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 Conversations By DateBrowse conversations by calendar date. Use when user asks "what was I working on last Thursday" or specifies a date. Use when this capability is needed.
- tomevault-io Bundle Tdd Orchestrate
TDDサイクル全体をPdMとして管理。Agent Teams有効時にtdd-initから呼ばれ、全Phaseを自律的に委譲・判断する。 Use when this capability is needed.
- tomevault-io Bundle Gh Address Comments
Help address review/issue comments on the open GitHub PR for the current branch using gh CLI; verify gh auth first and prompt the user to authenticate if not logged in. Use when this capability is needed.
- tomevault-io Bundle LLM Versions
Handle current AI model versions Use when this capability is needed.
- tomevault-io Bundle Praxis Gemini Engine
Reference for the Gemini / Antigravity engine path in Praxis. Auto-loads when an agent is touching Gemini, Antigravity, `@ai-sdk/google`, `direct.google`, `google-antigravity`, `GEMINI_API_KEY`, `GOOGLE_GENERATIVE_AI_API_KEY`, or considering a new engine adapter for Google models. Captures the policy + technical constraints found in `docs/research/gemini-subscription-engine.md` (2026-05-19) so future agents don't re-discover them. Use when this capability is needed.
- tomevault-io Bundle Sec Proxy Analysis
Analyze proxy statements (DEF 14A) to extract executive compensation, governance information, and shareholder voting matters using Octagon MCP. Use when researching CEO pay, board composition, say-on-pay votes, and corporate governance practices. Use when this capability is needed.
- tomevault-io Bundle Agently Task Dev
Use only when the user explicitly wants to build with the Agently framework (mentions Agently/agently/OpenAICompatible/TriggerFlow/ToolExtension/ChromaCollection, or says “用 Agently 做/用 agently 做”). Deliver runnable code plus regression tests validating schema/ensure_keys and streaming (delta/instant/streaming_parse), with optional tools (Search/Browse/MCP), TriggerFlow orchestration, KB (ChromaDB), and serviceization (SSE/WS/HTTP). Do not use for generic streaming/testing questions that are not about Agently, or for prompt-only writing without tests/structure. Use when this capability is needed.
- tomevault-io Bundle Agent File Structure
Standard structure and key principles for agent definition markdown files. Use when this capability is needed.
- tomevault-io Bundle Agent Tool Selection
Guide for selecting appropriate VS Code Copilot tools when configuring agents, including environment-specific considerations. Use when this capability is needed.
- tomevault-io Bundle Afml Docs Loop
Build and run an AFML-grounded, chapter-by-chapter documentation loop for OpenQuant docs. Use this when you need consistent module docs, hierarchical chapter coverage, and iterative progress tracking with MCP-backed prompts. Use when this capability is needed.
- tomevault-io Bundle Generate Skill From Url
Generates a multimodal Skill markdown file from a source URL. Use this Skill when a user wants to turn a web tutorial, product support article, or software guide into a reusable agent Skill with concise steps and embedded screenshots.
- tomevault-io Bundle Neo4j Cypher Guide
Comprehensive guide for writing modern Neo4j Cypher read queries. Essential for text2cypher MCP tools and LLMs generating Cypher queries. Covers removed/deprecated syntax, modern replacements, CALL subqueries for reads, COLLECT patterns, sorting best practices, and Quantified Path Patterns (QPP) for efficient graph traversal. Use when this capability is needed.
- tomevault-io Bundle Stack Patterns
Reference for Outfitter Stack patterns including Result types, Handler contract, Error taxonomy, and @outfitter/* package conventions. Use when learning the stack, looking up patterns, understanding packages, or when "Result", "Handler", "error taxonomy", "OutfitterError", "CLI output", "pagination", "MCP server", "MCP tool", "structured logging", "redaction", "test handler", "daemon", "IPC", or "@outfitter/*" are mentioned. Use when this capability is needed.
- tomevault-io Bundle Owent Libatapp AI Agent Maintenance
AI Agent Maintenance
- tomevault-io Bundle Ordo Rule Development
Ordo rule engine Rust development guide. Helps create RuleSet, Step, conditional branches, terminal results. Use for writing rule definitions, understanding Step Flow model, creating Decision/Action/Terminal steps. Use when this capability is needed.
- tomevault-io Bundle Panniantong Agent Reach Agent Reach
Agent Reach — 互联网能力路由器
- tomevault-io Bundle LLM Debugger
Diagnoses LLM output failures including hallucinations, constraint violations, format errors, and reasoning issues. Provides root cause classification, prompt fixes, tool improvements, and new test cases. Use for "debugging AI", "fixing prompts", "quality issues", or "output errors". Use when this capability is needed.
