LLM Mart Basic

Judgment rules for user-facing text and docs: CLI and diagnostic output, error and help text, README and docs structure, code comments, titles, and generated reports, decks, or exports. Use when writing or changing any user-visible string, when adding or restructuring docs or dec

Decide whether a task deserves its own git worktree and, if chosen, run it end to end: branch from the integration branch rather than the current tree, keep the main working copy untouched while the task runs, compare the result against the untouched baseline before declaring it

Accessibility audit and remediation for Canvas LMS courses. Scans content for WCAG-oriented issues, generates prioritized reports, guides fixes, and verifies remediation. Use when asked to "audit accessibility", "check WCAG", "fix accessibility issues", or "run accessibility revi

Bulk grading workflows for Canvas LMS assignments using rubrics. Covers single grading, batch grading, and code execution strategies with safety-first dry runs.

Scaffold complete Canvas LMS course structures from specs, templates, or existing courses. Creates modules, pages, assignments, and discussions in bulk. Use when asked to "build a course", "scaffold modules", "create course structure", "set up a new course", or "copy course struc

Learning designer quality check for Canvas LMS courses. Audits module structure, content completeness, publishing state, date consistency, and rubric coverage. Use when asked to "QC a course", "is this course ready", "pre-semester check", or "quality review".

Discussion forum facilitator for Canvas LMS. Helps students and educators browse, read, reply to, and create discussion posts. Trigger phrases include "discussion posts", "reply to students", "check discussions", "forum participation", "post a discussion", or any discussion-relat

Educator morning course health check for Canvas LMS. Shows submission rates, struggling students, grade distribution, and upcoming deadlines. Trigger phrases include "morning check", "course status", "how are my students", or any start-of-day teaching review.

Educator peer review management for Canvas LMS. Tracks completion rates, analyzes comment quality, flags problematic reviews, sends targeted reminders, and generates instructor-ready reports. Trigger phrases include "peer review status", "how are peer reviews going", "who hasn't

Student weekly assignment planner for Canvas LMS. Shows all due dates, submission status, grades, and peer reviews across all courses. Use when a student says "what's due", "plan my week", "weekly check", or wants to organize their coursework.

Use when reading today's US-market capital flow across multiple sectors to identify rotation direction — e.g. "今天资金流向", "板块强弱", "rotation map", "卖芯买云", "where is money moving today", "scan flows across sectors". Produces a cross-section snapshot of net inflows by cohort (indices

Render financial charts via the local chart web app (workspace at the repo root — Hono server + React front end, port 1792). Four chart types: intraday capital-flow line (`flow`) and cross-symbol signed-bar comparison (`cohort`) — both Recharts — plus SEPA strategy dashboard (`se

Global multilingual news event stream with tone scoring via GDELT 2.0 Doc API.

Short-term multi-timeframe (5m/15m/1h) technical read for a single symbol — pulls K-line across three timeframes, reads MACD + swing structure, writes a direction call (long/short/neutral) with an explicit anchor price, a 2–4 scenario forward read, a range-bound playbook (long ta

Korean market quotes (KOSPI / KOSDAQ / SK Hynix / Samsung) with capitulation-reversal detection. Use whenever reading the US memory/storage complex (MU / DRAM / SNDK / WDC / STX / SMH) — Korea is the SOURCE market and leads the US tape; Longbridge does not cover KRX. Triggers: 韩国

Use when monitoring stocks/ETFs/indices across pre-market, open, intraday, or close — especially when the user is reading session action live and may revise their take as it unfolds. Triggers include 盘前/盘中/收盘 sessions, multi-symbol watchlists (e.g. MU/TSM/SMH semi tracking), user

Use when the user wants to release a new desktop app version (发版 / release / 发布新版本) — bumps apps/desktop version, writes user-facing release notes into CHANGELOG.md, and opens the release PR that drives the automated tag → build → publish pipeline

Use when the user asks for an end-to-end orientation on a listed company they don't yet understand, especially when the request combines two or more dimensions in one ask. Triggers on "X 是干什么的", "帮我了解 X", "X 主营 + 同行", "盘前为什么涨", "本周趋势 + 阻力支撑", "X 和其他公司的关系", "first time looking at

交易决策关卡——任何买入/加仓/卖出/减仓动作发生前，先过一遍写死的检查关卡， 打分给出判定，判定与实际执行不一致的记为违规，落盘 JSON 供复盘统计。三个 入口：买入漏斗（六层打分，硬门+软分）、卖出触发器（复用用户既有的 6/27 持有计划触发线、周期见顶清单、爆仓潮反向保护）、巡检（对长桥全部持仓批量跑 卖出触发器）。不拦截下单（本仓库长桥只读），约束力来自违规账单而非技术拦截。 Triggers: 我想买 X、我想加仓 X、我想卖 X、我想减 X、要不要止盈、要不要止损、 巡检、跑一遍卖出检查、算一下违规账单、我该不该现在动这只票、trade

Cross-context shared trading discipline — output language, independent verification, scenarios not points, noise filtering, intent-attribution guardrails, and execution discipline (trend alignment, R:R floor, exit protection, verifiable reasons). Injected into both the app-side j

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

AI coding platform for teams

AI Multi-Agent Framework in .NET

Production-ready code examples for Telnyx AI Communications Infrastructure — Voice AI, SMS, SIP, and IoT APIs

UltraGameStudio - AI coding agent for game development: engine workflows, gameplay code, and asset generation.

🦞 ResearchClawBench: Evaluating AI Agents for Automated Research from Re-Discovery to New-Discovery

The context-aware model router that learns & adapts to your long-horizon coding agent workflows. Lightweight & extensible, works with any harnesses, any models,…

Open-source sandboxes where coding agents build and deploy. Spin up isolated environments where Claude Code, Cursor, and other agents code and deploy software.

Native desktop UI for Claude Code with orchestration, streaming, background agents, and multi-provider support. Built with Tauri + React.

OpenCode mobile client via Telegram: run and monitor AI coding tasks from your phone while everything runs locally on your machine. Scheduled tasks support.

Terminal session manager for AI coding agents. One TUI for Claude, Gemini, OpenCode, Codex, and more.

Exposes internet search tools for use by LLM-backed Assist in Home Assistant

Templates and workflow for generating PRDs, Tech Designs, and MVP and more using LLMs for AI IDEs

Versus Incident is the self-hosted AI SRE agent. It learns what your system normally look like and escalates only what is new or unexpected issues — routing to…

Browser-native side panel for Hermes Agent — connect web context to your local Hermes runtime.

Agentic-friendly CLI generator for APIs: turn Swagger, OpenAPI, and google.api.http protos into single-binary CLIs with catalogs and generated Skills.

Open-source agent platform for Global × China enterprises — wire every system through one agent core. Self-hosted, any LLM.

Official python implementation of UTCP. UTCP is an open standard that lets AI agents call any API directly, without extra middleware.

An agent small enough to run anywhere. A minimal agentic runtime in C — ~380 lines, 54KB binary, ~2MB RAM. A skill file + an LLM + a shell loop, no framework.

AgentiLoop Agent! An Autonomous Agentic Agent for Mac, and exclusive Apple only harnesss. Suppprtd automation, scripting, coding, build anything and more. Power…

微信公众号 AI 运营助手 | 选题、写稿、审稿、排版、配图、发布全流程 Skill，支持 OpenClaw / Claude Code / Cursor / Codex