AI & ML
AI & ML agent skills cover the machine-learning workflow itself: writing and evaluating prompts, building RAG pipelines, running evals, and wiring up model APIs. Each one is a SKILL.md file your agent loads on demand, so the know-how travels across Claude Code, Cursor, and 60+ agents.
-
tomevault-io Bundle Sheaf Laplacian CoordinationSheaf neural network coordination via graph Laplacians for distributed consensus and harmonic inference. Use when coordinating multi-agent systems, building sheaf-aware GNNs, or implementing distributed consensus protocols. Use when this capability is needed.
-
tomevault-io Bundle Universal Learning SignatureFramework for measuring learning dynamics in multi-agent systems and communication networks. Provides D (dimensionality), f (feedback fraction), and H₁ (topological cycles) measurements with confidence scoring. Validates across 4 domains (Topobench synthetic, GitHub networks, IES empirical, DuckDB real). Use this skill when measuring learning system characteristics, verifying convergence in multi-agent systems, comparing learning mechanisms across domains, or trading measurement services in agent marketplaces. Use when this capability is needed.
-
tomevault-io Bundle Multi LLM Judge同一プロンプトを複数 AI CLI(Claude Code / Codex / Gemini)に送り、回答を比較・評価する。 Use when this capability is needed.
-
tomevault-io Bundle Meta Agent CreatorGuide for creating specialized AI agents (subagents). This skill should be used when users want to create a new agent, define agent configurations, or need guidance on agent architecture. Use when this capability is needed.
-
tomevault-io Bundle Meta Skill CreatorGuide for creating effective AI agent skills. This skill should be used when users want to create a new skill, update an existing skill, or need guidance on skill architecture and best practices. Use when this capability is needed.
-
tomevault-io Bundle Praneybehl LLM Wiki Plugin LLM Wiki PluginLLM Wiki
-
tomevault-io Bundle Dia SetupActivates, reconfigures, or deactivates the Digital Innovation Agents workflow in a project. Writes the .dia/config.toml settings file and manages anchor blocks in agent-facing files (CLAUDE.md, AGENTS.md, GEMINI.md, .cursorrules, .github/copilot-instructions.md, .windsurfrules). Use this skill when the user mentions "DIA aktivieren", "DIA installieren", "DIA initialisieren", "DIA setup", "DIA settings", "Workflow-Modus", "Modus wechseln", "DIA off", "DIA deaktivieren", "Plugin aktivieren". Single skill that covers both first-time activation and later reconfiguration; the skill detects which path applies from the presence of .dia/config.toml. Use when this capability is needed.
-
tomevault-io Bundle Gh Default BranchRetrieve the default branch name of the current Git repository using GitHub CLI. Use when asked "What is the default branch?", "Get the default branch", "What is the main branch?", "Show me the base branch", "get repo default branch", or when git operations require the default branch name (creating PRs, comparing branches, checking out base branch). Returns branch names like main, master, or develop using GitHub CLI. Use when this capability is needed.
-
tomevault-io Bundle Raja Patnaik Obsidian Agent Obsidian AgentObsidian Vault Manager
-
tomevault-io Bundle Recomby AI Promptly Prompt Promptly Promptpromptly-prompt
-
tomevault-io Bundle Synthetic Data GenerationGenerate synthetic data using sdg_hub with composable blocks and YAML flows. Use when the user wants to create training datasets, generate QA pairs, run data generation pipelines, build custom flows, produce synthetic data from documents, use agent frameworks for data generation, or distill MCP tool-use traces. Supports pre-built flows, custom Python scripts, and YAML flow authoring with 20+ blocks, agent connectors (Langflow, LangGraph), MCP tool-use, and 100+ LLM providers via LiteLLM. Use when this capability is needed.
-
tomevault-io Bundle Claude OrchestratorSpawn and manage parallel Claude workers for software development. Use for parallel feature development, multi-agent coordination, or autonomous project execution. Use when this capability is needed.
-
tomevault-io Bundle Random NumberGenerate a random integer between min and max (inclusive). Use when the user asks for a random number. Use when this capability is needed.
-
tomevault-io Bundle Retrieve Relevant Information Through RAGLeverage Retrieval Augmented Generation to retrieve relevant information from a a LlamaCloud Index. Requires the llama_cloud_services package and LLAMA_CLOUD_API_KEY as an environment variable. Use when this capability is needed.
-
tomevault-io Bundle Agent Code Goal PlannerAgent skill for code-goal-planner - invoke with $agent-code-goal-planner Use when this capability is needed.
-
tomevault-io Bundle Agent Code Review SwarmAgent skill for code-review-swarm - invoke with $agent-code-review-swarm Use when this capability is needed.
-
tomevault-io Bundle Agent Crdt SynchronizerAgent skill for crdt-synchronizer - invoke with $agent-crdt-synchronizer Use when this capability is needed.
-
tomevault-io Bundle Agent Github Pr ManagerAgent skill for github-pr-manager - invoke with $agent-github-pr-manager Use when this capability is needed.
