LLM Mart Basic

Retired — /ultracook no longer exists as a standalone skill. Any /ultracook invocation resolves to /cook, which now owns the single implementation pathway (including the fan-out mechanics this skill used to run). Use /cook instead.

Mark the current conversation as a durable handoff so a new agent can resume the work. Use when the user wants to preserve state for a later or parallel session. Triggers include "hand this off", "write a handoff", "drop a wheypoint", "checkpoint this", "compact the conversation"

Write, edit, refactor, or review Python in easy-cheese with concise stdlib-first code, Python 3.12, Shiv .pyz packaging, and repository test and validation conventions. Use for Python changes under src/, scripts/, .github/scripts/, or tests/, especially when the user asks for Pyt

Codify the Iron Law, Red Flags, and Rationalization-table template that easy-cheese skills follow, plus the CSO description rule and size-budget checklist for authoring or revising a skill. Use when writing a new skill or SKILL.md, adding a discipline section, or reviewing an exi

Generate an instrumental music bed via ElevenLabs Music, ROUTED THROUGH THE elevenlabs-proxy so it bills the Ads agent. Trims any sparse intro, loudnorm, fades the tail. Prompt + length from the template recipe. Use for the music layer of any video-ad format.

Image-to-video (or text-to-video) via any FAL video model (Kling, Seedance, Veo), ROUTED THROUGH THE GooseWorks fal-proxy so the call bills the Ads agent. The template recipe names the model + params; image_url inputs must be public URLs (the orchestrator hosts local frames via M

Generate a voiceover (VO) clip via ElevenLabs text-to-speech, ROUTED THROUGH THE elevenlabs-proxy so it bills the Ads agent. Voice id + script text come from the template recipe. Use for the spoken narration of VO-driven video-ad formats (cgi-app-sizzle, flat-vector-explainer, hy

Scrape competitor ads from Google Ads by domain. Returns ad creatives, formats, and campaign details. Use for competitive ad research and messaging analysis.

Shared helper that routes ALL paid media generation (FAL image/video, ElevenLabs music) through the GooseWorks proxies so every call bills the Ads agent — never a provider SDK's default host. Host-swaps the FAL queue URLs, loads the agent token from ~/.gooseworks/credentials.json

Scrape competitor ads from Meta's Ad Library (Facebook, Instagram, Messenger, Threads, WhatsApp). Search by company name, Facebook Page URL, or keyword. Returns ad creatives, spend estimates, reach, impressions, and campaign details. Use for competitive ad research, messaging ana

Find newsletters relevant to a target audience/industry for sponsorship opportunities. Discovers newsletters through web search, newsletter directories, and industry research. Returns newsletter name, author, estimated audience, topic focus, sponsorship rates (if available), and

Assemble a glossy 3D-character animated-explainer video ad (~77s, 9:16) built on an "N types of X" listicle spine — a recurring human protagonist plus a locked cast of N persona characters, one per list item. Given the per-scene i2v clips + a per-scene target-duration table + a n

Assemble a premium 3D product-showcase ad from a config — four beat clips (an orbiting hero rotation, a macro push-in, a physics reveal, a typographic close) normalized to the brand-color canvas, hard-concatenated in order, closed on a deterministic Playwright brand end card, and

Assemble an absurdist animated-explainer video ad (~38s, 9:16) from per-scene i2v clips + their measured VO windows — retime each clip to its VO, re-encode every segment to identical 30fps/libx264/yuv420p so the concat demuxer never drops frames, concat, build a REAL-product PIL

Assemble a viral iOS "AirDrop" notification-carousel video ad (≈6–8s, 9:16) from a brand line plus 6–16 real product photos — a native AirDrop share-sheet card ("Brand would like to share a ___ · Decline / Accept") springs up and its preview window CYCLES through the products, la

Render a 'brand identity reveal' video from a config — a single poster frame in a real, softly-lit space (real wall, soft-focus plant in the corner, dappled leaf shadow, illuminated poster) whose artwork HARD-CUTS through ~10 on-brand poster mockups (hero product, IG post, hangin

