LLM Mart Basic

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

Design, review, and troubleshoot AWS network, hybrid, and multi-cloud connectivity across VPCs, Transit Gateway, Direct Connect, VPN, Cloud WAN, Route 53 Resolver, private DNS, CIDRs, route tables, endpoints, segmentation, ingress, egress, inspection, and failover. Prefer this fo

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.

Periodic multi-reviewer sweep of the whole codebase — surfaces a triaged checkpoint report.

Sanctioned lane for non-behavioral work — docs-only edits, dependency bumps, reverts. Type-scaled gates; no TDD demanded of prose.

{{SKILL_ENTRY:post-merge-cleanup}}

Show the codeArbiter command catalog — the public command list and what each routes to.

{{SKILL_ENTRY:commit-gate}}

Stop everything and surface a rule conflict — persona vs. docs vs. code. Present both sides and the conflict-hierarchy level; the user resolves. No silent reconciliation.

{{SKILL_ENTRY:context-check}}

{{SKILL_ENTRY:context-creation}}

{{SKILL_ENTRY:debug}}

{{SKILL_ENTRY:decompose}}

Verify the active host install, package, command ownership, enforcement{{IF:pi}}, wrapper self-test, and active-dispatch coverage gap{{ELSE}}, and harmless live-fire probe{{END}}. Read-only.

Start a feature: brainstorm a spec, get it approved, then drive it test-first through the pipeline. The one entry to implementation.

Fix a confirmed bug: a failing regression test first, then a minimal fix, then the rest of the tdd gates.

Opt this repo into codeArbiter — scaffold the root-level .codearbiter/ state store.

Read-only 3-metric governance glance — override rate, small-lane rate, sprint low-confidence ratio — each with a trend arrow vs. the prior 20-commit window.

Sanctioned, logged bypass of a gate or hard rule — one audit line, then proceed.

{{SKILL_ENTRY:finishing-a-development-branch}}

Zero-onboarding, read-only dry-run of the reviewer fleet against the current uncommitted diff. Predicts reviewers, runs the state-free secret scan, writes nothing.

Trim transcript clutter to extend session lifetime — analyze, prune a copy, or toggle the after-each-turn service. Dry-run by default; gains land at resume/compaction, not the current turn.

{{SKILL_ENTRY:decision-variance}}

AI coding platform for teams

AI Multi-Agent Framework in .NET

Production-ready code examples for Telnyx AI Communications Infrastructure — Voice AI, SMS, SIP, and IoT APIs

UltraGameStudio - AI coding agent for game development: engine workflows, gameplay code, and asset generation.

🦞 ResearchClawBench: Evaluating AI Agents for Automated Research from Re-Discovery to New-Discovery

The context-aware model router that learns & adapts to your long-horizon coding agent workflows. Lightweight & extensible, works with any harnesses, any models,…

Open-source sandboxes where coding agents build and deploy. Spin up isolated environments where Claude Code, Cursor, and other agents code and deploy software.

Native desktop UI for Claude Code with orchestration, streaming, background agents, and multi-provider support. Built with Tauri + React.

OpenCode mobile client via Telegram: run and monitor AI coding tasks from your phone while everything runs locally on your machine. Scheduled tasks support.

Terminal session manager for AI coding agents. One TUI for Claude, Gemini, OpenCode, Codex, and more.

Exposes internet search tools for use by LLM-backed Assist in Home Assistant

Templates and workflow for generating PRDs, Tech Designs, and MVP and more using LLMs for AI IDEs

Versus Incident is the self-hosted AI SRE agent. It learns what your system normally look like and escalates only what is new or unexpected issues — routing to…

Browser-native side panel for Hermes Agent — connect web context to your local Hermes runtime.

Agentic-friendly CLI generator for APIs: turn Swagger, OpenAPI, and google.api.http protos into single-binary CLIs with catalogs and generated Skills.

Open-source agent platform for Global × China enterprises — wire every system through one agent core. Self-hosted, any LLM.

Official python implementation of UTCP. UTCP is an open standard that lets AI agents call any API directly, without extra middleware.

An agent small enough to run anywhere. A minimal agentic runtime in C — ~380 lines, 54KB binary, ~2MB RAM. A skill file + an LLM + a shell loop, no framework.

AgentiLoop Agent! An Autonomous Agentic Agent for Mac, and exclusive Apple only harnesss. Suppprtd automation, scripting, coding, build anything and more. Power…

微信公众号 AI 运营助手 | 选题、写稿、审稿、排版、配图、发布全流程 Skill，支持 OpenClaw / Claude Code / Cursor / Codex