LLM Mart Basic

Writes production-grade, distinctive interface code — one strong art direction (editorial, brutalist, soft-depth, retro-terminal), a real typographic scale, custom details (cursor, selection, focus states), semantic HTML, delivered as a single file or as components. Ships with an

Generates 20-hook batches for any topic across eight proven patterns — curiosity gap, contrarian, specific number, mistake/warning, transformation, insider secret, question, call-out-the-reader — each tagged with pattern and platform fit, plus a top-3 pick with rationale. Refuses

Runs collections on late invoices: builds an aging ladder (current/30/60/90+), assigns each invoice a rung on an escalation sequence with ready-to-send emails — friendly nudge, firm reminder with late-fee mention, final notice — plus a phone script, tone rules that preserve the r

Drafts correct double-entry journal entries from described business events, with templates for accruals, deferrals, depreciation, payroll, prepaids, and corrections. Every entry carries a date, memo, and support reference; reversals are drafted where due; a running debits-equal-c

Designs and fully produces a lead magnet — checklist, template, calculator, swipe file or mini-guide — plus the landing section, delivery email and a 3-email nurture starter. Use when the user asks to "create a lead magnet", "build something to grow my email list", "make a freebi

Severity-by-likelihood legal risk register for a situation or deal — enumerates concrete risks, scores each one impact 1-5 × likelihood 1-5, renders a heat-map table, attaches mitigations to every risk at or above threshold, defines escalation criteria for immediate human counsel

Breaks unit economics down per product, service, or client: revenue minus direct costs into a contribution-margin ranking, allocated overhead into net margin, a price floor per unit, a push/fix/kill mix analysis, and three pricing moves with quantified margin impact. Use when the

Scaffolds and ships MCP servers in Python (FastMCP) or TypeScript (@modelcontextprotocol/sdk) — tools designed around workflows rather than raw endpoints, with model-guiding schemas and error messages, pagination, a direct-call test harness, and wiring into .mcp.json or claude mc

Turns prospect pushback into progress — diagnoses the real objection behind the stated one and scripts calm, honest responses for price, timing, competitor, authority and brush-off objections. Use when the user says "they said it's too expensive", "prospect went silent", "they're

Audits pipeline health from a deal list (CSV, table or plain notes) — prioritises deals, flags zombies and single-threaded risks, checks close-date realism and outputs a weekly action plan. Use when the user says "review my pipeline", "which deals should I focus on", "why is noth

Plans payroll cash: true loaded cost per hire (gross plus employer taxes, benefits, tools), a payroll calendar with cutoffs and cash-out dates, a scenario table for new hire vs raise vs contractor-vs-employee, and a payroll-to-revenue check against rough industry bands. Use when

Writes LinkedIn and X posts that read human — a hook line drawn from proven patterns, whitespace rhythm, story or insight structure, a soft CTA — and delivers three full variants per ask (story, contrarian, list). Applies the project's voice profile when one exists and enforces p

Audits and rewrites LinkedIn/X profiles element by element — a headline built on who-you-help + outcome + proof, an About section with a three-line hook and scannable body, a banner brief, featured-section picks, and a keyword pass for search — delivering a before/after for every

Builds proposals, quotes and offers that close — problem restatement in the client's words, scoped options, anchored pricing, timeline, terms and next step. Use when the user says "write a proposal", "send them a quote", "build an offer for X", or after a successful discovery or

Matches two datasets — bank vs ledger, subledger vs GL — via exact matching, fuzzy matching (amount tolerance, date window, reference similarity), and split detection; buckets exceptions (timing, missing, duplicate, amount mismatch), ages unmatched items, proposes adjusting entri

Scripts 15–60 second short videos (Reels, TikTok, Shorts) in a timestamped two-column VISUAL | AUDIO/VO format — verbal + visual hook in the first two seconds, a retention beat every 3–5 seconds, pattern interrupts at drop points, on-screen captions, a loop-friendly ending, and a

