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.
-
majiayu000 Bundle Generate Video 3プロダクトデモ動画を自動生成。百聞は一見にしかず、を体現。Use when user mentions '/generate-video', video generation, product demos, or visual documentation. Do NOT load for: embedding video players, live demos, video playback features. Requires Remotion setup.
567 - majiayu000 Bundle Lark Agent Simple 2
version: 1.0.0
567 - majiayu000 Bundle Moonshot Orchestrator 2
PM workflow orchestrator. Analyzes user requests and automatically runs the optimal agent chain.
567 - majiayu000 Bundle Opencode Copilot Opus 2
Use this skill when you need Codex to collaborate with GitHub Copilot Opus (via opencode), especially for architecture review, second-opinion validation, and iterative discussion that must continue in the same opencode session_id. Covers model selection for github-copilot/claude-opus-4.6, stable sandbox-safe invocation, session continuity with -c / -s, and troubleshooting common opencode errors.
567 - majiayu000 Bundle Context Engineering 18
Master context engineering for AI agents - token optimization, degradation patterns, compression, memory systems, multi-agent coordination, evaluation. Use when designing agents, debugging context failures, or building LLM pipelines.
567 - majiayu000 Bundle Paw Review Correlation 2
Synthesizes findings across multiple PRs to identify cross-repository dependencies, interface mismatches, and coordination gaps.
567 - majiayu000 Bundle Hybrid Search Implementation 2
Combine vector and keyword search for improved retrieval. Use when implementing RAG systems, building search engines, or when neither approach alone provides sufficient recall.
567 - majiayu000 Bundle Startup Financial Modeling 2
This skill should be used when the user asks to "create financial projections", "build a financial model", "forecast revenue", "calculate burn rate", "estimate runway", "model cash flow", or requests 3-5 year financial planning for a startup.
567 - majiayu000 Bundle Test Multitenant Isolation 2
Validates complete data isolation between tenants, tests cross-tenant access, ensures proper query scoping
567 - majiayu000 Bundle Add Voice Transcription 5
Add voice message transcription to FFT_nano using OpenAI's Whisper API. Automatically transcribes WhatsApp voice notes so the agent can read and respond to them.
567 - majiayu000 Bundle Project Learnings 7
Captures project-specific patterns and anti-patterns into the project's configuration. Loaded by other skills (bug-killer, feature-dev, etc.) when they discover project-specific knowledge worth encoding for future sessions.
567 - majiayu000 Bundle Memory Checkpoint 3
在對話被 Summarize 壓縮前，主動將詳細記憶外部化到 Memory Bank，避免重要上下文遺失。
567 - majiayu000 Bundle Motherduck Migrate To Motherduck 2
Plan a migration onto MotherDuck. Use when moving from Snowflake, Redshift, PostgreSQL, dbt-heavy stacks, or lakehouse tooling and the key decisions are target pattern, cutover slices, validation, rollback, and native-versus-DuckLake posture.
567 - majiayu000 Bundle Creating Effective Skills 2
Creating high-quality agent skills following Claude's official best practices. Use when designing, implementing, or improving agent skills, including naming conventions, progressive disclosure patterns, description writing, and appropriate freedom levels. Helps ensure skills are concise, well-structured, and optimized for context efficiency.
567 - majiayu000 Bundle Android Development 3
Use when working with .kt/.kts files, Gradle builds, Jetpack Compose, or Android-specific features
567 - majiayu000 Bundle Factory Spec 2
Phase MODEL - Génère specs + ADR + rules
567 - majiayu000 Bundle Ln 002 Best Practices Researcher 2
Research best practices via MCP Ref/Context7/WebSearch and create documentation (guide/manual/ADR/research). Single research, multiple output types.
567 - majiayu000 Bundle Preserve Existing Code Rule 2
You are a coding standards expert specializing in preserve existing code rule.
567 - majiayu000 Bundle Configure Integration 2
Set up a new MCP server, tool integration, or workspace extension
567 - majiayu000 Bundle Hive Project Management 2
Manage Agent Hive projects using AGENCY.md files. Use this skill when creating, updating, or working with AGENCY.md project files, managing project metadata (status, owner, blocked, priority), marking tasks complete, adding agent notes, or understanding the Agent Hive shared memory system.
