AI Ml AI agent skills

8,771 skills in the archive. Read a skill’s instructions or open its original repository.

• Nw Collapse Detection

  by @nWave-ai

  Documentation collapse anti-patterns - detection rules, bad examples, and remediation strategies for type-mixing violations

• Nw Divio Framework

  by @nWave-ai

  DIVIO/Diataxis four-quadrant documentation framework - type definitions, classification decision tree, and signal catalog

• Nw Buddy Project Reading

  by @nWave-ai

  How the nWave buddy agent reads a project to answer questions — detection, order of inspection, and citation discipline.

• Nw Operational Safety

  by @nWave-ai

  Tool safety protocols, adversarial output validation, error recovery patterns, and I/O contracts for research operations

• Nw New

  by @nWave-ai

  Guided wizard to start a new feature. Asks what you want to build, recommends the right starting wave, and launches it.

• Nw Agent Creation Workflow

  by @nWave-ai

  Detailed 5-phase workflow for creating agents - from requirements analysis through validation and iterative refinement

• Nw Interviewing Techniques

  by @nWave-ai

  Mom Test questioning toolkit, JTBD analysis, interview conduct, assumption testing framework, and hypothesis design

• Nw Authoritative Sources

  by @nWave-ai

  Domain-specific authoritative source databases, search strategies by topic category, and source freshness rules

• Nw Ab Critique Dimensions

  by @nWave-ai

  Review dimensions for validating agent quality - template compliance, safety, testing, and priority validation

• Nw Abr Critique Dimensions

  by @nWave-ai

  Review dimensions for validating agent quality - template compliance, safety, testing, and priority validation

• Nw Opportunity Mapping

  by @nWave-ai

  Opportunity Solution Trees, opportunity scoring, Lean Canvas, JTBD job mapping, and technique selection guide

• Nw Production Safety

  by @nWave-ai

  Agent safety boundaries - input validation, output filtering, scope constraints, and document creation policy

• Nw Continue

  by @nWave-ai

  Detects current wave progress for a feature and resumes at the next step. Scans docs/feature/ for artifacts.

• Nw Buddy Ssot Knowledge

  by @nWave-ai

  Single Source of Truth detection — where truth lives in an nWave repo and how to avoid contradicting it.

• Nw Five Whys Methodology

  by @nWave-ai

  Toyota 5 Whys methodology with multi-causal branching, evidence requirements, and validation techniques

• Nw Discovery Workflow

  by @nWave-ai

  4-phase discovery workflow with decision gates, phase transitions, success metrics, and state tracking

• Nw Investigation Techniques

  by @nWave-ai

  Evidence collection methods, problem categorization, analysis techniques, and solution design patterns

• Nw Design Patterns

  by @nWave-ai

  7 agentic design patterns with decision tree for choosing the right pattern for each agent type

• Nw Fp Hexagonal Architecture

  by @nWave-ai

  Hexagonal architecture patterns with pure core and side-effect shell for functional codebases

• Nw Fp Algebra Driven Design

  by @nWave-ai

  Algebra-driven API design with monoids, semigroups, and interpreters via algebraic equations

• Nw Fp Domain Modeling

  by @nWave-ai

  Domain modeling with algebraic data types, smart constructors, and type-level error handling

• Nw Fp Principles

  by @nWave-ai

  Core functional programming thinking patterns and type system foundations, language-agnostic

• Nw Fast Forward

  by @nWave-ai

  Fast-forwards through remaining waves end-to-end without stopping for review between waves.

• Nw Command Optimization Workflow

  by @nWave-ai

  Step-by-step workflow for converting bloated command files to lean declarative definitions

• Nw Fp Clojure

  by @nWave-ai

  Clojure language-specific patterns, data-first modeling, REPL-driven development, and spec

• Nw Fp Fsharp

  by @nWave-ai

  F# language-specific patterns, Railway-Oriented Programming, and Computation Expressions

• Nw Fp Kotlin

  by @nWave-ai

  Kotlin language-specific patterns with Arrow, Raise DSL, and coroutine-based effects

• Nw Hotspot

  by @nWave-ai

  Git change frequency hotspot analysis — find the most-changed files in your codebase

• Nw Pdr Review Criteria

  by @nWave-ai

  Evidence quality validation and decision gate criteria for product discovery reviews

• Nw Bugfix

  by @nWave-ai

  Bug fix workflow: root cause analysis → user review → regression test + fix via TDD

• Release Local

  by @MaxGfeller

  Run the local maintainer release flow for this Changesets-based pnpm monorepo.

