#SkillRepo stars
- 913Claude Design PackPeiiii/skildDesign toolkit: UI/UX, themes, brand guidelines, and generative art.117
- 914Claude Dev PackPeiiii/skildDeveloper toolkit: build, test, deploy, and debug with curated skills.117
- 915Claude HudTerminalSkills/skillsBuild heads-up display (HUD) dashboards for AI coding agents — show context usage, active tools, running sub-agents, and task progress in real-time. Use when: monitoring AI agent activity, building developer tools for AI-assisted coding, creating status dashboards for agent workflows.213
- 916Claude MemTerminalSkills/skillsAdd persistent memory to Claude Code that survives across sessions. Use when: maintaining continuity across Claude Code sessions, building agents with persistent project memory, avoiding repeated context setup. Covers claude-mem (AI-compressed session logs) and Claude Subconscious (Letta-based background agent).213
- 917Claude Office PackPeiiii/skildOffice toolkit: PDF/Word/PPT/Excel + internal comms.117
- 918ClearmlTerminalSkills/skillsClearML is an open-source MLOps platform that records machine-learning experiments, versions datasets, chains tasks into pipelines and runs them on remote machines through agents and queues. Use when a user asks to "track experiments with ClearML", "log metrics, artifacts and models", "version a dataset", "run training on a remote GPU with clearml-agent", "build a ClearML pipeline", "run hyperparameter optimization", or "self-host ClearML Server". Covers the clearml 2.x Python SDK, clearml-agent 3.x and ClearML Server 2.x.213
- 919ClineTerminalSkills/skillsCline is an open-source autonomous coding agent that runs in VS Code, JetBrains IDEs, the terminal (npm package `cline`) and a desktop app, and edits files, runs commands and uses MCP tools with your approval. Use when a user asks to set up Cline, run it headless in CI, choose a model provider, write .clinerules, connect an MCP server, switch between Plan and Act mode, control auto-approve or YOLO mode, or hand a multi-file refactor to an agent.213
- 920Coding AgentTerminalSkills/skillsRun Codex CLI, Claude Code, or other coding agents as background processes for programmatic control. Use when a user asks to run a coding agent, delegate a task to another AI, spawn a sub-agent, run Claude Code in the background, or orchestrate multiple coding agents on separate tasks.213
- 921Comet MlTerminalSkills/skillsComet ML is a platform for tracking machine learning experiments, managing registered models, and comparing runs. Use when logging experiments, hyperparameters and metrics, registering model versions, or comparing training runs; LLM tracing goes through Comet's Opik. Helps developers log experiments, compare model versions, and build reproducible ML pipelines with automatic code/data versioning.213
- 922Conf Pipeline Orchestrationlyndonkl/claudeThe multi-agent communication and orchestration discipline for a staged pipeline whose stages each carry calibrated uncertainty. Agents talk through files with defined schemas and status fields (never free text); the orchestrator passes input paths plus an explicit output path plus a return contract, verifies each artifact's confidence before advancing a stage gate, holds and integrates worker outputs rather than passing them through, freezes its protected control logic against a checksum, maintains a diversity floor, hardens the fragile handoffs not the resilient hubs, and names the substitut200
- 923Context EngineeringTerminalSkills/skillsAudits and reorganises what an AI coding agent carries in its context window: instruction files, path-scoped rules, skills, subagents, hooks and the running conversation. Use when someone says "the agent ignores our CLAUDE.md", "set this repo up for Claude Code / Codex / Cursor", "my AGENTS.md is too long", "quality drops in long sessions", "it keeps inventing APIs", "what should go in a skill versus the rules file", or asks how to hand work to a subagent. Grounded in the documented loading behaviour of Claude Code, with the equivalents for Codex, Gemini CLI and Cursor.213
- 924Context7TerminalSkills/skillsContext7 fetches current, version-specific documentation and code examples for software libraries and hands them to an AI coding agent, so generated code matches the library version in use instead of stale training data. Use when someone says "use context7", "get the latest docs for this library", "look up the current API", "the agent keeps using a deprecated method", "set up Context7 in Claude Code or Cursor", or asks how to call a framework whose API changed recently. Covers the ctx7 CLI, the MCP server and its two tools, library IDs and version pinning, API keys and rate limits, and the RES213
