LLM Mart Basic

Design, review, and improve AWS DevOps Agent-compatible skills, investigation workflows, learned skills, tool-use best practices, agent type targeting, frontmatter descriptions, reference materials, and operational output contracts. Use when creating or adapting skills for AWS De

Review Amazon DynamoDB data modeling and performance across access patterns, partition keys, sort keys, secondary indexes, GSI/LSI design, hot partitions, query versus scan behavior, capacity mode, adaptive capacity, global tables, TTL, DAX, item size, transactions, and cost. Use

Review Amazon EC2 compute operations across instances, Auto Scaling groups, Launch Templates, AMIs, Systems Manager, Patch Manager, Session Manager, EBS volumes, snapshots, health checks, instance refresh, lifecycle hooks, patch compliance, and fleet reliability. Use for EC2 day-

Review Amazon ECS and Fargate platform operations across services, task definitions, task roles, execution roles, capacity providers, load balancers, deployment circuit breakers, blue/green, autoscaling, health checks, logs, secrets, networking, and rollback. Use only for ECS/Far

Correct AWS ECS and Fargate service definitions, task definition config, deployment parameters, health checks, environment settings, and rollout wiring in-repo. Use for non-destructive repo fixes only; do not force deployments or mutate live services from this role.

Review Amazon EKS Kubernetes platform operations across cluster access, IRSA, IAM roles for service accounts, pod identity, node groups, Karpenter, autoscaling, CNI/network policy, upgrades, reliability, observability, and cost. Use only for EKS/Kubernetes; prefer ECS/Fargate ope

Review AWS event-driven system design across EventBridge, event buses, Pipes, SQS, SNS, Step Functions, event schemas, filtering, cross-account routing, retries, DLQs, replay, idempotency, monitoring, and event-loop risk. Prefer serverless production readiness for Lambda runtime/

Build Amazon Bedrock and serverless generative AI applications using Lambda, API Gateway, Step Functions, EventBridge, S3, DynamoDB, SQS, Guardrails, and IAM. Prefer this for serverless GenAI app design and implementation; prefer aws-agentcore for AgentCore runtime, aws-bedrock-a

Review AWS infrastructure-as-code changes across CDK, CloudFormation, SAM, Terraform, Serverless Framework, generated templates, plans, stack updates, change sets, and drift. Use when the user asks whether an AWS IaC deployment is safe, what a change set will do, why a resource r

Edit AWS IaC files including CloudFormation, SAM, CDK config, and Terraform to patch defects, prepare change set review, or unblock rollout work. Prefer this for bounded repo changes only; do not use for apply, deploy, or destructive infrastructure execution.

Review AWS IAM identity policies, trust policies, resource policies, permission boundaries, SCPs, session policies, role design, pass-role, federation, and Access Analyzer findings for least-privilege risk. Prefer KMS/secrets steward for key/secret lifecycle design and S3 perimet

Review AWS KMS and Secrets Manager lifecycle posture across key policies, grants, rotation, multi-Region keys, imported key material, aliases, secret rotation, replication, caching, endpoint conditions, recovery, and break-glass access. Prefer this for cryptography/secret lifecyc

Review and design AWS landing zones, AWS Control Tower environments, Organizations structures, OUs, account vending patterns, guardrails, central logging, security/audit accounts, and multi-account governance. Use when the user asks how to structure AWS accounts or govern a cloud

Operate guarded live AWS deployment changes with explicit account, region, profile, approval, dry-run, rollback, and verification gates. Use only when the target environment is confirmed and a live deployment action is intentionally requested.

Guard live Amazon ECS and Fargate rollout actions with ecs service, task definition, deployment circuit breaker, alarms, rollback, health check, and approval gates. Use only for intentional live ECS rollout actions against confirmed targets.

Guard live CloudFormation, SAM, CDK, and Terraform-backed AWS infrastructure changes with change set, drift, stack policy, rollback trigger, approval, and execute gates. Use only for intentional live IaC execution with confirmed targets.

Handle live CodePipeline approval and gated resume decisions with pipeline, stage, approver, SNS, approval, blast radius, and rollback checks. Use only when a real pipeline execution is paused or about to be approved.

Guard live Lambda and serverless release actions with lambda alias, codedeploy, canary, linear, alarms, rollback, and approval gates. Use only for intentional live serverless rollout actions against confirmed targets.

Route AWS tasks to the narrowest specialist or team of specialists from the 42-agent catalog. Use when you do not already know the specialist. Not for direct AWS answers; Maestro classifies, dispatches, and synthesizes only. Dispatches single agent for focused tasks, parallel tea

Plan, review, and de-risk AWS migrations and cutovers across discovery, dependency mapping, wave planning, AWS Application Migration Service, Migration Hub, test launches, acceptance tests, downtime windows, rollback, DNS, data consistency, and post-cutover validation. Use for mi

Fourteen posts of being wrong in production, compressed to checkboxes

Healthy nodes, a quiet network, 300 restarts in three days, and a latency budget measured in milliseconds

Discovery worked. Ping worked. Every TCP connection timed out, and later the tunnel only worked when someone had a terminal open.

Every VM came back. The cluster did not. Declarative systems converge on config, and the datapath isn't config.

A surprising share of AI-in-the-terminal failures aren't the AI. They're zsh, and a version of bash from 2006.

A Claude Code plugin turns standalone project configuration into a namespaced, installable extension that teams and communities can update as one unit.

None of the safety came from the model. It came from six boring habits.

