LLM Mart Basic

Post-mortem analysis when a client churns. Takes client history, engagement data, support tickets, usage logs, and exit feedback to produce a comprehensive churn autopsy with root cause classification, timeline of decline, and preventive measures.

Audit a website or UI and de-AI it — find the patterns that make it look template-generated (in both design and copy) and return specific, prioritized fixes that push it toward editorial, premium, human-crafted. Reviews layout, color, type, spacing, motion, accessibility, AND the

Generate a complete, premium design system from a brand brief or an existing site — color tokens, type scale, spacing/radius/elevation, motion language, and component specs — exported as Tailwind config, CSS variables, and a usage doc. Built to look editorial and human-crafted, n

Compose a premium, animated landing page section by section in Next.js + Tailwind + Motion (Framer Motion) — built on a real design system, with editorial copy and motion that feels human-crafted, not template-generated. Use when building or rebuilding a landing page, marketing s

Use to create or clean up the CLAUDE.md (or AGENTS.md) file that tells a coding agent how to work in a repo — commands, conventions, architecture, and the traps. Trigger when onboarding an agent to a codebase, when the agent keeps making the same repo-specific mistake, or when th

Generates a comprehensive client health overview across all accounts. Reads CRM data, support tickets, usage metrics, billing, and engagement logs. Calculates health scores, trend direction, and RAG status per client. Outputs a sorted risk report with recommended actions.

Generates full consulting proposals from a brief. Input client name, problem description, and rough scope. Outputs proposal.md with executive summary, problem statement, proposed approach, timeline, team, pricing tiers, and terms. Researches client company for personalization. Mu

Generate personalized cold email sequences (7-14 emails) with A/B test subject lines, follow-up timing recommendations, and integrated social proof. Creates multi-touch campaigns optimized for response rates. Use when users need outbound email campaigns, sales sequences, or lead

Extract color palettes from images, websites, or designs. Identifies dominant colors, generates complementary schemes, and exports in multiple formats (HEX, RGB, HSL, Tailwind, CSS variables). Use when users need color schemes from images, brand colors, or design system palettes.

Decode a commercial lease before signing or renewing -- true all-in occupancy cost (base rent plus NNN/CAM plus escalations), the clauses that hurt small tenants (personal guarantees, relocation, restoration), and the negotiation asks landlords routinely grant. The lease is most

Monitors competitor websites, pricing, content changes, hiring patterns, and product updates. Generates intelligence reports with strategic implications and trend analysis. Stores history for longitudinal tracking.

Audits a codebase or business process for regulatory compliance across GDPR, HIPAA, SOC2, CCPA, and PCI-DSS. Scans for PII handling, data retention, encryption, access controls, audit logging, consent management, and data transfer issues. Generates a structured compliance report

Search and extract contact information for people or companies including names, phone numbers, emails, job titles, and LinkedIn profiles. Aggregates data from multiple sources and provides enriched contact details. Use when users need to find contact information, build prospect l

Use when a coding session is burning context fast, output is drowning in noise, the model keeps forgetting earlier decisions, or the user asks to reduce tokens, stop the verbose narration, work in a huge repo, or make a long session survive. Covers what to read, what to summarize

Review contracts for concerning clauses, extract key terms, compare to standard terms, and flag unusual provisions. Use when user needs contract review, legal document analysis, or agreement evaluation.

Reads a contract and generates redline suggestions with replacement language. Identifies unfavorable terms, missing protections, ambiguous language, liability exposure, IP risks, termination traps, and auto-renewal gotchas. Produces a contract-review.md with clause-by-clause anal

Audit your calendar with Cowork's calendar tools -- measure meeting load and fragmentation, identify which recurring meetings earn their slot, propose consolidations and focus blocks, and draft the diplomatic messages that reclaim your week.

Sweep a contracts folder and extract every renewal date, auto-renew clause, notice window, and price-escalation term into a renewal calendar -- then create calendar reminders ahead of each notice deadline via Cowork's calendar write tools. The skill that stops auto-renewals from

Prepare YOUR data room for a fundraise, acquisition, or bank diligence -- builds the checklist for your deal stage, sweeps your folders for what you already have, produces a gap report, and organizes everything into the structure buyers and investors expect. The sell-side complem

Uses Cowork-style multi-step analysis to process deal room documents -- contracts, financials, org charts. Outputs risk assessment, term comparison, key findings, and negotiation recommendations.

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

Offline-first Python AI agent that runs a tiny research business: quotes each job against its own costs, collects via Stripe, fulfils with NVIDIA Nemotron, pays…

DSH 插件 · 注入式优化器 0.8（主线）：你照常说话，它在你发送后,AI接收前把"这一轮到底要什么"理清楚，再把这份理解交给工作 AI(上下文注入) —— 原话不改写，条条带逐字依据。含控制界面（档位/权限/模型/上下文/只读工具）、拦截浮层（思维层+产出层）与真实 token 用量。可明显提升大多数模型的发挥稳…

Reliable AI Skill + MCP toolkit for agent-driven desktop CAD automation.

Curated real-world use cases for Hermes Agent — the self-improving AI agent from Nous Research. Backed by primary sources.

AI Agent 教学仓库 | 系统化 LangChain、RAG、LangGraph、MCP 全栈实战代码 | 万字博客详解 | 开源可运行示例 | 从零构建智能体

从 0 复刻 WorkBuddy-style 桌面 AI 助手 Harness：24 章 Python 教程，覆盖 Agent Loop、工具调用、记忆系统、Sidecar、沙盒审计、DeepSeek/OpenAI 评测轨迹

MCP server and CLI tools for web search and crawling, built on SearXNG and Crawl4AI

Delta MCP is a free app that sits between your AI apps and their MCP servers: one program per task instead of one tool call per step, up to 24.1× fewer tokens i…

Ava turns any Android 5+ device into a voice-first Home Assistant kiosk. Native C++ under the hood, so a 10-year-old tablet still listens, talks, and runs the h…

Roblox Studio macOS Window Capture Fix 2026: Real Screenshot Tool Instead of Magenta Playtest Glitch

LabTether