- 925Continue DevTerminalSkills/skillsContinue is an open-source AI code assistant for VS Code, JetBrains and the terminal (the cn CLI) that works with any LLM: Claude, GPT, Gemini, Ollama and other local models. Use when a user asks to configure Continue with config.yaml, add chat or tab autocomplete models, write rules or custom prompts, connect MCP servers, run cn headless in scripts, or migrate from config.json. Continue was acquired by Cursor in June 2026: the release from that month is final and the Hub is offline, so the skill covers local, self-configured use.213
- 926CuaTerminalSkills/skillsCua gives AI agents a computer of their own: disposable Linux, Windows or macOS sandboxes on your machine that an agent can run commands in, take screenshots of, and drive with mouse and keyboard, from a `cua` command line or a Python SDK. Use when someone asks to "give my agent a sandboxed desktop", "run a command in an isolated container or VM", "take a screenshot of the sandbox", "automate a GUI app safely", or "script a computer-use agent environment". Local sandboxes only; no account needed.213
- 927Cursor AITerminalSkills/skillsBuild software with Cursor, the AI-powered code editor. Use when a user asks to configure Cursor rules, write project rules (.cursor/rules, AGENTS.md), use Agent (formerly Composer) for multi-file edits, integrate MCP servers, or optimize AI-assisted coding workflows.213
- 928Data Schema Knowledge Modelinglyndonkl/claudeCreates rigorous, validated models of entities, relationships, and constraints for database schemas (SQL, NoSQL, graph), knowledge graphs, ontologies, API data models, and taxonomies. Covers relational, document, graph, event/time-series, and dimensional schema patterns with lifecycle modeling, soft deletes, polymorphic associations, and hierarchies. Use when user mentions "schema", "data model", "entities", "relationships", "ontology", "knowledge graph", or when data structures need formalization.200
- 929Deer FlowTerminalSkills/skillsInstalls and runs DeerFlow 2.0, ByteDance's open-source "super agent harness" that gives a lead agent sub-agents, long-term memory, a sandbox for running code, and a library of skills for deep research, reports and slide decks. Use when a user wants to set up DeerFlow with Docker or locally, configure models in config.yaml, choose a sandbox mode, call it from Python with DeerFlowClient, or debug a broken setup with make doctor. Triggers include "set up DeerFlow", "run a deep research agent", "super agent harness", "deer-flow config.yaml".213
- 930Delete AgentBerriAI/litellm-skillsDelete an AI agent from a live LiteLLM proxy. Ask for the agent_id and confirm before calling DELETE /v1/agents/{agent_id}.109
- 931Delete MCPBerriAI/litellm-skillsDelete an MCP server from a live LiteLLM proxy. Ask for the server_id and confirm before calling DELETE /v1/mcp/server/{server_id}.109
- 932Delete ModelBerriAI/litellm-skillsDelete a model from a live LiteLLM proxy. Asks for the model name or model_id and confirms before calling POST /model/delete. Use when the user wants to remove, delete, or unregister a model from a LiteLLM proxy instance.109
- 933DifyTerminalSkills/skillsDify is an open-source platform for building LLM apps such as chatbots, agents, workflows and RAG knowledge bases, and it exposes every published app as a REST API. Use when a user asks to self-host Dify with Docker Compose, configure Dify environment variables, call a Dify app or workflow API, upload documents to a Dify knowledge base, export or import a Dify DSL file, run a Dify app from the terminal with difyctl, or upgrade and back up a Dify instance.213
- 934DspyTerminalSkills/skillsDSPy is a Python framework from Stanford NLP that replaces hand-written prompts with code: you declare LLM tasks as typed signatures, compose them into modules, and let optimizers (BootstrapFewShot, MIPROv2, GEPA) tune the prompts and few-shot examples against your metric. Use when the user asks about DSPy, signatures, ChainOfThought, ReAct, teleprompters or optimizers, or wants to stop hand-tuning prompts.213