-
tomevault-io Bundle Agent Orchestrator TaskAgent skill for orchestrator-task - invoke with $agent-orchestrator-task Use when this capability is needed.
-
tomevault-io Bundle Agent Pagerank AnalyzerAgent skill for pagerank-analyzer - invoke with $agent-pagerank-analyzer Use when this capability is needed.
-
tomevault-io Bundle Agent Queen CoordinatorAgent skill for queen-coordinator - invoke with $agent-queen-coordinator Use when this capability is needed.
-
tomevault-io Bundle Agent Sparc CoordinatorAgent skill for sparc-coordinator - invoke with $agent-sparc-coordinator Use when this capability is needed.
-
tomevault-io Bundle Agent Trading PredictorAgent skill for trading-predictor - invoke with $agent-trading-predictor Use when this capability is needed.
-
tomevault-io Bundle Agent Worker SpecialistAgent skill for worker-specialist - invoke with $agent-worker-specialist Use when this capability is needed.
-
tomevault-io Bundle Gh Address Pr CommentsAddress GitHub Pull Request feedback with the gh CLI. Use when a user provides a PR number and asks to fetch comments, verify which comments are meaningful, add regression tests, implement fixes, run all tests, and push the branch. Use when this capability is needed.
-
tomevault-io Bundle Optim OrchestratorOrchestrate N optimization agents with random personas for Kokkos CUDA GPU optimization. Use when optimizing GPU code, running parallel optimization experiments, or benchmarking different algorithm variants. Use when this capability is needed.
-
tomevault-io Bundle Scofieldfree Excalidraw MCP Excalidraw MCPExcalidraw Drawing (Minimal)
-
tomevault-io Bundle Braintrust TracingBraintrust tracing for Maestro - hook architecture, sub-agent correlation, debugging Use when this capability is needed.
-
tomevault-io Bundle Write Agents MdUse when Codex needs to create, rewrite, audit, slim down, or install AGENTS.md/CLAUDE.md agent instruction files for a repository, especially when avoiding /init-style generated context, reducing context debt, adding repo-specific pitfalls, or setting nested AGENTS.md guidance.
-
tomevault-io Bundle ProofreadingProofread and correct text for grammar, spelling, punctuation, style, clarity, and consistency, with support for multiple style guides and readability analysis. Use when this capability is needed.
-
tomevault-io Bundle Dependency CheckerAnalyzes the Agent Alchemy plugin ecosystem to detect dependency issues across all plugin groups
-
tomevault-io Bundle Git WorkflowmergeMerge git branches with auto-generated Conventional Commits messages. Use when merging branches, finishing feature work, or creating merge commits. Use when this capability is needed.
-
tomevault-io Bundle Dev Logs开发日志记录规范。每次开发循环后必须记录。 Use when this capability is needed.
-
tomevault-io Bundle Parallel ClaudeLaunch multiple Claude Code instances in parallel using tmux and git worktrees to tackle beads tasks concurrently. Use when user mentions parallel execution, multi-agent, parallel claude, or wants to run multiple Claude instances simultaneously on different tasks. Use when this capability is needed.
-
tomevault-io Bundle Mandatory Testing Linting GuardEnforce mandatory npm test and npm run lint execution after every code change with no exceptions for code quality and test coverage compliance Use when this capability is needed.
-
tomevault-io Bundle Sluggable DevelopmentUse when making a field on an Eloquent model sluggable, generating the migration for a slug column, switching to self-healing URLs, or resolving a model from its slug in a route. Trigger when the request mentions slugs, permalinks, the spatie/laravel-sluggable package, the HasSlug or HasTranslatableSlug trait, the #[Sluggable] attribute, SlugOptions, findBySlug, self-healing URLs, or stale slug redirects in a Laravel project. Covers choosing between the attribute and the trait, generating unique slugs, configuring separator/length/language/scope/uniqueness, preventing slug overwrites, translatable slugs via spatie/laravel-translatable, route model binding through the slug column, self-healing route keys, customizing the 308 redirect through the SelfHealing facade, and overriding the default actions via config/sluggable.php. Do not use for one-off URL-safe strings, signed URLs, or Laravel's built-in Str::slug helper when the result is not stored on a model.
Frequently asked questions
What are AI & ML agent skills?
AI & ML agent skills cover the machine-learning workflow itself: writing and evaluating prompts, building RAG pipelines, running evals, and wiring up model APIs. Each one is a SKILL.md file your agent loads on demand, so the know-how travels across Claude Code, Cursor, and 60+ agents.
Which AI & ML skills are most installed?
Popular AI & ML skills on SkillMD right now include sheaf-laplacian-coordination, universal-learning-signature, multi-llm-judge. Rankings shift as installs change; sort this page by "Most installs" for the live list.
Do AI & ML skills work with Claude Code and Cursor?
Yes. Every skill here ships as a SKILL.md file, an open format that works in Claude Code, Claude.ai, Cursor, Codex, Windsurf, and 60+ other agents. Install one with npx skillmds@latest add <owner>/<name>, or copy the file into your agent's skills directory.