LLM Mart Basic

Multi-jurisdiction reference framework for corporate capital allocation, investment appraisal (NPV, IRR, MIRR, payback, profitability index), cost of capital (WACC, CAPM, hurdle rates), M&A valuation methods (DCF, trading comparables, precedent transactions, accretion/dilution),

Multi-jurisdiction reference framework for debt and capital structure advisory — optimal capital structure theory (M&M, trade-off, pecking order), leverage and credit metrics, debt instruments, covenant analysis, refinancing, WACC optimization, Basel III/IV capital requirements,

Route corporate finance questions to the narrowest specialist in the catalog. Use when you do not already know the specialist needed. Not for direct finance answers; Maestro classifies, dispatches, and synthesizes only. Dispatches single agent for focused tasks, parallel team (ma

Reference framework for financial planning and analysis (FP&A) covering driver-based budgeting, rolling forecasts, zero-based budgeting (ZBB), scenario and sensitivity analysis, budget-versus-actual variance analysis, long-range planning (LRP), integrated P&L/balance sheet/cash f

Multi-jurisdiction reference framework for OECD transfer pricing (arm's length principle, five TP methods, BEPS Action 13 documentation, CbCR) and OECD Pillar Two GloBE rules (IIR, UTPR, QDMTT, ETR computation, SBIE carve-outs, safe harbors, deferred tax divergence under IAS 12 v

Multi-jurisdiction reference framework for corporate treasury operations, cash and liquidity management, FX and currency risk, hedge accounting qualification (ASC 815 / IFRS 9), FX translation (ASC 830 / IAS 21), Basel III LCR/NSFR, Dodd-Frank and EMIR derivatives reporting, and

Variance decomposition framework and SEC Regulation S-K Item 303 MD&A commentary guidance for FP&A and corporate finance teams. Provides driver decomposition methodology (Volume/Price/Rate/Mix/One-Time), MD&A structural requirements with regulatory citations, restatement-risk tri

Multi-jurisdiction reference framework for working capital management — cash conversion cycle (CCC) optimization, accounts receivable management (collections, credit policy, aging analysis, factoring, invoice discounting, AR securitization, ASC 860 / IFRS 9 SPPI derecognition), a

Pair every cloud spend value with a kgCO2e estimate by region and service category for CSRD and SEC climate disclosure. Input is region, service category, and dollar value; output is paired kgCO2e with confidence label (vendor-published, third-party, or estimated) and source cita

Fetch live per-token, per-image, and per-GPU-hour prices for foundation models across Anthropic, OpenAI, Google, AWS Bedrock, Azure OpenAI, OCI Generative AI, and Vertex AI. Supports single-model lookup and comparative multi-provider tables. Every price is labeled with source URL

Fetch live public prices and build cost estimates for AWS, Azure, OCI, Scaleway, Gandi, Alibaba Cloud, and Tencent Cloud using each provider's public pricing API or official documentation. Supports live-environment cost analysis and prototype cost planning. Currency defaults to U

Normalize vendor-specific billing rows (AWS CUR, Azure Cost Management, GCP Billing Export, OCI) into FOCUS v1.2 columns from user-pasted CSV or JSON input. Refuses to invent column values not derivable from the input. No credentials accepted; operates on user-supplied data only.

Emit pod CPU and memory request/limit recommendations from user-pasted p50, p95, and p99 utilization metrics over a 7-14 day window. Outputs recommended requests at p95 plus 20% headroom, limits at p99 plus 30%, estimated monthly savings, and Karpenter consolidation eligibility f

Use this skill when reviewing FluxCD Kustomization, HelmRelease, GitRepository, HelmRepository, or OCIRepository resources. Trigger when the user asks whether a Flux configuration is safe for production, whether SOPS encryption is required, whether prune is safe on a given worklo

Apply an elevated review pass to AI or LLM-generated frontend code changes, checking specifically for hallucinated framework APIs, slopsquatted or non-existent dependency names, unsanitized dynamic-HTML sinks, and missing accessibility semantics before the diff is merged.

Statically review Angular component and service architecture for correct Signals usage (signal/computed/effect boundaries and purity), appropriate change-detection strategy (OnPush vs default), and service/DI boundary design, grounded in Angular's own Signals, change-detection, a

Statically review Angular SSR bootstrap configuration and component templates for hydration-mismatch risk (NG0500-class errors), unjustified ngSkipHydration usage, and direct-DOM-manipulation patterns that bypass Angular's template-owned DOM model, grounded in Angular's own hydra

Statically review Angular templates and components for injection via DomSanitizer bypass calls (bypassSecurityTrustHtml, bypassSecurityTrustUrl, bypassSecurityTrustResourceUrl), unsanitized [innerHTML] bindings, and dynamically bound iframe security attributes such as [attr.sandb

Reviews frontend-to-backend API contracts — BFF route handlers and direct backend calls — for data-minimization, server-side object-level authorization enforcement, error-shape leakage, CORS misconfiguration, and backward-compatible versioning before they ship.

Audit JS/CSS/HTML feature usage against the project's declared Browserslist/supported-browser matrix using Baseline and caniuse status data, flag unguarded non-Baseline usage, and verify feature-detection or polyfill fallback coverage, with per-feature caniuse/Baseline lookups lo

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

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…