Latest Agent Skills

Autonomous experiment loop that optimizes any file by a measurable metric. Inspired by Karpathy's autoresearch. The agent edits a target file, runs a fixed evaluation, keeps improvements (git commit), discards failures (git reset), and loops indefinitely. Use when: user wants to optimize code speed, reduce bundle/image size, improve test pass rate, optimize prompts, improve content quality (headlines, copy, CTR), or run any measurable improvement loop. Requires: a target file, an evaluation command that outputs a metric, and a git repo.

Scan codebases for technical debt, score severity, track trends, and generate prioritized remediation plans. Use when users mention tech debt, code quality, refactoring priority, debt scoring, cleanup sprints, or code health assessment. Also use for legacy code modernization planning and maintenance cost estimation.

Runbook Generator

Use when the user asks to design database schemas, plan data migrations, optimize queries, choose between SQL and NoSQL, or model data relationships.

Use when the user asks to review pull requests, analyze code changes, check for security issues in PRs, or assess code quality of diffs.

Use when the user asks to plan releases, manage changelogs, coordinate deployments, create release branches, or automate versioning.

Use when the user asks to design multi-agent systems, create agent architectures, define agent communication patterns, or build autonomous agent workflows.

Use when the user asks to design RAG pipelines, optimize retrieval strategies, choose embedding models, implement vector search, or build knowledge retrieval systems.

Skill Tester

Use when the user asks to fix, debug, or make a specific feature/module/area work end-to-end. Triggers: 'make X work', 'fix the Y feature', 'the Z module is broken', 'focus on [area]'. Not for quick single-bug fixes — this is for systematic deep-dive repair across all files and dependencies.

Multi-agent collaboration plugin that spawns N parallel subagents competing on the same task via git worktree isolation. Agents work independently, results are evaluated by metric or LLM judge, and the best branch is merged. Use when: user wants multiple approaches tried in parallel — code optimization, content variation, research exploration, or any task that benefits from parallel competition. Requires: a git repo.

Use when the user wants to inspect or drive the local OpenClaw desktop wrapper, NemoClaw route, Ollama models, or Mermate pipeline from Claude Code.

自动捕获经验并安全进化的技能。触发条件：(1)命令/操作失败时→记ERRORS.md (2)被用户纠正('不对'/'应该是')时→记LEARNINGS.md (3)用户需要不存在的能力时→记FEATURE_REQUESTS.md (4)外部API/工具出错时→记ERRORS.md (5)发现自己知识过时/错误时→记LEARNINGS.md (6)发现更好做法时→记LEARNINGS.md (7)每个任务完成时→回顾过程，有新经验则记LEARNINGS.md。去重原则：如果没有新经验或已有条目已覆盖则跳过不写。每次写入同时在.learnings/CHANGELOG.md追加JSONL日志。经验反复出现≥3次时晋升到AGENTS.md/TOOLS.md/SOUL.md。详见正文。

Explore a codebase to find opportunities for architectural improvement, focusing on making the codebase more testable by deepening shallow modules. Use when user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make a codebase more AI-navigable.

25 advanced engineering agent skills and plugins for Claude Code, Codex, Gemini CLI, Cursor, OpenClaw. Agent design, RAG, MCP servers, CI/CD, database design, observability, security auditing, release management, platform ops.

Master TypeScript's advanced type system including generics, conditional types, mapped types, template literals, and utility types for building type-safe applications. Use when implementing complex type logic, creating reusable type utilities, or ensuring compile-time type safety in TypeScript projects.

Patterns for OrbStack Linux VMs and Docker on macOS. Covers orbctl/orb commands, machine lifecycle, cloud-init, networking, file sharing, and SSH access. Must use when working with OrbStack, orbctl commands, or Linux VMs on macOS.

Configure secure, high-performance connectivity between on-premises infrastructure and cloud platforms using VPN and dedicated connections. Use when building hybrid cloud architectures, connecting data centers to cloud, or implementing secure cross-premises networking.