- 935DvcTerminalSkills/skillsDVC (Data Version Control) tracks large datasets and models next to Git, builds reproducible ML pipelines and compares experiments. Use when the user says "version my dataset", "dvc add", "dvc repro", "track ML experiments", "push data to S3 or GCS" or wants to reproduce a model from a Git commit.213
- 936E2bTerminalSkills/skillsE2B is a cloud platform that gives AI agents secure, isolated sandboxes — ephemeral Linux VMs with a filesystem, package managers, and internet access — to run AI-generated code safely. Use when a user wants an agent to execute Python or JavaScript, install packages, read/write files, or run a long process without risking the host machine, or wants to wire code execution into a LangChain, CrewAI, or custom agent loop.213
- 937Earendil PiTerminalSkills/skillsPi is a minimal, open-source terminal coding agent from Earendil Works that works with many model providers and is customised through extensions, skills and prompt templates. Use when the user asks to install Pi, run `pi` in a repository, log in to a provider, script Pi with `--print` or `--mode json`, point it at a local Ollama model, add MCP servers, or sandbox an agent that has no built-in permission prompts.213
- 938Embedding Fusion Strategylyndonkl/claudeDesigns embedding strategies that combine semantic (text-based) and structural (graph-based) information at node, edge, path, and subgraph levels for knowledge graphs. Use when selecting embedding granularity, choosing complementary semantic and structural approaches, designing fusion strategies (concatenation, attention, contrastive alignment), or when user mentions node embeddings, embedding fusion, vector representations for graphs, or combining text and graph signals.200
- 939Fal AITerminalSkills/skillsRun hosted image, video and audio AI models through the fal.ai API with the JavaScript or Python client. Use when generating images with Flux or LoRA, animating images into video, transcribing audio with Whisper, running inference through a queue with webhooks, or building AI media features.213
- 940FastmcpTerminalSkills/skillsFastMCP is a Python framework for building Model Context Protocol (MCP) servers and clients: a decorated Python function becomes a tool, resource or prompt that an AI agent can call, with the schema generated from type hints. Use when someone asks to "build an MCP server in Python", "create a FastMCP server", "expose this function to Claude as a tool", "turn our OpenAPI spec into MCP tools", "test my MCP server", "call an MCP server from Python", or "install my server into Claude Code or Cursor". Covers tools, resources and prompts, stdio and HTTP transports, the fastmcp CLI, in-memory tests, 213
- 941Fff NvimTerminalSkills/skillsfff (Fast File Finder, fff.nvim) is a Rust file-search toolkit with typo-resistant path and content search, frecency ranking and an in-memory index, shipped as a Neovim picker, an MCP server for AI agents, Node and Bun, Rust and C libraries. Use when the user wants faster file search or grep for Claude Code, Codex or Cursor, a Telescope replacement in Neovim, or a search library for an agent tool.213
- 942Fireworks AITerminalSkills/skillsFireworks AI runs open-weight LLMs (Kimi, GLM, DeepSeek, Qwen, gpt-oss and others) through an OpenAI-compatible serverless API and dedicated deployments. Use when integrating Fireworks inference, streaming chat, tool calling, JSON-schema structured output, prompt caching, batch inference, or fine-tuning a model with firectl and serving the result.213
- 943Flux ModelTerminalSkills/skillsFLUX is Black Forest Labs' family of image generation models (FLUX.2, FLUX 3 Image, and the older FLUX.1 Dev, Schnell and Pro), available through the BFL API, fal.ai and Replicate. Use when generating photorealistic or product images, text-heavy graphics, exact brand colors, image editing with references, fast batch generation, or LoRA styles with FLUX.1 Dev or FLUX.2 klein. Covers model choice, request code for each provider, and licensing.213
- 944Function CallingTerminalSkills/skillsFunction calling (tool use) lets an LLM request calls to your own functions while your code runs them and returns the results in a loop. Covers the OpenAI Responses API, the Anthropic Messages API, parallel calls, tool_choice, strict schemas and error handling. Use when building AI agents with tools, letting LLMs query APIs or databases, or creating agentic workflows.213