- tomevault-io Bundle Oracle Codex
This skill should be used when the user asks to "use Codex", "ask Codex", "consult Codex", "use GPT for planning", "ask GPT to review", "get GPT's opinion", "what does GPT think", "second opinion on code", "consult the oracle", "ask the oracle", or mentions using an AI oracle for planning or code review. NOT for implementation tasks. Use when this capability is needed.
- tomevault-io Bundle Resolve Human Reviews
Resolve human PR review comments on current PR. Fetches unanswered human comments, evaluates each piece of feedback, applies fixes, and replies to every comment with the outcome. Use when this capability is needed.
- tomevault-io Bundle Nextcrm
Connect to NextCRM MCP server to manage CRM data — accounts, contacts, leads, opportunities, targets, products, contracts, activities, documents, target lists, enrichment, email accounts, campaigns, projects, and reports. Use when this capability is needed.
- tomevault-io Bundle Debug A Graphics Problem
Enable an agent to debug graphics problems Use when this capability is needed.
- tomevault-io Bundle Phauks Grimbound Prompt Engineering
Prompt Engineering for Claude Agents
- tomevault-io Bundle Spatialml
Convert ML models (ONNX/TFLite/PB/PyTorch) to QNN context binaries. Use when asked to convert models with convert_model.sh, generate QNN context binaries, or document SecureMRTools model conversion steps. Use when this capability is needed.
- tomevault-io Bundle Accept No Substitutes
This skill should be used when agents generate placeholder tokens like "pseudo-", "mock-", "temporary", "TODO", "demo-", or similar incompleteness markers. Detects substitution patterns in agent OUTPUT and triggers mandatory user interview instead of accepting incomplete work. Activates automatically on any output containing forbidden tokens. Use when this capability is needed.
- tomevault-io Bundle Bmorphism Interactome
GitHub interactome explorer for bmorphism/plurigrid ecosystem. Maps collaborations across AlgebraicJulia, Topos Institute, Anthropic, and MCP servers. Use for discovering cobordisms between research communities. Use when this capability is needed.
- tomevault-io Bundle Implicit Coordination
Stigmergic agent coordination through environment modification, not messages. Vehicle semantics where carrier encodes meaning. Use when this capability is needed.
- tomevault-io Bundle Create Simple Prompt
This skill should be used when the user asks to "create a new prompt sample", "add a new prompt sample", "scaffold a new prompt sample", "create a prompt contribution", "add a prompt", or needs to create a new prompt sample with proper folder structure, README, and sample.json metadata. Do NOT use this skill for agent instructions or system prompts. Use when this capability is needed.
- tomevault-io Bundle Restful Hateoas
RESTful API design guidelines following the Richardson Maturity Model through to Level 3 (HATEOAS) for Ruby on Rails. This skill should be used when designing, building, reviewing, or refactoring REST APIs to ensure proper resource modeling, HTTP method semantics, hypermedia controls, content negotiation, and API evolvability. Triggers on tasks involving API controllers, serializers, routing, link relations, pagination, error handling, or HTTP caching in Rails. Use when this capability is needed.
- tomevault-io Bundle Pr0nin Copilot Agent Team Team Init
Team Init — Repo Onboarding
- tomevault-io Bundle Llms Md Updater
Update llms.md documentation for LLM consumption based on codebase changes. Use when adding providers, changing APIs, updating types, or when the LLM reference guide drifts from implementation. Use when this capability is needed.
- tomevault-io Bundle Pubgo Agentdocs Agent Customization
Agent Customization
- tomevault-io Bundle Taac Competition Environment
Use before running TAAC repository Python commands, pytest, console scripts, packaging/docs CLIs, or run.sh, and when working on local setup, uv/CUDA dependency flow, online training or inference bundles, package contents, platform Python execution, or environment/debug docs. Use when this capability is needed.
- tomevault-io Bundle AI Switch Start
Resume a project previously checkpointed with ai-switch-stop. Reads PROGRESS.md and inspects git history to understand exactly where the last agent left off, then reports the current state and asks the user before continuing. Use whenever the user starts a new session on a project that has a PROGRESS.md, switches from another AI agent, or says phrases like "ai-switch start", "/ai-switch-start", "continue where we left off", "resume project", "I just switched from Claude/Codex/Gemini". Use when this capability is needed.
- tomevault-io Bundle Codex Agent
Run Codex tasks via the ai_cli Task Tool runner. Use when this capability is needed.
- tomevault-io Bundle Rayk Lucid Toolkit Dart Flutter MCP
<objective>
- tomevault-io Bundle Kill Claude Mem
Kill stale claude-mem worker and MCP server processes that leak memory across sessions. Use when Codespace feels slow or memory is low. Use when this capability is needed.
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 conversations-by-date, tdd-orchestrate, gh-address-comments. 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.