Python design patterns including KISS, Separation of Concerns, Single Responsibility, and composition over inheritance. Use when making architecture decisions, refactoring code structure, or evaluating when abstractions are appropriate.

Organize messy laptop folders like Desktop, Downloads, and Documents into smart categories. Scans your folders, groups files by purpose and content, and creates a clean structure with dynamic depth based on how many files you have. Works on macOS, Windows, and Linux. Always asks before moving anything.

Expert code review of current git changes with a senior engineer lens. Detects SOLID violations, security risks, and proposes actionable improvements.

A self-evolution engine for AI agents. Analyzes runtime history to identify improvements and applies protocol-constrained evolution.

TypeScript and JavaScript expert with deep knowledge of type-level programming, performance optimization, monorepo management, migration strategies, and modern tooling.

Expert-level PostgreSQL database administration, advanced queries, performance tuning, and production operations

Backend architecture patterns, API design, database optimization, and server-side best practices for Node.js, Express, and Next.js API routes.

Socratic coach for breaking down problems to fundamental truths. Use when users want to think through a problem deeply, challenge assumptions, or find innovative solutions. Triggers on requests like "help me think through this", "let's break this down", "what are my blind spots", "I'm stuck on a problem", "challenge my assumptions", or explicit requests for first-principles thinking.

NVIDIA NemoClaw plugin for secure sandboxed installation and orchestration of OpenClaw always-on AI assistants via OpenShell

Use when creating new skills, editing existing skills, or verifying skills work before deployment

English LaTeX academic paper assistant for existing `.tex` projects. Use this skill whenever the user wants to compile, lint, audit, or improve an English LaTeX conference or journal paper such as IEEE, ACM, Springer, NeurIPS, or ICML submissions. Trigger even when the user only mentions one paper issue, such as bibliography errors, grammar cleanup, sentence splitting, logic review, expression polishing, translation, title optimization, figure checks, pseudocode review, algorithm block cleanup, de-AI editing, or experiment-section review. Also trigger for "proofread my paper", "fix my LaTeX", "prepare for submission", "check my manuscript", "improve my writing", `algorithm2e`, `algorithmicx`, `algpseudocodex`, `Require/Ensure`, or "Algorithm 1" when the user has a .tex file.

UI/UX design intelligence for web and mobile. Includes 50+ styles, 161 color palettes, 57 font pairings, 161 product types, 99 UX guidelines, and 25 chart types across 10 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui, and HTML/CSS). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, and check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, and mobile app. Elements: button, modal, navbar, sidebar, card, table, form, and chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, and flat design. Topics: color systems, accessibility, animation, layout, typography, font pairing, spacing, interaction states, shadow, and gradient. Integrations: shadcn/ui MCP for component search and examples.

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

Rust specialist with expertise in async programming, ownership patterns, FFI, and WebAssembly development

Guides and best practices for working with Neon Serverless Postgres. Covers getting started, local development with Neon, choosing a connection method, Neon features, authentication (@neondatabase/auth), PostgREST-style data API (@neondatabase/neon-js), Neon CLI, and Neon's Platform API/SDKs. Use for any Neon-related questions.

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.

Comprehensive cryptography guidance covering encryption algorithms, password hashing, TLS configuration, key management, and post-quantum considerations. Use when implementing encryption, choosing hashing algorithms, configuring TLS/SSL, managing cryptographic keys, or reviewing cryptographic implementations.

Guide for quality focused software architecture. This skill should be used when users want to write code, design architecture, analyze code, in any case that relates to software development.

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.

Use when the user wants to build, extend, or debug the Python MCP bridge that exposes Mermate actions and stage flows to OpenClaw or other MCP clients.

Python SDK for inference.sh - run AI apps, build agents, and integrate with 150+ models. Package: inferencesh (pip install inferencesh). Supports sync/async, streaming, file uploads. Build agents with template or ad-hoc patterns, tool builder API, skills, and human approval. Use for: Python integration, AI apps, agent development, RAG pipelines, automation. Triggers: python sdk, inferencesh, pip install, python api, python client, async inference, python agent, tool builder python, programmatic ai, python integration, sdk python

Master Rust 1.75+ with modern async patterns, advanced type system features, and production-ready systems programming.

