LLM Mart Basic

Design and review Azure platform automation and DevOps delivery for landing zones, shared platform services, and safe infrastructure rollout flows. Use for IaC approach selection, Bicep versus Terraform positioning, bootstrap/run phase separation, pipeline control design, secret-

Use this skill for Azure Private Link and private endpoint adoption planning, including hub-versus-spoke placement, private DNS zone linkage, route implications, centralized versus workload-local endpoint trade-offs, and safe rollout validation.

Use this skill for Azure RBAC, Entra-backed access, role assignment, custom role, scope, subscription, management group, or least-privilege review tasks. Trigger when the user asks whether Azure access is too broad or how to grant access safely.

Use this skill for Azure resilience, business continuity, and disaster recovery reviews covering RTO/RPO realism, failover and failback assumptions, shared-responsibility gaps, and recovery runbook or drill quality.

Use this skill for Azure Resource Health, Service Health, activity-log alert, and first-pass incident triage when the question is whether Azure platform health is part of the problem.

Use this skill when the user asks which Azure role to assign, how to grant minimum access, whether a built-in role is sufficient, or when a custom role may be required.

Use this skill for Azure security posture review, baseline hardening, managed identity adoption, Key Vault posture, private access decisions, Azure Policy guardrails, and logging or audit gap analysis. Trigger when the user asks how to harden an Azure workload or platform without

Use this skill for Azure management-group hierarchy, subscription placement, resource-group boundary, and platform-versus-workload ownership decisions that affect governance, operations, and landing-zone scale.

Review Azure workload cost posture against the Well-Architected Framework Cost Optimization pillar: cost modeling, rightsizing, reservations, hybrid benefit, storage lifecycle, and idle resource elimination.

Review Azure workload reliability against the Well-Architected Framework Reliability pillar: availability targets, AZ/region topology, health monitoring, data resilience, deployment safety, and chaos testing.

Review Azure workload security posture against the Well-Architected Framework Security pillar: identity and access, segmentation, data protection, threat detection, secure development lifecycle, incident response, and policy compliance.

Use this skill when reviewing Backstage Scaffolder software templates. Trigger when the user asks whether a template is safe for developer self-service, whether template RBAC gates are in place, whether input parameters are validated, whether a step action has excessive blast rad

Use this skill for Cilium network policy review across the three policy formats (Kubernetes NetworkPolicy, CiliumNetworkPolicy, CiliumClusterwideNetworkPolicy), L7 policy via embedded Envoy, ClusterMesh cross-cluster semantics, Hubble flow observability, and CiliumEgressGatewayPo

用于对小说作者做"自我进化"蒸馏：①手动 / 周期回访（挖创作判断、捕获叙述原声（A 类）与创作判断原声（B 类）、周期蒸馏回填"作者小说风格画像"（十层）并反向净化防 AI 自创）；②全流程嵌入（选题构思 / 竞品 / 大纲 / 人物 / 背景 / 章节创作等全部环节自动调用，低频环节必采 1–2 问、高频草稿环节只读消费画像）；③散落触点（改稿痕迹 / 审阅回流 / 作者窗口 / 口述转写原声）；④像不像审计（原声句占比 / 惯用语命中 / 立场显影溯源 / 风格漂移，脚本取数）。与 通用-蒸馏作者文风 组成"静态种子 + 动态进化"双闭环，让写出来

用于围绕起点中文网或其他目标平台的同题材 TopN 候选池，按“市场数据层→内容创作层→运营策略层→受众反馈层”的四层框架锁定 3–5 本核心强样本并逐本深搜式竞对分析；若用户明确要求，也可对 TopN 全量逐本落盘。适合搜索榜单、筛选强样本、阅读目录/公开正文/设定/书评/读者评论/读后感/拆解材料，并在 `竞对分析/` 中为每部作品分别写出可举证、可横比、可回用于当前项目的详细竞对分析报告。关键词：竞对分析、竞品分析、标杆作品拆解、TopN 榜单、同题材对标、榜单深搜、四层拆解、读者评论分析、单书竞对报告。

用于创建连载小说章节正文、作者有话说与章节后记。适合新写单章、重写章节、扩写草稿、直接写回章节文件与完整跑通正文落稿工作流；其中 `## 作者有话说` 默认按读者向小剧场处理，不写成章节点评或创作总结。关键词：写章节正文、重写这章、扩写正文、作者有话说、章节后记、直接写回文件。

