta Spreadsheet (XLSX)
Lettaoperations
Use when tasks involve creating, editing, analyzing, or formatting spreadsheets (`.xlsx`, `.csv`, `.tsv`) with formula-aware workflows, cached recalculation, and visual review.
Apache-2.0Get via MCP →
Letta Transcribe Audio
Lettawriting
Transcribe audio files to text with optional diarization and known-speaker hints. Use when a user asks to transcribe speech from audio/video, extract text from recordings, or label speakers in interviews or meetings.
Apache-2.0Get via MCP →
Letta Visual Identity
Lettacreative
Build and maintain a persistent visual identity for your agent using Flux Kontext Pro. Use when the user asks the agent to generate selfies, avatars, character art, or any image that should look like the same person across generations.
MITGet via MCP →
open contribution
Want to publish an Oski?
Oskis are open-source Skilskis — contribute yours via GitHub. Include a SKILL.md, a license, and a source attribution and we will list it here.
Submit a PR →