• Nw Fp Usable Design

  by @nWave-ai

  Naming conventions, API ergonomics, and usability patterns for functional code

• Nw Fp Haskell

  by @nWave-ai

  Haskell language-specific patterns, GADTs, type classes, and effect systems

• Nw Fp Scala

  by @nWave-ai

  Scala 3 language-specific patterns with ZIO, Cats Effect, and opaque types

• Nw Der Review Criteria

  by @nWave-ai

  Evaluation criteria and scoring for data engineering artifact reviews

• Changeset

  by @MaxGfeller

  Draft a Changesets file for modified public packages in this repo.

• Nw Mikado

  by @nWave-ai

  [EXPERIMENTAL] Complex refactoring roadmaps with visual tracking

• Nw Por Review Criteria

  by @nWave-ai

  Review dimensions and bug patterns for journey artifact reviews

• Nw Canary

  by @nWave-ai

  Canary skill for auto-injection detection

• Llm Council

  by @dair-ai

  Orchestrate multiple open-weight LLMs via Fireworks AI to deliberate on queries. Models respond individually, rank each other's responses, then a Chairman synthesizes the final answer. Use this skill when the user wants multiple…

• Skill Based Architecture

  by @WoJiSama

  This skill should be used when the user asks to "organize the project rules", "clean up scattered documentation", "把规则迁移到 skills 目录", "优化 skill 路由", "提高 description 命中率", or "减少薄壳重复维护". Activate when a SKILL.md is too large,…

• Tooluniverse

  by @ynulihao

  Use this skill when working with scientific research tools and workflows across bioinformatics, cheminformatics, genomics, structural biology, proteomics, and drug discovery. This skill provides access to 600+ scientific tools…

• Transformers

  by @ynulihao

  Work with state-of-the-art machine learning models for NLP, computer vision, audio, and multimodal tasks using HuggingFace Transformers. This skill should be used when fine-tuning pre-trained models, performing inference with…

• Prompt Engineering Patterns

  by @ynulihao

  Master advanced prompt engineering techniques to maximize LLM performance, reliability, and controllability in production. Use when optimizing prompts, improving LLM outputs, or designing production prompt templates.

• Crawl4ai

  by @smallnest

  This skill should be used when users need to scrape websites, extract structured data, handle JavaScript-heavy pages, crawl multiple URLs, or build automated web data pipelines. Includes optimized extraction patterns with schema…

• Burner Phone

  by @smallnest

  Control Android devices via ADB with vision feedback. Use this to see the screen, take screenshots, analyze UI elements, and automate phone tasks.

• Actionbook

  by @smallnest

  This skill should be used when the user needs to automate multi-step website tasks. Activates for browser automation, web scraping, UI testing, or building AI agents. Provides complete action manuals with step-by-step…

• Coding Agent

  by @smallnest

  Run Codex CLI, Claude Code, Kiro CLI, OpenCode, or Pi Coding Agent via background process for programmatic control.

• Feishu Upload Image

  by @smallnest

  Upload images to Feishu/Lark. Returns image_key for use in messages.

• Find Skills

  by @smallnest

  Helps users discover, install, and manage goclaw skills. Use when users ask "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. Provides guidance for finding…

• Weather

  by @smallnest

  This skill should be used when users ask for weather information, current conditions, or forecasts for any location worldwide. Use for queries like "weather in Beijing", "what's the weather today", "temperature in Tokyo",…

• Compose Expert

  by @aldefy

  Compose and Compose Multiplatform expert for UI development across Android, Desktop, iOS, and Web. Use whenever the user mentions Compose APIs (@Composable, remember, LaunchedEffect, NavHost, MaterialTheme, LazyColumn, Modifier,…

• Llm4ad Task Builder

  by @Optima-CityU

  Use when a user wants to build an LLM4AD_Next task package — a runnable directory that lets the LLM4AD platform evolve an algorithm for their problem. Covers what files a task package contains, each file's contract, and how the…

• Document Knowledge Organizer

  by @Optima-CityU

  Organize one or more Markdown source documents into high-fidelity, editable knowledge blocks. Use when an agent must plan a semantic document reorganization, execute that plan without fixed-size chunking, or refine previously…

• Proposal Foundation Layout

  by @Optima-CityU

  Use when establishing a research proposal's project foundation, submission constraints, and presentation system before section drafting begins.

