LLM Mart Basic

Design Alibaba Cloud solutions — product selection (PolarDB vs RDS, ACK vs ASK vs SAE, MaxCompute vs AnalyticDB), architecture patterns, landing zone design, and disaster recovery strategies aligned to the Alibaba Well-Architected Framework.

Coordinate Alibaba Cloud support incidents — case creation with correct severity (紧急/高/中/低), Enterprise Support SLA enforcement, account manager escalation path, status page monitoring for CN-* and international, internal stakeholder communication, and post-incident evidence pack

Triage Alibaba Cloud operational alerts, incidents, and support tickets — P0/P1/P2/P3 classification, Alibaba Cloud Support SLA enforcement, account manager escalation, DingTalk war room coordination, evidence collection from CloudMonitor and SLS, and safe escalation paths.

Assess Alibaba Cloud cost posture: ECS instance family rightsizing, Savings Plans and Reserved Instance coverage, Preemptible Instance adoption, cost allocation tagging, OSS storage tiering, analytics pricing, and idle resource elimination.

Assess Alibaba Cloud workload reliability: multi-AZ ECS topology, SLB/ALB/NLB load balancing, Auto Scaling health policies, RDS/PolarDB HA failover, backup and cross-region DR, and Cloud Monitor/ARMS observability coverage.

Assess Alibaba Cloud workload security posture: RAM least-privilege, VPC isolation, KMS/HSM encryption, Cloud Security Center threat detection, ActionTrail audit, WAF/Anti-DDoS web protection, and Chinese regulatory compliance (MLPS 2.0, DSL, PIPL).

Use this skill when reviewing Argo Rollouts progressive delivery configuration. Trigger when the user asks about canary or blue-green Rollout strategy correctness, AnalysisTemplate success/failure conditions, traffic weighting provider alignment, canaryService isolation, PDB dead

Use this skill for Argo CD GitOps review across Application, AppProject, ApplicationSet, sync windows, RBAC, sync impersonation, and Argo CD Agent multi-cluster topologies. Trigger when the user asks whether an Argo CD configuration is safe for production, whether automated sync

Build, test, migrate, integrate, and deploy Amazon Bedrock AgentCore agents. Use for AgentCore runtime, local development, import/migration, deployment, Memory, Gateway/MCP tools, Identity, Observability, Browser, Code Interpreter, Evaluations, Registry, Payments, policy, and har

Review AWS API and edge delivery posture across API Gateway, CloudFront, AWS WAF, Shield, ALB, custom domains, TLS policies, authentication, authorization, throttling, quotas, caching, origin protection, logging, and abuse controls. Use when public APIs, web entry points, or edge

Review Amazon Bedrock agents, AgentCore, Guardrails, knowledge bases, action groups, memory, MCP/tool integrations, prompt-injection and prompt-leakage defenses, PII handling, encryption, logging, observability, and least-privilege IAM. Use for AWS-native GenAI and agent security

Assess AWS change impact using change sets, deployment blast radius, rollback readiness, dependency mapping, risk, go/no-go context, approval context, and stakeholder communication. Prefer this for non-destructive pre-change advisory work; prefer IaC or platform-specific skills f

Review AWS CI/CD and release safety across CodePipeline, CodeBuild, CodeDeploy, GitHub Actions, GitLab, artifact provenance, deployment gates, approvals, tests, progressive delivery, rollback, change correlation, and incident-prevention recommendations. Use when AWS releases or p

Map AWS compliance evidence for audits across Security Hub controls, AWS Config rules/conformance packs, Audit Manager assessments, evidence folders, manual evidence, AWS Artifact reports, CloudTrail, and control narratives. Use for evidence packaging and audit readiness, not gen

Review AWS cost anomalies using Cost Explorer, Cost Anomaly Detection, Budgets, usage spikes, commitments, and tagging gaps. Prefer this for proactive FinOps watch and non-destructive escalation; prefer aws-cost-optimization-governor for broader optimization strategy.

