LLM Mart Basic

Review Alibaba Cloud workload HA and BCDR designs — RDS High-Availability Edition failover, PolarDB Global Database Network, ACK multi-zone, ECS disaster recovery cross-region, RTO/RPO target analysis, and HBR (Hybrid Backup Recovery) coverage.

Harden Alibaba Cloud security posture via Security Center (threat detection, vulnerability scanning, baseline checks), WAF, Anti-DDoS Pro, Cloud Firewall, and Network Traffic Analysis (NTA).

Review Function Compute 3.0 (FC3), SAE (Serverless App Engine), and EDAS for production readiness — cold start optimization, VPC binding, RAM role injection, ARMS distributed tracing, security group rules, concurrency limits, and SLA-readiness.

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,

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.

Run autonomous hunt loop on a target — scope check → recon → rank surface → hunt → validate → report with configurable checkpoints. Usage: /autopilot target.com [--paranoid|--normal|--yolo]

Build an exploit chain — given bug A, finds B and C to combine for higher severity and payout. Knows common chain patterns: IDOR→ATO, SSRF→cloud metadata, XSS→ATO, open redirect→OAuth theft, S3→bundle→secret→OAuth. Usage: /chain

Active vulnerability hunting. Two-track dispatcher — asks Red Team vs WAPT, hands off to hunt-dispatch skill and sibling commands. Usage: /hunt target.com | /hunt *.target.com | /hunt targets.txt [--vuln-class X] [--source-code P] [--chrome]

On-demand intelligence fetch for a target — CVEs, disclosed reports, new features. Pulls NVD/GitHub-Advisory CVEs + bundled disclosed reports + hunt memory context. Usage: /intel target.com

Inspect or rotate the autopilot ledger JSONL files (findings.jsonl, negatives.jsonl). Caps file size and keeps N rotated backups so memory does not grow unbounded.

Pick up a previous hunt on a target — shows hunt history and untested surface from the autopilot ledger. Usage: /pickup target.com

Run full recon pipeline on a target — subdomain enum (Chaos API + subfinder), live host discovery (dnsx + httpx), URL crawl (katana + waybackurls + gau), gf pattern classification, nuclei scan. Outputs to recon/<target>/ directory. Usage: /recon target.com

Optional manual note on a target or the last confirmed finding. Capture is automatic during autopilot; this is for extra context. Usage: /remember

Write a submission-ready bug bounty report. Generates H1/Bugcrowd/Intigriti/Immunefi format with CVSS 3.1 score, proof of concept, impact statement, and remediation. Run /validate first. Usage: /report

Mandatory pre-flight scope check — verify an asset is in scope BEFORE any HTTP touch. Deterministic (deny-wins, default-deny) via engine/scope.py against the engagement's scope.md. Blocks out-of-scope testing. Usage: /scope <asset> [<asset> ...]

Show ranked attack surface for a target from its recon manifest + hunt memory. Deterministic backing is `cbh surface <target>` (reads recon/<target>/manifest.json); LLM layer adds ledger signal. Usage: /surface target.com

Meme coin and token security scan — checks for rug pull vectors (hidden mint, honeypot, fee manipulation, LP lock bypass, authority retention, bonding curve exploits, fake renounce, sandwich amplification). Manual 8-class grep audit (with an optional automated scanner if present). Usage: /token-scan <contract_path_or_dir> [--chain solana]

Quick 7-Question Gate triage on a finding before writing a report. Kills N/A submissions before they happen. Faster than /validate — for quick go/no-go decisions. Usage: /triage

Validate a finding — runs 7-Question Gate + 4-gate checklist. Kills weak findings before report writing. Prevents N/A submissions that hurt validity ratio. Usage: /validate

Smart contract security audit — runs through 10 bug class checklist (accounting desync, access control, incomplete path, off-by-one, oracle errors, ERC4626, reentrancy, flash loan, signature replay, proxy/upgrade). Applies pre-dive kill signals first. Generates Foundry PoC template for confirmed findings. Usage: /web3-audit <contract.sol>

Crabbox is a single CLI (`crabbox`). Commands are top-level, not nested under a

`crabbox actions` prepares a leased box from your repository's own GitHub

See [Runtime adapter stack](../features/runtime-adapter-stack.md) for the

`crabbox admin` groups trusted operator controls for coordinator-backed leases and the cloud resources behind them. Use it to inspect every lease the broker tracks, reconcile expired leases against live cloud state, force-release or delete a backing server, print provider IAM pol

`crabbox artifacts` turns a desktop lease into durable QA evidence: it collects

Open-source super AI assistant & Agent Harness. Plans tasks, runs tools and skills, self-evolves with memory and knowledge. Multi-model, multi-channel. Lightwei…

Open-source AI browser agent for web automation: a web browsing agent and computer-use agent in plain English. Browser MCP for Claude Code and Gemini CLI.

Agent-native trading terminal built on DeepSeek Harness. Crypto, US, CN and HK in one three-column GUI, 19+ hot-swappable connectors, dry-run by default with hu…

Open-source desktop and web coding agent with a first-party host and harness, durable sessions, model connections, streaming chat, and workspace tools.

OrcaReplay — Time travel for AI agents. Record, replay, fork, and debug any agent run with any model. Built by the OrcaRouter.ai team.

A complete toolkit for connecting R and LLMs

OpenSRE — the memory-first AI SRE. Self-hosted incident investigation with episodic memory, knowledge graph, web console, Slack & Teams. opensre.in

A desktop AI coding assistant that works with your local projects. Ally helps you understand code, edit files, search a workspace, manage tasks, and complete de…

【在线免费使用】 简单快速将SQL或DBML转换为美观的ER图（支持 Agent Skill）/ The best SQL to ER Diagram converter (Support Agent Skill).

Operation-bound protection for autonomous AI agents: contain and verify operations before committing changes, understand intent and risk across long-running wor…

Local-first AI coding agent desktop: Electron + Rust host core + pi Agent Harness + user-installable plugins

Local-only Go static analysis engine with a built-in MCP server. Gives AI coding agents deterministic structural awareness: call graphs, impact analysis, symbol…

Self-hosted AI agent workspace with tool calling, MCP, multi-model routing, sandboxed execution, multi-agent workflows, and LLM-authored 3D character animation…

Automated TDD enforcement for Claude Code

High-performance platform for building websites, e-commerce, and web applications—with Native AI, JavaScript development, and a marketplace for portable sites a…

Autonomous AI-agent orchestration engine for job discovery with decision traces, tool adapters, and production-grade run control.

Token efficient Claude Code full Python rebuild. AI Coding Agent in 310K LoC Python.

OPC — One Person Company. A full team in a single Claude Code skill. Adaptive agent orchestrator with 21 built-in roles, 6 flow templates, and adversarial quali…

Open-source, secure environment with real-world tools for enterprise-grade agents.

MCP server for AI-powered GitHub project management — agent orchestration, PRD-to-issues pipeline, sprint planning, and multi-agent swarm coordination