LLM Mart Basic

Make any vibekit or qt314 promotional asset — tweets and threads, promo videos of the TUI, title cards, OG/link-preview images, quote cards, lore dossier cards, qt314 animations, GIFs, and TUI screenshots — in the vibekit voice and on the brand palette. Use whenever asked to writ

Maintain VibeKit's canonical vendored skills and generated CLI copies. Use when adding, reviewing, refreshing, or removing content under skills/, updating source links or upstream pins, or changing shipped behavior that affects skill guidance. Excludes arbitrary third-party skill

Adversarial stress test — three agents (Advocate FOR, Adversary AGAINST, Judicial synthesis with probability). Trigger when: user wants to stress-test a position, check weaknesses before filing, or requests adversarial review. Also option '4' in /legal menu. Do NOT trigger for: i

Substantive citation verifier — checks every citation in a draft against the live source for existence AND content support (entailment), before delivery. Status per citation: MATCH / PARTIAL / MISMATCH / UNVERIFIED. UNVERIFIED or MISMATCH blocks automatic delivery (remove, discla

Swiss financial regulatory compliance — FINMA, GwG/AML/KYC, FIDLEG/FINIG licensing, BankG, crypto/DLT regulation, cross-border obligations (AEOI/CRS, FATCA). Trigger when: user asks about FINMA licensing, AML/KYC compliance, financial services cross-border, crypto regulation, or

Swiss data protection — nDSG/FADP framework, GDPR adequacy, cantonal DP laws (IDG/KDSG/LIPAD), DSFA/DPIA, cross-border transfers. Trigger when: user asks about nDSG/GDPR compliance, DPAs, data transfers, DPIA, data subject rights, or references FDPIC/nDSG/FADP. Do NOT trigger for

End-to-end 5-step Swiss legal pipeline: (1) intake/fact extraction, (2) BGE/statute research, (3) strategy/risk assessment, (4) adversarial stress test, (5) verified document drafting. Trigger when: user asks for full analysis, 'run all steps', 'full pipeline', or 'end-to-end'. D

Legal chronology builder — turns case documents (contracts, correspondence, court filings, expert reports) into a sourced legal timeline. Every event carries mandatory provenance (document + locus), an undisputed/alleged/contested status with attribution, explicit date conflicts

Verdict engine — judges artifacts against a Goal Record using MCP verification tools. Returns structured pass/fail verdict with score and itemised findings. Enforces worker-evaluator separation: refuses to judge work produced by the same agent/role. Used by /legal-loop. Do NOT tr

Swiss legal intake — transforms vague or complex queries into actionable execution plans. Two modes: **Refine** (single-domain, Socratic dialogue ≤3 rounds, structured prompt) and **Briefing** (multi-domain/multi-jurisdiction, specialist panel assembly, execution plan with checkp

Decision-map decomposition for legal matters too big or too foggy for one session. Charts a map (destination, decisions so far, fog, out-of-scope) plus decision tickets under bcc-output/YYYY-MM-DD-<slug>/wayfinder/, then works tickets one at a time until the route to the delivera

Privacy routing for Swiss attorney-client privilege (Anwaltsgeheimnis, Art. 321 StGB) with pattern detection in German, French, and Italian to protect confidential legal communications

Shared deliverable-as-file output conventions for all BetterCallClaude commands. Defines the bcc-output folder structure, file naming, and chat summary template.

Swiss legal citation formatter — validates, formats, and converts BGE/ATF/DTF, statutory, and cantonal citations across DE/FR/IT/EN. Trigger when: citations need formatting, validation, or cross-language conversion. Uses legal-citations MCP (validate, format, convert). Also handl

Swiss legal document analyzer — structured analysis of contracts, court decisions, statutes, submissions. Includes NDA triage (GREEN/YELLOW/RED) and playbook-aware contract review. Trigger when: user uploads a document for review, requests NDA triage, or mentions 'playbook' or 'p

Swiss legal document drafter — creates contracts (OR), court submissions (ZPO), and legal opinions (Gutachten) in DE/FR/IT/EN with correct Swiss citations and Gutachtenstil. Trigger when: a user asks to draft, write, or create a legal document. Uses swiss-citation-formats for cit

Swiss legal research and jurisdiction resolution — searches BGE/ATF/DTF precedents, interprets federal and cantonal statutes, resolves federal vs. cantonal jurisdiction, and produces verified multi-lingual legal analysis. Trigger when: a user asks what the law says, requests prec

Swiss legal strategy — case strength, risk probability, cost-benefit, settlement/BATNA, and ADR assessment across ZPO/StPO/VwVG proceedings. Trigger when: user needs litigation viability, settle-or-sue decision, procedural options, or strategy memo. Uses entscheidsuche MCP for pr

Swiss legal translator — translates Swiss legal texts (contracts, submissions, statutes, opinions) between DE, FR, IT, and EN with correct terminology and register. Trigger when: a user asks to translate a Swiss legal document or term, or a document must be prepared in a differen

Auto-activates structured briefing sessions for complex legal queries -- detects when multi-agent coordination benefits from pre-execution intake and plan building

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…