• Dyca

  by @Optima-CityU

  DyCA (Dynamic Clustering Algorithm) method skill. USE WHEN the user explicitly requests DyCA / dynamic clustering adaptive evolution, or wants instance-aware search that clusters problem instances and allocates specialized…

• Island Ga

  by @Optima-CityU

  Island Genetic Algorithm (IslandGA) method skill. USE WHEN the user explicitly requests IslandGA / island genetic algorithm, or wants multiple sub-populations evolving in parallel with periodic inter-island migration to preserve…

• Mcts Ahd

  by @Optima-CityU

  Monte Carlo Tree Search for Automatic Heuristic Design (MCTS-AHD) method skill. USE WHEN the user explicitly requests MCTS / Monte Carlo Tree Search for heuristic design, or wants tree-structured search with UCT-based…

• Moead

  by @Optima-CityU

  MOEA/D (Multi-objective Evolutionary Algorithm based on Decomposition) method skill. USE WHEN the user explicitly requests MOEA/D / Decomposition-based multi-objective evolution, or wants weight-vector decomposition with…

• Diverse Island Ga

  by @Optima-CityU

  Diverse Island Genetic Algorithm skill. USE WHEN the user explicitly requests Diverse Island GA / diversity-oriented island GA, or wants specialized island roles with adaptive migration and novelty preservation instead of a…

• Nsga2

  by @Optima-CityU

  NSGA-II multi-objective evolutionary method skill. USE WHEN the user explicitly requests NSGA-II / Non-dominated Sorting Genetic Algorithm, or wants multi-objective optimization with non-dominated sorting and crowding distance…

• Reevo

  by @Optima-CityU

  Reflective Evolution (ReEvo) method skill. USE WHEN the user explicitly requests ReEvo / Reflective Evolution, or wants evolution with reflection mechanisms that summarize failure lessons and inject them into the next generation.

• Meoh

  by @Optima-CityU

  Multi-objective Evolution of Heuristics (MEoH) method skill. USE WHEN the user explicitly requests MEoH / Multi-objective EoH, or wants Pareto-based population evolution with archive for multi-objective problems.

• Eoh

  by @Optima-CityU

  Evolution of Heuristics (EOH) method skill. USE WHEN the user explicitly requests EoH / Evolution of Heuristics, or wants population-level heuristic evolution with explore-exploit-merge-modify operators.

• Funsearch

  by @Optima-CityU

  FunSearch (Program Search) method skill. USE WHEN the user explicitly requests FunSearch / Program Search, or wants search with a programs database that stores and samples from high-scoring programs.

• Proposal Foundation Feasibility

  by @Optima-CityU

  Use when documenting a proposal's research foundation, available conditions, team support, feasibility, and risk controls from author-supplied facts.

• Proposal Rationale

  by @Optima-CityU

  Use when developing a proposal's research purpose, necessity, significance, application value, and practical problem framing from verified evidence.

• Proposal Methods

  by @Optima-CityU

  Use when translating established proposal objectives into research methods, a technical route, formal definitions, and an evaluation plan.

• Proposal Final Review

  by @Optima-CityU

  Use when assembling a completed staged Typst proposal and checking its evidence, logic, citations, structure, and export readiness.

• Proposal Literature Evidence

  by @Optima-CityU

  Use when researching, organizing, and citing the evidence base for a research proposal after its project foundation is established.

• Proposal Innovation Plan

  by @Optima-CityU

  Use when distilling a proposal's innovations and defining milestones, annual plans, contingency points, and expected outcomes.

• Proposal Objectives

  by @Optima-CityU

  Use when defining a proposal's objective hierarchy, research content, work packages, and key scientific or technical problems.

• Algorithm Discovery

  by @Optima-CityU

  Discover an evolvable algorithm from an uploaded paper, build and validate its complete LLM4AD_Next task package, and publish that exact runnable package for project management.

• Writing Plans

  by @Optima-CityU

  Use before a multi-step document restructuring task to map the source, preserve important relationships, and decide whether child documents are justified.

