LLM Mart Basic

Analyze insurance claims workflow systems for intake optimization, adjudication rules, subrogation, litigation management, and settlement analytics. Triggers: 'audit claims process', 'review FNOL workflow', 'evaluate claims automation', 'check subrogation recovery'.

Analyze agricultural climate risk systems for weather impact modeling, crop insurance, drought/flood prediction, soil moisture, and carbon tracking. Triggers: 'assess crop climate risk', 'evaluate weather yield models', 'review crop insurance integration'.

Review clinical data models and APIs for HL7 FHIR conformance, terminology standards, interoperability, and clinical workflow correctness. Triggers: 'check FHIR compliance', 'review clinical data model', 'audit HL7 conformance', 'validate medical terminology codes'.

Design CNC-ready modular, interlocking, flat-pack furniture and functional objects from sheet materials (plywood, MDF, acrylic) with slot/tab joinery, precise tolerances, full parts lists, cut layouts, assembly instructions, and CAD export guidance — no fasteners required.

Score your codebase 0-100 across complexity, coupling, cohesion, test coverage, documentation, churn hotspots, dependency health, and lint/type safety. Triggers: 'how healthy is this codebase', 'check code quality', 'score my project', 'find tech debt hotspots'.

Four-phase skill for planning and executing large-scale codebase migrations using full-context AI analysis. Produces an impact map, ordered batch plan, subagent execution protocol, and cross-codebase validation pass. Optimized for Fable 5's 1M-token context window.

Analyze commodity pricing and trading systems including forward curves, option models, position management, risk metrics, and regulatory reporting. Triggers: 'review pricing models', 'audit trading system', 'evaluate VaR implementation', 'check commodity risk management'.

Competitive intelligence and market positioning analysis. Researches competitors, compares features, pricing, and tech stacks, then produces a prioritized gap analysis with actionable roadmap..

Analyze compliance operations for regulatory change tracking, control mapping, policy management, audit readiness, and training compliance. Triggers: 'audit compliance program', 'assess GRC platform', 'review regulatory change management', 'check control framework'.

Analyze consumer modeling systems for purchase prediction, lifetime value estimation, multi-touch attribution, brand affinity, and switching cost analysis. Triggers: 'evaluate CLV model', 'review purchase prediction', 'audit attribution model', 'assess customer lifetime value'.

Detect content cannibalization on a site — multiple URLs ranking (or impressing) for the same query, splitting click-through, diluting authority, and confusing Google about which URL is canonical for the intent..

Analyze content engagement metrics, audience retention, attribution models, A/B test results, and recommendation engine effectiveness. Triggers: 'audit content metrics', 'evaluate recommendation engine', 'review retention curves', 'assess content A/B tests'.

Audit contract management codebases for clause extraction accuracy, obligation tracking completeness, risk scoring model quality, renewal management, SLA monitoring, liability exposure, force majeure handling, and IP assignment detection..

Analyzes infrastructure costs at 1K-100K user scales by reading the actual codebase, auto-detecting cloud providers, modeling per-action costs, and projecting total monthly spend with optimization recommendations.

Audit construction project management software for budget tracking accuracy, earned value management (EVM) formula correctness, risk factor modeling, schedule-cost integration, change order workflow completeness, and early warning detection..

Generate an institutional-grade commercial real estate underwriting model — input schema (T-12 income, T-3 trailing, rent roll, debt terms, exit assumptions), calc engine (Cap Rate, NOI, Cash-on-Cash, IRR, DSCR, Debt Yield, ROI, Equity Multiple, levered & unlevered returns).

Audit credit risk modeling software for scoring algorithm accuracy, regulatory compliance (ECOA, FCRA, SR 11-7), bias and disparate impact testing, model governance lifecycle, and explainability..

Audit precision agriculture and crop management software for yield prediction model accuracy, soil analysis integration, irrigation optimization algorithms, pest and disease detection pipelines, satellite and drone imagery processing, weather data integration.

Audit curriculum management software for learning outcome alignment, pacing guide optimization, standards coverage mapping (Common Core, NGSS, state standards), differentiation support, assessment design quality, and content gap detection across grade levels and subjects..

Audit any product from a Customer Success Manager perspective -- evaluate onboarding flow completeness, self-service help infrastructure, customer health signal tracking, support channel accessibility, expansion and retention triggers, and customer communication systems.

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

An open-source, privacy-first, self-hosted knowledge workspace where humans and AI agents work together 开源、隐私优先、自托管的知识工作空间，让人与智能体在此协作

Scale computer-use 2.0 with open-source drivers, cross-OS fleets, and benchmarks for training, evaluation, and data generation.

The go-to web for your AI coding agent — local-first search, fetch, crawl & research over MCP. No API keys, no cloud, $0/query. Public beta.

Transform and optimize your markdown documentation for Large Language Models (LLMs) and RAG systems. Generate llms.txt automatically.

合乎周礼：DeepSeek-powered Zhouli-style Chinese translator, web app, and distributable Skill package.

This is a fork of the https://dockbox.dev project I made

🏆 Curated, ranked list of AI agent harnesses (100+) — plus an MCP server, llms.txt & JSON so agents can recommend them too. Rescored weekly.

A Python framework for modular, self-contained skill management for machines.

ADHD — a skill for coding agents. Tree-of-thought with pruning, built on the Claude & Codex Agent SDK. Fans out parallel divergent thoughts under different cogn…

AI Agent 驱动的开源可自部署视频工作台：将小说与剧本转为角色、场景、道具资产、分镜、视频和剪映草稿，支持跨镜头一致性、多供应商与费用追踪 | Self-hosted AI video workspace for stories, storyboards and short-form video producti…

DeepSeek Harness Desktop App: a local AI desktop workspace for DSH Sessions, projects, files, web research, plugins, and Office artifacts.

Autonomous Offensive Security, Bug Bounty & Red Teaming Agent Framework powered by Hermes Agent, specialized reasoning skills, and multi-model LLM orchestration…

⌥ Coding agent with the IDE wired in

Supercharge AI Agents, Safely

X (Twitter) Scraper API and X API Alternative. You do not need an official X developer account. You do not need to connect or use an X account for supported scr…

My AI Stand. Realtime by day, rewriting itself by night. Summon my AI superpower.

Open-source coding agent for your terminal, built in Rust and on a journey of continuous community improvement. Issues and PRs welcome.

观澜 / Guanlan：AI Agent 的中文互联网研究、阅读与信源路由工具。

Mac Agent for macOS 26: the agentic AI harness for your Mac Desktop. Computer use, automation, scripting, coding, and more. Powered by 18+ providers across loca…

Semantic version control => entity-level diffs, blame, and impact analysis on top of git. 28 languages via tree-sitter. Built for coding agents.