567 - majiayu000 Bundle Ln 510 Quality Coordinator 4
Coordinates code quality checks: metrics, cleanup, agent review, regression, log analysis. Use when Story needs quality_verdict with aggregated results.
567 - majiayu000 Bundle Context Optimization 6
Apply compaction, masking, and caching strategies to optimize context windows. Use when reducing token usage or improving LLM context efficiency.
567 - majiayu000 Bundle Smart Fork 2
Smart Forking - Find and fork from relevant historical sessions using parallel memory search across claude-mem, memvid, handoffs, and ledgers
567 - majiayu000 Bundle Backend Atomic Commit 2
Pedantic backend pre-commit and atomic commit Skill for Django/Optimo-style repos. Enforces local AGENTS.md / CLAUDE.md, pre-commit hooks, .security/* helpers, and Monty’s backend engineering taste – with no AI signatures in commit messages.
567 - majiayu000 Bundle Eld Record Memory Collector 2
Collect and verify project information for pce-memory with multi-model validation using Codex CLI. Use when gathering project context, onboarding to a new codebase, or building a knowledge base. Triggers on "collect project info", "build knowledge base", "index this project", or "remember this codebase".
567 - majiayu000 Bundle Motherduck Security Governance 2
Explain MotherDuck security, governance, and access-control patterns. Use when a security_compliance_owner, technical_owner, or application_builder is asking about residency, access boundaries, service accounts, isolation, sharing, or governance posture.
567 - majiayu000 Bundle Test Intelligence Algorithms 2
Validates sports science algorithms (VDOT, TSS, TRIMP, FTP, VO2max, Recovery, Nutrition) for correctness
567 - majiayu000 Bundle Data Engineering Data Driven Feature 2
Build features guided by data insights, A/B testing, and continuous measurement. Use when implementing data-driven product features or running experiments.
567 - majiayu000 Bundle Chrome Devtools Site Search 2
Validate website parsing and browser automation feasibility by browsing and searching within a user-specified website scope using the chrome-devtools MCP server (mcp_servers.chrome-devtools); summarize results backed by observed page content (real titles/URLs), and open matching pages for review. Use when the user asks you to open a site, find specific content on it, run a site-scoped query, and keep the relevant pages open.
567 - majiayu000 Bundle Output Dev Step Function 2
Create step functions in steps.ts for Output SDK workflows. Use when implementing I/O operations, error handling, HTTP requests, or LLM calls.
567 - majiayu000 Bundle Content Modeling Best Practices 2
Structured content modeling principles with Sanity-specific guidance. Use when designing or reviewing content schemas, document types, field structures, or content architecture — including decisions around references vs embedding, content reuse, taxonomy, page builders, multi-channel delivery, or refactoring existing schemas. Trigger when the user mentions schema design, content model, document types, content structure, headless CMS architecture, or asks how to model any content type.
567 - majiayu000 Bundle Context Engineering 19
Optimize context windows and token usage for LLM efficiency.
567 - majiayu000 Bundle Swimlane Visualization 2
Design swimlane UI patterns for visualizing ADW execution. Use when building observability dashboards, monitoring agent workflows, or creating real-time status displays.
567 - majiayu000 Bundle Orchardcore AI Chat Interactions 2
Skill for configuring AI Chat Interactions in Orchard Core using the CrestApps module. Covers ad-hoc chat sessions, prompt routing with intent detection, document upload with RAG support, image and chart generation, and custom processing strategies.
567 - majiayu000 Bundle Context Compression 3
Design and evaluate context compression strategies for long-running agent sessions. Use when agents exhaust memory, need to summarize conversation history, or when optimizing tokens-per-task rather than tokens-per-request.
567 - majiayu000 Bundle Sparc Methodology 6
SPARC (Specification, Pseudocode, Architecture, Refinement, Completion) is a systematic development methodology integrated with Claude Flow's multi-agent orchestration capabilities. It provides 17 spe
567
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 generate-video, lark-agent-simple, moonshot-orchestrator. 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.