• Research Stage Publication

  by @Optima-CityU

  Publish the current revision of an LLM4AD research workflow stage, including after a user edits and replaces an earlier conversation turn.

• Rebuttal Baseline

  by @Optima-CityU

  Build and confirm the complete paper, review, constraint, concern, and reviewer-card baseline before rebuttal generation.

• Ac Summary

  by @Optima-CityU

  Summarize an existing author rebuttal into a copy-ready message addressed to the Area Chair or conference chair.

• Autorebuttal

  by @Optima-CityU

  Automatically plan, draft, and compliance-check a complete evidence-grounded rebuttal from a confirmed baseline.

• Pathml

  by @jimmc414

  Computational pathology toolkit for analyzing whole-slide images (WSI) and multiparametric imaging data. Use this skill when working with histopathology slides, H&E stained images, multiplex immunofluorescence (CODEX, Vectra),…

• Runware Api

  by @LayrKits

  Use when making, reviewing, debugging, or scripting Runware API requests. Follow Runware's raw REST/WebSocket request shape, authentication, UUID, async polling, error, retry, and model-selection rules.

• Agent Workflow

  by @sharpdeveye

  Use when any Maestro command is invoked — provides foundational workflow design principles across prompt engineering, context management, tool orchestration, agent architecture, feedback loops, knowledge systems, and guardrails.

• Zero Defect

  by @sharpdeveye

  Use when you need maximum precision on a critical task — production deployments, security-sensitive code, financial calculations, or any work where mistakes are unacceptable.

• Turbocharge

  by @sharpdeveye

  Use when the user wants to push past conventional workflow limits with advanced performance techniques like parallel orchestration, streaming pipelines, or adaptive routing.

• Amplify

  by @sharpdeveye

  Use when the workflow works but needs to handle more complex cases or produce higher-quality output through better tools, context, prompts, or models.

• Temper

  by @sharpdeveye

  Use when the workflow feels over-engineered, has premature optimizations, unnecessary abstraction layers, or complexity beyond actual requirements.

• Specialize

  by @sharpdeveye

  Use when the user wants to tailor a workflow for a specific industry, domain, or vertical with specialized expertise, terminology, and guardrails.

• Guard

  by @sharpdeveye

  Use when deploying to production, handling sensitive data, or the workflow needs safety constraints, input validation, and security boundaries.

• Extract Pattern

  by @sharpdeveye

  Use when the user wants to create templates, extract reusable patterns, document solutions, or build a pattern library from working workflows.

• Fortify

  by @sharpdeveye

  Use when the workflow lacks error handling, has been failing in production, or needs retry logic, fallback strategies, and circuit breakers.

• Calibrate

  by @sharpdeveye

  Use when workflow components are inconsistent, naming conventions vary, or a new team member's work needs alignment to project standards.

• Streamline

  by @sharpdeveye

  Use when the workflow feels too complex, has accumulated cruft, or has redundant steps and overlapping tools that need consolidation.

• Chain

  by @sharpdeveye

  Use when the workflow needs multi-step processing with sequential, parallel, or conditional tool compositions and proper data flow.

• Enrich

  by @sharpdeveye

  Use when the agent needs access to information beyond its training data — knowledge sources, RAG pipelines, or grounding data.

• Onboard Agent

  by @sharpdeveye

  Use when starting a new project, adding a new agent to an existing system, or setting up workflow infrastructure from scratch.

• Diagnose

  by @sharpdeveye

  Use when the user wants to find problems, audit workflow quality, or get a comprehensive health check on their AI workflow.

• Refine

  by @sharpdeveye

  Use when the workflow works but needs polish, or as the final step in a diagnose → fix → refine cycle before shipping.

• Iterate

  by @sharpdeveye

  Use when the workflow needs to self-correct, improve over time, or establish feedback loops and evaluation cycles.

• Teach Maestro

  by @sharpdeveye

  Use when starting a new project with Maestro or when no .maestro.md context file exists yet. Run once per project.

• Evaluate

  by @sharpdeveye

  Use when the user wants a quality review, interaction audit, or to test the workflow against realistic scenarios.

• Accelerate

  by @sharpdeveye

  Use when the workflow is too slow, too expensive, or both and needs latency, cost, or token usage optimization.