LLM Mart Basic

Convert PDF files to a single vertically concatenated PNG image using macOS native CoreGraphics. Each page is rendered at 2x scale and stitched top-to-bottom. ~20x faster than pdftoppm+ImageMagick, zero external dependencies on macOS. Trigger when the user mentions "pdf to png",

Convert PNG images to high-quality SVG with optional white-background removal, vtracer spline vectorization, and svgo compression. Use when the user asks for "PNG to SVG", "png2svg", "转 SVG", "矢量化", "去白底", logo tracing, or converting raster icons into editable vector assets.

Orchestrate a complete investor BP workflow or route to one focused module: source-backed outline, PPTX/PDF production, or evidence/content/visual polishing. Use when the user wants to create a business plan end to end, combine BP stages, continue from an existing BP workspace, o

Turn existing project materials into a source-backed investor BP brief, evidence ledger, and 12–15 slide outline. Use before making slides, when the product positioning is unclear, or when an existing outline is too technical, generic, or unsupported. Trigger on "写 BP 大纲", "融资叙事"

Turn an approved investor BP outline into a clean, professional slide deck with deliberate style selection, real product evidence, charts, branding, PPTX/PDF, and a full-deck preview. Use when the narrative already exists and the user wants PPT production, visual style exploratio

Review and improve an existing BP outline, PPTX, PDF, or rendered slide set across investment logic, evidence, copy, charts, and visual quality. Produces a scored report, page-level revisions, and targeted regeneration instructions while keeping facts separate from assumptions. T

Generate complete business proposals for client projects from requirements.

Create research-backed product and technical solution plans from a user's requirement. Use when the user asks for detailed feasibility analysis, technology selection, architecture, implementation roadmap, library/vendor comparison, "解决方案", "技术方案", "产品方案", "选型", "调研分析", or a Skill

Professional-grade contract review skill that adds comment-based issue annotations without changing original text. Enforces a four-layer review (entity verification, basic, business, legal), writes structured comments (issue type, risk reason, revision suggestion) with risk level

Extract invoice data from images or text descriptions and generate a categorized Excel expense report. Supports receipt photos, scanned invoices, and manual text input. Auto-classifies into: business entertainment (客户餐费), travel-transport (机票/火车票/打车), travel-accommodation (酒店), t

Generate a complete professional event plan from guest background material.

Use when the user needs multi-source research with citation tracking, evidence persistence, structured report generation, or an implementation landscape that includes GitHub and other open-source forges. Triggers on "deep research", "comprehensive analysis", "research report", "c

Write multi-chapter books end-to-end from an outline.

Export WeChat Official Account articles into reusable structured content.

Polish and elevate MBA thesis / dissertation to national outstanding thesis quality (全国优秀论文). Performs comprehensive improvement: academic language, argument structure, logical rigor, innovation highlights, and formatting. Input: markdown thesis text. Output: polished full text.

Audit and optimize one or more existing Agent Skills from a canonical source path, then bump semver, update README/SKILL.md/skill.yaml/CHANGELOG.md, and verify installed copies and catalog synchronization. Checks frontmatter, trigger quality, CLI hygiene, naming, portability, ver

Create Gentle AI pull requests with issue-first checks. Trigger: creating, opening, or preparing PRs for review.

Trigger: PRs over 400 lines, stacked PRs, review slices. Split oversized changes into chained PRs that protect review focus.

Design docs that reduce cognitive load. Trigger: writing guides, READMEs, RFCs, onboarding, architecture, or review-facing docs.

Write warm, direct collaboration comments. Trigger: PR feedback, issue replies, reviews, Slack messages, or GitHub comments.

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

面向中文开发者的 Claude Code Skills / Agents / Plugins 精选与原创技能库｜按场景分类｜复制即装｜持续更新

原生 macOS Git 客户端，以 Agent 驱动仓库管理、审阅与协作。

A 股短线复盘看板：涨停池·连板梯队·龙虎榜·板块资金一屏看完，赚钱效应/晋级率/梯队断层/情绪周期等派生指标纯计算直出（不经过 AI），AI 只把数据串成能读的盘面研判。全本地运行，可用 Claude/Codex 订阅免 API key。| A-share short-term daily-review dashbo…

禁漫天堂 Agent Skills / AI 原生 JMComic 助手：通过 MCP 与 Skills 将 JMComic 注入你的 AI Agent. / AI-powered JMComic assistant for seamless integration with AI Agents via MCP & S…

Pairlet (formerly CC Pocket / cc-pocket) — Continue your local AI coding tasks from phone, tablet, or desktop.

Self-hosted Personal AI + agent runtime in .NET (NativeAOT-friendly)

A self-hosted knowledge platform for humans and AI agents — publish wikis, blogs, and portable Agent Skills.

Notion CLI with AI agent support. Smart queries, Obsidian sync, batch ops, backups, validation and more.

AI Coding Agent Multiplexer

Independent executor–verifier orchestration for software changes.

AI-native, local-first video editor by Ribbi — runs entirely in the browser. Rust/WASM engine, WebGPU compositing, WebCodecs export; humans and LLM agents edit…

Distill your knowledge, memories, and decisions into an open-source, inspectable AI Agent Twin.

🔬 Harness Vibe Research with Self-evolving AI Scientists

Personal AI desktop agent for Windows, macOS, Linux, Android & iOS. Set a goal, it works on its own. Teams (pair two desktops, agents + humans), Agent2Agent, Wo…

Run agents like a company. AgentOS is the native control plane for OpenClaw — manage agents, tasks, models, context, approvals, and runtime visibility from one…

Create Agentic admin panels faster on TypeScript and Vue.js with AdminForth Framework. Setup main CRUD pages within minutes, extend as you need

OpenJudge: A Unified Framework for Holistic Evaluation and Quality Rewards

An ebook reader with a self-evolving agent: it remembers your reading across books, and plugins extend the reader and the agent alike.

A curated list of awesome resources for vibe coding

Agentic Voice Notes for iPhone and macOS - Rust, Dioxus, LanceDB + RIG + SQLite