- 945Gemini CLITerminalSkills/skillsGemini CLI is Google's open-source AI agent for the terminal: it reads and edits code, runs shell commands, and connects to MCP servers using Gemini models. Use when someone asks to "install Gemini CLI", "run gemini in a script", "set up GEMINI.md", "add an MCP server to Gemini CLI", "sandbox Gemini CLI", or "log in to Gemini CLI". Covers current install, authentication (the unpaid Google-account tier ended 18 June 2026), headless mode, GEMINI.md, MCP, and sandboxing.213
- 946Generative Engine OptimizationTerminalSkills/skillsAudits and improves how a website is found and cited by AI answer engines (Google AI Overviews and AI Mode, ChatGPT search, Perplexity, Claude, Copilot). Use for Generative Engine Optimization (GEO, AEO, "AI SEO"): "get cited by ChatGPT", "are AI crawlers blocked", "AI Overviews visibility", "llms.txt", "will AI bots see my site". Checks crawler access in robots.txt, server-rendered content, entity markup and answer-ready writing, and says which findings are documented and which are heuristics. Not about geography. For classic ranking use seo-audit; for JSON-LD use schema-markup.213
- 947GitdiagramTerminalSkills/skillsShows how a public GitHub repository is built: an AI-made architecture diagram with a written explanation, the main components and their source paths, and Mermaid source. Use when the user asks "how is owner/repo structured?", wants an architecture overview of an open-source project before reading its code, needs Mermaid source for a repository, or wants to add the GitDiagram MCP server to Claude Code, Codex, Gemini CLI or Copilot CLI. Covers the hosted site, the .md endpoint, the MCP tools and self-hosting.213
- 948GitnexusTerminalSkills/skillsGitNexus indexes a codebase into a local knowledge graph of symbols, calls, imports, clusters and execution flows, and serves it to AI coding agents through an MCP server and a CLI. Use when a user asks to index a repo with GitNexus, set up the GitNexus MCP server for Claude Code, Cursor or Codex, check what breaks before changing a function (impact, blast radius), see how a feature flows through the code, review the impact of uncommitted changes, run Cypher queries on a code graph, or explore a repository in the GitNexus web UI.213
- 949Graphrag System Designlyndonkl/claudeDesigns complete GraphRAG systems integrating graph databases, vector stores, orchestration frameworks, and LLM reasoning. Guides through pattern selection, technology stack decisions, integration pipeline design, and domain-specific customizations. Use when designing GraphRAG systems, choosing technology stacks for graph-augmented retrieval, combining Neo4j with LLM, using LangChain/LlamaIndex knowledge graphs, applying community detection for RAG, building hybrid symbol-vector pipelines, or deploying production or domain-specific GraphRAG.200
- 950Heuristics and Checklistslyndonkl/claudeProvides practical frameworks for fast decision-making through mental shortcuts (heuristics) and systematic error prevention through structured checklists. Guides through designing effective heuristics, creating checklists for complex procedures, and recognizing when shortcuts lead to biases. Use when making decisions under time pressure or uncertainty, preventing errors in complex procedures, designing decision rules or checklists, simplifying complex choices, or when user mentions heuristics, rules of thumb, mental models, checklists, error prevention, cognitive biases, satisficing, or stand200
- 951Interrogateadriannoes/awesome-agentic-aiUse for "interrogate", "adversarial review", "multi-model review", "challenge this", "stress test this code", "find blind spots", or "tear this apart". Multiple LLM reviewers challenge changes from independent angles.100
- 952Knowledge Graph Constructionlyndonkl/claudeDesigns and builds knowledge graphs from unstructured or semi-structured data sources. Guides through data model selection (LPG, RDF, hypergraph, temporal), schema design, entity/relation extraction pipelines, and layered architecture construction. Use when designing knowledge graphs, choosing between LPG vs RDF, planning entity extraction, designing graph schemas, aligning ontologies, building a KG for RAG, or when user mentions knowledge graph construction.200