Comprehensive guide for creating software diagrams using Mermaid syntax. Use when users need to create, visualize, or document software through diagrams including class diagrams (domain modeling, object-oriented design), sequence diagrams (application flows, API interactions, code execution), flowcharts (processes, algorithms, user journeys), entity relationship diagrams (database schemas), C4 architecture diagrams (system context, containers, components), state diagrams, git graphs, pie charts, gantt charts, or any other diagram type. Triggers include requests to "diagram", "visualize", "model", "map out", "show the flow", or when explaining system architecture, database design, code structure, or user/application flows.

Generate architecture documentation using C4 model Mermaid diagrams. Use when asked to create architecture diagrams, document system architecture, visualize software structure, create C4 diagrams, or generate context/container/component/deployment diagrams. Triggers include "architecture diagram", "C4 diagram", "system context", "container diagram", "component diagram", "deployment diagram", "document architecture", "visualize architecture".

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

Generate a persistent .nexus-map/ knowledge base that lets any AI session instantly understand a codebase's architecture, systems, dependencies, and change hotspots. Use when starting work on an unfamiliar repository, onboarding with AI-assisted context, preparing for a major refactoring initiative, or enabling reliable cold-start AI sessions across a team. Produces INDEX.md, systems.md, concept_model.json, git_forensics.md and more. Requires shell execution and Python 3.10+. For ad-hoc file queries or instant impact analysis during active development, use nexus-query instead.

Write Architectural Decision Records following MADR template. Applies Definition of Done criteria, marks gaps for later completion. Use when generating ADR documents from extracted decisions.

autonomous architecture design and refinement for mermate using iterative copilot guidance, local reasoning, repeated low-cost render validation, and final max-quality render selection. use when building, stress-testing, refining, decomposing, validating, or evolving system architectures from simple ideas, complex problem statements, markdown specifications, mermaid drafts, or ambiguous design notes. especially useful when chatgpt should act like a professional architect that thinks step by step, uses mermate repeatedly, compares intermediate diagrams, and decides when to continue refining versus when to finalize with max mode.

OODA loop decision framework (Observe, Orient, Decide, Act). Use for complex decisions, problem-solving, unclear situations, or when someone is jumping to solutions without analysis.

Find deepening opportunities in a codebase, informed by the domain language in CONTEXT.md and the decisions in docs/adr/. Use when the user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make a codebase more testable and AI-navigable.

Grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) inline as decisions crystallise. Use when user wants to stress-test a plan against their project's language and documented decisions.

Tell the agent to zoom out and give broader context or a higher-level perspective. Use when you're unfamiliar with a section of code or need to understand how it fits into the bigger picture.

Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".

Disciplined diagnosis loop for hard bugs and performance regressions. Reproduce → minimise → hypothesise → instrument → fix → regression-test. Use when user says "diagnose this" / "debug this", reports a bug, says something is broken/throwing/failing, or describes a performance regression.

Ultra-compressed communication mode. Cuts token usage ~75% by dropping filler, articles, and pleasantries while keeping full technical accuracy. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman.

Test-driven development with red-green-refactor loop. Use when user wants to build features or fix bugs using TDD, mentions "red-green-refactor", wants integration tests, or asks for test-first development.

Create Request for Information templates for construction. TRIGGERS - Use when user needs help with rfi-template related tasks.

Create release plans with scope and deployment strategy. TRIGGERS - Use when user needs help with release-plan related tasks.

Design reading plans with retention strategies. TRIGGERS - Use when user needs help with reading-plan related tasks.

Build quizzes with question types and scoring. TRIGGERS - Use when user needs help with quiz-builder related tasks.

Design pulse surveys for rapid employee feedback. TRIGGERS - Use when user needs help with pulse-survey related tasks.

Write policy briefs with analysis and recommendations. TRIGGERS - Use when user needs help with policy-brief related tasks.