用于对章节正文做去 AI 味重写。适合主编式多轮去味、先诊断再定强度、整章去模板腔、局部拆解释腔、打散均匀句群、保信息重写与人物声音去同腔化。关键词：去AI味、主编式去味、多轮改稿、模板腔、解释腔、均匀句群、太像AI、重写这段。

用于做章节或片段的多平台适配策略。适合平台分发前的策略设计、改写前推演与平台撞车修复。关键词：多平台适配、平台差异矩阵、改写前推演、平台撞车修复、平台风格拉开。

用于对单章或多章执行多平台输出全流程编排。适合多平台输出 SOP、批量平台分发、断点恢复、门禁回炉与最终摘要收口。关键词：多平台输出编排、平台分发、断点恢复、门禁回炉、平台日志、最终摘要、今日头条。

用于对指定提纲执行"审阅→修改→复审"的闭环，直到双轴评分（技法分 ≥ 6.0 / 留存分 ≥ 5.0）加权的综合评分连续两轮独立审阅在保留两位小数后均严格大于 9.20。适合大纲审阅优化 SOP、报告复用、回炉循环、评分门槛控制与最终回执收口。关键词：大纲审阅闭环、回炉到 9.20 以上、双轴评分、复审循环、主报告覆盖、提纲优化 SOP。

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

Conduit — native SwiftUI iOS client for Hermes Agent

一个现代化的可视化规则引擎平台，用于编排复杂的 AI 工作流。在无限画布上设计、测试和部署 AI 流程——无需编写代码。结合 flowgram.ai 的能力与 Java 服务端，提供生产级工作流管理。在此之上提供AI Agent / Copilot的助手编排能力。

Job application tracker and AI-powered job search assistant. Helps job seekers manage their search journey with AI resume review, job matching, task logging, an…

📝 Markdown and HTML renderer for Svelte 5 — built for streaming AI agent output from Claude Code, ChatGPT, and agentic workflows. XSS-safe defaults, token cach…

ServiceNow MCP server: 500+ tools and 26 AI capabilities for any AI (Claude, ChatGPT, Gemini, Cursor, Copilot). Multi-transport (stdio, SSE, HTTP), A2A, dynamic…

Free crypto news API - real-time aggregator for Bitcoin, Ethereum, DeFi, Solana & altcoins. No API key required. RSS/Atom feeds, JSON REST API, historical archi…

Build production-ready AI agents in both Python and Typescript.

From agent user to agent builder: build a Claude Code-style coding agent from scratch in Python: 8 articles, 4 videos, one codebase

🪁 A lightweight, modern Kubernetes dashboard that unifies multi-cluster and resource management, enterprise-grade user governance (OAuth, RBAC, and audit logs)…

Stateful runtime management for LLM agents—inject, manipulate, and retrieve Python objects across turns.

AgentCall lets AI Agents join meetings with voice, video & screen-share to build together. Supports Google Meet, Teams, Zoom (Beta)

Kition brings Markdown, DataTable, WhiteBoard, a tool-using AI agent, browser research, and visual workflows into one desktop workspace.

IntentKit is an open-source, self-hosted cloud agent cluster that manages a collaborative team of AI agents for you.

A powerful Model Context Protocol (MCP) server providing comprehensive Google Maps API integration with LLM processing capabilities.

Turn your Claude Pro/Max subscription into an OpenAI-compatible API for your IDEs and devices — LAN auth, per-key quotas, response cache, disciplined cli.js ali…

Paw Work - selection-first web agent for Chrome: select on the live page, describe the outcome, take away an editable office file. BYOK, sandboxed, no server.

基于 AI Agent + MCP 工具链 + 渗透 Skill 编排， 配合大语言模型， 自然语言输入 → 自动完成「信息收集 → 漏洞发现 → 漏洞利用 → 报告生成」全流程。

Lexora — Personal AI workspace built around Desktop / 以 Desktop 为核心的个人 AI 工作台

First AI Journey for DevOps - with comprehensive learning paths, practical tips, and enterprise guidelines

AI coding agent with one Python core and three front-ends — headless CLI, Textual TUI, and an Electron desktop. Works with any OpenAI-compatible API, with risk-…