Skills package instructions and references. Subagents run work in a separate context and return results. They solve different problems and can be composed deliberately.

Six hours in, one step left, everything green, and the incident that didn't happen

CLAUDE.md carries persistent project context. Skills load reusable procedures when relevant. Separating stable facts from task-specific workflows keeps both easier to maintain.

Twenty minutes recovering secrets that never existed, and the one sentence from a human that ended it

An API request routing a model's tool call through an approval gate to a remote MCP server

31 config keys, two audits, and why the first one was wrong in both directions

The official MCP Registry stores standardized server metadata rather than package code. Publishers verify a namespace, describe installation or remote access, and submit immutable versions.

Everyone looks at the Dockerfile. The file that actually leaked the key was the project file.

Remote MCP authorization uses established OAuth standards, but secure integration still requires issuer validation, least-privilege scopes, protected token handling, and server-side enforcement.

"Copy it over and switch the reference" is two steps, and the outage lives in the one nobody checks

stdio fits local processes and prototypes. Streamable HTTP fits hosted services and shared integrations. The right choice follows where the capability runs and who must reach it.

The most important rule wasn't about what I could change. It was about what I was allowed to display.

Tools perform operations, resources expose readable context, and prompts provide reusable templates. Choosing the correct primitive makes an MCP server easier to understand and govern.

Analyze Python async code for correctness, patterns, and potential issues.

Profile Python code for performance bottlenecks using cProfile, memory_profiler, or py-spy.

Evaluate public API surfaces against guidelines and exemplars.

Principal-level architecture assessment against ADRs and design patterns.

Systematic bug detection with language-specific expertise.

Run a detailed review that picks its dimensions from what the codebase and diff contain.

Active security hardening of the existing codebase, with a report and concrete proposals to apply.

Audit Makefiles for best practices and portability.

Intensive mathematical analysis for numerical stability and correctness.

Static-analysis hot-spot review for time and space complexity.

Analyze code quality across 6 dimensions (duplication, algorithms, clean code, architecture, errors, style) and apply fixes.

Expert-level Rust audits for safety and correctness.

Audit shell scripts for correctness, safety, and portability.

View recent skill executions with full context and error details.

Analyze skill execution metrics and identify unstable or underperforming skills.

Evaluate and upgrade test suites with TDD/BDD rigor.

Run a computer use task on the desktop via Claude's vision and action API

Stage changes, generate conventional commit message, commit, and push to current branch. One-shot git add-commit-push.

Draft a Conventional Commit message for staged changes. Analyzes diffs, classifies change type, and formats scope/body.

Create git release tags from merged PRs or version args. Pushes a v-prefixed tag to trigger the release pipeline, then confirms the run started.

Claude Code skills for Chinese-narration recaps from supported video files, with optional editable JianYing/CapCut draft export. | 用 Claude Code skills 为支持的视频文件…

Drive the Unity Editor from an AI agent or the terminal. The Editor serves MCP itself over HTTP, so there is no second process to run, and the isuzu-unity-cli c…

面向企业的数字员工构建与运行平台：把专业员工的经验、流程与判断标准，固化为可随时上岗、可配置、可审批、可观测的 AI 数字员工。

A local-first, Pi-powered AI agent workspace for Desktop, WebUI, and CLI

660+ muapi-hosted generative-media models plus community-submitted third-party API tools (SEO, enrichment, social, scraping) — one YAML file per entry, browsabl…

A compounding agent OS for recursive agents. Also an open source alternative to Grok Bot and Meta's Muse.

Independent desktop client for OpenCode 2. Manage projects, sessions, parallel agents, requests, and changes on Linux and macOS.

Production agent skills for Claude Code, Cursor, and any SKILL.md harness — Codex fleets, video pipeline, monorepo review bundles, multi-chain explorer.

See and manage what your coding assistants load — skills, commands, subagents, plugins and MCP servers, with real usage.

An Enterprise-Grade Full-Stack RBAC Permission Management System Built with Go + React

Create AI Agents in a No-Code Visual Builder or TypeScript SDK with full 2-way sync. For shipping AI assistants and multi-agent AI workflows.

基于 DeepSeek Harness（DSH）的稳定桌面端，集成Git、内置浏览器与记忆功能 | DeepSeek Harness desktop GUI with local workspaces, Git, browser and memory.

⚡ Control Apache Airflow with natural language via MCP. Chat with your workflows using Claude, GPT, or any LLM — no REST API calls needed. Supports Airflow 2.x…

Open-source CLI, schemas, resolver, and DSH agent tools for DSH Plugin Hub

Pi Coding Agent 中文学习蓝皮书：从安装与第一个可验收任务开始，逐步掌握 Session、Context、Skill、Extension、Subagent 与长期 Agent 工作流。

Self-hosted framework for orchestrating fleets of specialist AI agents — ensemble reasoning and a full agentic coding pipeline, model-agnostic and local-friendl…

Self-hosted, vendor-neutral control plane for your local coding agents (Claude Code & Codex). Run your agents, on any plane.

A practical AI agents handbook covering agent systems, agentic workflows, LangGraph, MCP/A2A, context engineering, agent memory, evaluation, observability, and…

Vibe Coding 从入门到精通教程｜AI 结对编程工作流｜Prompt、Skill、Workflow、上下文管理、codex实战指南

Static security scanner for LLM agents — prompt injection, MCP config auditing, taint analysis. 51 rules mapped to OWASP Agentic Top 10 (2026). Works with LangC…