Review AWS cost optimization and FinOps posture across Cost Explorer, Budgets, Cost Optimization Hub, Compute Optimizer, Savings Plans, Reserved Instances, tagging, showback, idle resources, rightsizing, storage, data transfer, and forecast risk. Use when the user asks to reduce

Prepare AWS daily operations briefings using CloudWatch, Personal Health Dashboard, Trusted Advisor, cost signals, deployment timelines, incidents, risks, and action backlog. Prefer this for non-destructive business and engineering status coordination; prefer observability, cost,

Review AWS backup and data protection implementation across AWS Backup, EBS/RDS/EFS/S3 recovery patterns, vaults, vault lock, retention, encryption, cross-account/cross-Region copy, restore testing, lifecycle, and recovery evidence. Prefer resilience BCDR review for broader RTO/R

Patch AWS deployment hotfix config, release parameters, manifest mistakes, environment drift, rollback blockers, and rollout blockers in-repo. Use for rapid non-destructive deployment corrections; do not use for live deploy/apply/destroy actions.

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

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.

`crabbox attach` follows the recorded events of an active coordinator run and

`crabbox azure` groups Azure provider setup commands. It currently has a single

`crabbox bench` records and reports local benchmark timing observations. It is a

`crabbox cache` inspects, purges, or warms package and build caches on a

`crabbox capsule` captures, replays, and tracks lightweight failure capsules.

Save the state of a lease, then restore it onto another box or fork it into a

`crabbox claims list` prints the lease claims stored on the current machine. It

`crabbox cleanup` sweeps direct-provider machines and local provider state that

`crabbox code` bridges a Linux lease's `code-server` workspace into the

`crabbox config` inspects and updates user configuration. It has three

`crabbox connect` resolves a lease and opens an interactive SSH session to it.

`crabbox cp` copies files or directories between the host and a Crabbox-owned

`crabbox desktop` drives a visible desktop session on a lease that was warmed

`crabbox doctor` runs a preflight before you commit to a long workflow. It is

`crabbox egress` gives a lease mediated outbound network: a lease-local browser

`crabbox events` prints the broker's event log for a recorded run.

`crabbox heartbeat` refreshes the idle deadline for one owned lease and prints

`crabbox history` lists recorded remote command runs from the broker. Each run is

`crabbox image` holds the trusted-operator controls for provider base images:

`crabbox init` onboards the current repository: it writes the minimal config

Your Personal AI Assistant; easy to install, deploy on your own machine or on the cloud; supports multiple chat apps with easily extensible capabilities.

Agent OS: the agent gets smarter on its own. We just hold the line: the grading command and expected result never make it into the success contract we hand it.…

Curated systems, benchmarks, and papers etc. on memory for LLMs/MLLMs --- long-term context, retrieval, and reasoning.

:memo: Vimlike Modal Text Editor in Rust

CI-native security testing for MCP servers. Attack simulation, schema drift detection, and health scoring before agents depend on them.

Hermes Agent memory plugin/provider for scope-aware recall, SQLite truth, LanceDB semantic search, and hybrid retrieval.

For You Agent——AI 时代的个人随身数字人格。把你的模型、AI 账号、技能、提示词和工作方式，带到每一个 AI 工具里。

A coding agent: give it a prompt and it reads, writes, runs commands, and searches code in a loop until the work is done, using native tool-calling across OpenA…

A secure persistent personal agent server in Rust. One binary, sandboxed execution, multi-provider LLMs, voice, memory, Telegram, WhatsApp, Discord, Teams, and…

Self-evolving agent: grows skill tree from 3.3K-line seed, achieving full system control with 6x less token consumption

DeepSeek Harness Desktop (dsh-desktop). EAC: Embracing All Creation (揽尽万象). Bundled Node.js runtime with full dsh-CLI kernel, one-click startup, 10 built-in UI…

See your agent think. Zero-config observability & governance for 26 AI agent runtimes: Claude Code, Cursor, OpenAI Codex, GitHub Copilot, Gemini CLI, Cline, Ope…

Save 94% on AI coding tokens. Index your codebase, agents search instead of reading files. Works with Claude Code, Codex, Copilot, Cursor, Gemini CLI. Local MCP…

Yet another coding agent harness, lightweight and written in go.

a coding Agent from pi. ∞ providers, sub-agents, hashline edits, and a permission gate

Omnigent is an open-source AI agent framework and meta-harness: orchestrate Claude Code, Codex, Cursor, Pi, and custom agents — swap harnesses without rewriting…

🧠 Leon is your open-source personal assistant.

The Station, an open-world multi-agent environment that models a miniature scientific ecosystem.

The Frontend Stack for Agents & Generative UI. React, Angular, Mobile, Slack, and more. Makers of the AG-UI Protocol

VelaTerm = iTerm2 + Codex, The Best Terminal for AI Coding