- 953Meta Prompt Engineeringlyndonkl/claudeTransforms vague or unreliable prompts into structured, constraint-aware prompts with explicit roles, task decomposition, output formats, and quality checks. Use when prompts produce inconsistent outputs, need explicit structure and constraints, require safety guardrails, involve multi-step reasoning that needs decomposition, need domain expertise encoding, or when user mentions improving prompts, prompt templates, structured prompts, prompt optimization, reliable AI outputs, or prompt patterns.200
- 954Ml Primitive Decoderlyndonkl/claudeDecomposes any ML construct (attention, layer norm, softmax, convolution, dropout, contrastive loss, diffusion step, gradient descent update, cross-entropy) into the small set of linear-algebra primitives it's built from, then explains why those primitives produce the observed behavior. Includes an ablation thought experiment that asks "what would break if you removed this piece?". Use when the user asks "why does X work?", "explain attention/conv/norm intuitively", "what's actually happening in this layer", or when reading an architecture paper and a particular block doesn't make sense yet.200
- 955Mlb Decision Loggerlyndonkl/claudeAppends structured decision entries to the yahoo-mlb decision log (tracker/decisions-log.md) on behalf of any agent in the MLB team. Validates entries against the authoritative schema, serializes concurrent writes from parallel agents, and runs the Monday calibration pass to fill in outcomes and update the variant scoreboard. Use when any MLB agent needs to record a decision, when the coach requests "log decision", "append to decision log", "record variant outcome", or runs the "calibration pass".200
- 956Mlb Faab Sizerlyndonkl/claudeComputes FAAB (Free Agent Acquisition Budget) recommended and maximum bids for Yahoo fantasy baseball waiver targets. Implements the baseball-specific layering of the faab-bid-framework (positional_need_fit, role_certainty, urgency, season_pace, league-inflation calibration) and DELEGATES the game-theoretic primitives -- first-price shading and winner's-curse haircut -- to the sibling skills `auction-first-price-shading` and `auction-winners-curse-haircut`. Produces a recommended bid, a hard ceiling, a rationale with the full delegation chain, and guardrail flags. Use when the user asks "how m200
- 957Mlb League State Readerlyndonkl/claudeParses Yahoo Fantasy Baseball league state (roster, standings, current matchup, FAAB remaining, free agents) from authenticated Yahoo team pages via Claude-in-Chrome browser automation, then grounds it against league-config.md and team-profile.md to emit a normalized league-state bundle every other agent can consume without re-scraping. Use when the coach or any downstream agent needs to read Yahoo roster, refresh team profile, pull league state, get current matchup, check FAAB remaining, list free agents, or when user mentions "what's on my roster", "who am I playing this week", "how much FAA200
- 958Model Equivariance Auditorlyndonkl/claudeVerifies that implemented neural network models correctly respect their intended symmetries through systematic equivariance testing, layer-wise isolation, and gradient analysis. Use when testing model equivariance, debugging symmetry bugs, verifying implementation correctness, checking if a model is actually equivariant, or diagnosing why an equivariant model isn't working.200
- 959Narrative Fidelity Auditlyndonkl/claudeRuns the hard gate on invention in fact-based narrative — a bright-line refusal sweep, an interior-state provenance ladder ([A] said-so / [B] contemporaneous document / [C] behavioural inference / [D] unsourced, where any [D] blocks publication), an LLM-specific fabrication red-flag scan, a three-altitude "How do you know?" prosecution at sentence, paragraph and passage level, a subtraction-log set review, and a note on sources generated from the deviation log. Use before shipping any narrative built on real evidence — market history, incident post-mortem, biography, ML writeup, supply-chain r200
- 960Normalize Formatlyndonkl/claudeNormalizes a single inbox file of any supported format (plain markdown, Claude.ai JSON export, Claude Code JSONL session, Readwise markdown/CSV highlight, transcript with timestamps or speaker labels, link capture) into a clean markdown body plus partial frontmatter (id, title, source block, word_count). Handles format-specific failure modes — JSON content-block arrays, timestamp stripping, per-highlight chunking, URL-vs-commentary separation. Use when ingesting any inbox item for the substacker Librarian. Trigger keywords — normalize, convert, parse, transcript, export, JSON, JSONL, highlight200