Assemble a cartoon / animated / hand-crafted music-video ad from a config — a sung song carries the whole narrative while N per-bar i2v clips (one recurring animated character, one look pack) are each cut to their BAR window from librosa beat-tracking and hard-concatenated on the

Assemble a 3D-CGI app sizzle — nano-banana CGI plates (blank-glow floating phone + smoky-black studio + amaranth rim-light + placeholder burst shapes) plus PIL compositing of the REAL App Store screenshots onto the bezel + burst-out overlays, driven by Kling 3.0 i2v steady-float

Assemble a ChatGPT chat-reveal video ad from a thread + timeline JSON — one continuous Playwright recording of a ChatGPT mobile chat (user types with the iOS keyboard up → taps send → keyboard slides down + header cluster swaps in one beat → one gray loading dot → the assistant a

Assemble a cinematic live-action-style music-video ad from a config — an original sung anthem carries the whole narrative while N 35mm-film-look i2v clips are each cut to their lyric window and hard-concatenated on the beat as a 3-act arc, the anthem muxed at loudnorm I=-14, cine

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

Your car as a chat-room agent: Raspberry Pi 5 + dashcam + local AI. CodeWatch's sibling for the garage.

The enterprise gateway for autonomous agents. Identity management, per-channel isolation, credential vault, per-session tamper-evident audit log.

AI agent for Home Assistant — talk to your home, create automations in plain language, analyze cameras with face recognition, and get proactive anomaly alerts.…

A desktop app to prototype agent ideas, inspect every harness step, replay failures, and evaluate performance, all in one place. Local-first, cloud-ready for ma…

Local-first AI memory you can see, edit, and override — portable across Claude Code, Codex, Cursor, Windsurf, and other MCP coding tools.

Web & desktop (Electron) client for the OCTO open workplace — one React + TypeScript codebase shipping browser and PC surfaces, with first-class AI agent UX.

同花顺官方 A股金融数据服务，提供股票实时行情、历史行情、财务报表、指数、板块、涨停等数据，适用于 AI Agent、量化研究和应用开发，支持 API、MCP、CLI 和 Python。Official Tonghuashun (HiThink) A-share financial data service provi…

Open-source desktop SQL workspace for PostgreSQL, MySQL/MariaDB, SQLite and 15+ more databases like DuckDB, ClickHouse, Redis and Firestore. Built-in MCP server…

🤖 Local-assist BOSS Zhipin CLI for AI agents — search, welfare filtering, shortlist, JSON-envelope output; low-risk & compliant by default.

The local-first sidebar AI agent for ComfyUI — runs on your own Claude OR ChatGPT subscription (no API keys, no extra LLM costs). Drives your live graph: edits,…

Persistent memory for Claude Code — identity, context, and continuity across sessions

🔬 A curated collection of 23,000+ agent skills for empirical research across 8 social science disciplines. | 精选 23,000+ AI Agent 技能库，覆盖8大社会科学学科的实证研究。CoPaper.AI…

A curated list of plugins, skills, MCP servers, patch/profile layers, orchestrators & UIs for DeepSeek Harness (DSH). Visualization · PPT · Coding · Agents · Lo…

World Memory Protocol.

Run your own organization of agents.

The most RAM efficient harness

AI-native, free, open-source alternative to Jira, Trello, ClickUp & Monday. Built for Scrum teams where humans and AI agents collaborate as equals — on the same…

Free open-source desktop app that scrapes JAV metadata and generates NFO + cover art for Jellyfin, Emby & Kodi. No Docker, no CLI — one-click install on Windows…

A cross-platform desktop app to manage Agent Skills in one place and sync them to multiple AI coding tools’ global skills directories — “Install once, sync ever…

天枢 (Tianshu) 是一个基于harness工程的终端编程智能体运行时（Tui X Gui），针对DeepSeek V4 做了前缀缓存工程优化（长会话实测稳态命中率 97–99%）和深度适配。它跳出了传统 AI 编程助手把大模型仅当成“工具”的局限，基于认知虚拟机 (CVM)、自感知层和信息素（Stigmergy…