Clause-by-clause contract review — inventories key clauses (term, termination, liability cap, indemnity, IP, payment, confidentiality, governing law, auto-renewal), flags deviations from market-standard positions with RED/YELLOW/GREEN severity and verbatim quotes, drafts redline

Builds a 7-day SMB campaign kit: one offer with value, deadline, and an honest reason-why; channels picked from what the owner already has (email list, socials, storefront, partners); a day-by-day calendar; every asset drafted (three emails, three social posts, flyer copy); a sim

Pre-signature gate and routing plan for a finalized document — verifies exact legal entity names, signatory authority, attached exhibits, filled blanks, consistent dates, and counterparty details, then sets the signing order (sequential vs. parallel, with reasons), writes envelop

Authors new SKILL.md employees for this repo — interviews for the job-to-be-done, picks a slug, writes a trigger-rich description under 500 chars, fills the standard body sections, then tests triggering against five paraphrased asks and iterates. Use when the user says "make me a

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

🤖 MateClaw — Your second brain with Multi-Agent Orchestration, MCP Protocol, Skills & Memory, Dream, and Multi-Channel Support. Built on Spring AI Alibaba.

Vibe-Research: Your Personal Trading Research Agent · A股/美股/港股 的个人投研 Agent：每日复盘、资讯雷达、个股数据、板块中心、我的持仓、研究记录、回测。Vibe-Research 把数据和功能配齐，由你自己的 Agent 驱动投资研究。基于开源的 Code…

Wayland - The AI Agent That Perceives. Reasons. Acts. Evolves.

Observability and enforcement for AI agent harnesses. Capture every run and runtime reliability with policy enforcement. 40 built-in policies, a local dashboar…

Turn your Solana Seeker (or any Android phone) into a 24/7 personal AI agent

A curated collection of offensive, defensive and AI/LLM security tools.

AI agent 通用任务治理框架：对齐目标与事实，规划和调度能力，守住授权与风险边界，治理任务执行到真实验收与交付。Governance framework for evidence-driven planning, orchestration, and verified delivery.

Open-source (Apache-2.0) PDF takeoff for construction & flooring — the first engine an AI agent drives natively over MCP, not bolted on. One-click room detectio…

Stop degrading your model's reasoning. A minimal, zero-config AI coding agent. Enforced ephemeral subagents keep context pure. From tiny local models up to Sol,…

实习.skill — 双非也能拿大厂 offer。帮你改简历、抠面经、准备面试，把真实背景翻译成面试官想要的样子。

专门为 agent 打造的 agent 搜索工具，具备多语言搜索能力，覆盖中文/英文/学术/代码/购物/金融/新闻/百科。

Local-first AI agent workspace for multi-agent collaboration, agent orchestration, scoped permissions, evidence-aware runs, and human-in-the-loop decisions.

Keyboard-first desktop Kanban workspace for AI coding agents with embedded terminals, git worktrees, and hook-driven task tracking.

Claude Code Prompt Mechanism Visualizer — Electron desktop app

Multi-repo semantic code search MCP server in Rust — hybrid vector + BM25 retrieval, tree-sitter AST chunking, fully offline. For OpenCode, Claude Code, Cursor,…

One-ink editorial print image skill — warm paper, halftone photography, active negative space, and restrained typography.

US stock market data for AI coding assistants — zero-auth, official sources. CBOE options with full Greeks + 0DTE flow, FINRA market-wide short volume, SEC EDGA…

AI-powered Werewolf (Mafia) social deduction game where every player is controlled by top LLMs like DeepSeek, Qwen, Gemini, and more

A股全栈数据工具包 · 十一层架构 · 54端点 · 19数据源 · 零鉴权 | Full-stack China A-share data toolkit for AI agents — 11 layers, 54 endpoints, 19 sources, zero-auth

Agentic desktop GUI client for Elasticsearch, OpenSearch, DynamoDB, MongoDB & EasySearch. Natural language queries, visual management, and monitoring. Privacy-f…