LLM Mart Basic

商品换背景。白底商品图 → 逼真场景图，光影与投影匹配新环境。当用户说「换背景」「加场景」「白底转场景」「放到桌面上」时使用。

生成带中文排版的详情页模块。商品图 + 卖点 → 可直接上架的详情页图文模块。当用户说「详情页」「做详情图」「商品描述图」「详情页模块」时使用。

商品精修、去褶皱。随手拍的商品图 → 可直接上架的精修图。当用户说「精修」「去褶皱」「修图」「拍得不好看」「整理一下」时使用。

商品图生成带文案排版的转化主图。商品图 + 卖点 → 带中文文案的电商主图。当用户说「主图」「加卖点文案」「转化图」「促销图」「主图文案」时使用。

主图 A/B 组与转化复盘。商品图 + 卖点 → 多组对照主图 + 每组的差异假设 + 复盘模板。当用户说「A/B 测试」「主图优化」「提点击率」「哪版更好」「换个版本试试」时使用。

静态主图转主图视频。一张商品图 → 3–5 秒可上架的主图短视频。当用户说「主图视频」「图转视频」「让图动起来」「加个视频」时使用。

材质质感增强与纹理重建。糊掉的图 + 高清商品图 → 纹理清晰可信的图。当用户说「增强质感」「图糊了」「补纹理」「提清晰度」时使用。

已有模特图换模特、换背景。一张模特图 → 多人群多场景版本，商品本身不变。当用户说「换模特」「换背景」「换人种」「一图多版」「同一件衣服换个人」时使用。

上架前平台合规校验与自动修复。待上架图 → Amazon / TikTok Shop / Temu / Shopee / 淘宝 各平台的通过或驳回风险报告，可一键修成合规图。当用户说「会不会被驳回」「合规检查」「白底不达标」「主图规格」「传上去被拒」时使用。

商品短视频广告。卖点 → 分镜脚本 → 分段生成 → 拼接加字幕成片。当用户说「做条广告」「短视频」「投流素材」「分镜脚本」「带货视频」时使用。

去水印去文字。带水印 / 文字 / logo 的图 → 干净图，背景纹理自然补全。当用户说「去水印」「去文字」「擦掉 logo」「把字去了」时使用。

平铺图转隐形模特立体图。平铺图 → 有体积感与版型的立体展示图。当用户说「转 3D」「立体图」「隐形模特」「把衣服撑起来」时使用。

UGC 口播种草视频。商品 + 人设 → 口播脚本与成片，达人自拍质感。当用户说「口播视频」「种草视频」「达人风格」「UGC」「真人推荐」时使用。

鞋包配饰真人穿戴图。商品图 + 模特参考图 → 真人佩戴图，落位、透视与阴影自然。当用户说「鞋包上脚」「配饰上身」「墨镜戴上」「首饰佩戴图」「包包上身」时使用。

Apply WIT (Writing Is Thinking) as a human–LLM collaborative scientific reasoning skill for scientific question formulation, finding-driven research planning, next-experiment selection, Results or Discussion review, claim–evidence and reviewer stress tests, manuscript logic audit

Use when creating skill repositories, standardizing or validating skill repo structure, setting up composer/release workflows, configuring split licensing (MIT + CC-BY-SA-4.0), fixing plugin.json / SKILL.md validation or version-parity errors, or releasing a skill version (versio

Conversational design workshop for substantial work. Interviews the human one question at a time, explores 2-3 approaches with trade-offs, and presents the design section by section for approval before writing only design.md, then stops. Combines requirements discovery with codeb

Post-implementation completion workflow for Spec-backed Plans. Use after spec-implement completes to validate, review, create stacked commits, and open a PR via code-pull-request. Triggers only with an active Spec-backed Plan after spec-implement completes, including when the use

Continue an approved Spec-backed workflow when the user says "implement", "go", "start", or "do it". After Codex Plan Mode, persist the next missing design.md or plan.json artifact and stop. When both artifacts exist, execute plan.json with TDD and report between batches.

Write approved implementation plans in one of two modes. Explicit Inline mode creates a conversational plan for bounded work. Spec-backed Plan converts an approved design.md into plan.json. Both modes stop after producing their plan output. Trigger after atelier-orchestrator sele

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

Okou connects to the tools your team already uses and does the work — across marketing, sales, engineering, and operations, under your control.

An open-source Digital Worker platform for reliable execution, continuous co-evolution, and building Enterprise AI assets.

A curated list of AI Agent evolution, memory systems, multi-agent architectures, and self-improvement projects. | evomap.ai

A governance harness for AI coding.

DeepSeek Harness 手机版：可直接安装的 Android APK，AI 免 Root 操作手机（Shizuku/root 可选），文件编辑只需所有文件访问权限，前台保活 + AI 通知

Local-first, governed AI agent runtime for Python — embed it in your app, or run it as a CLI or ACP server. Permissions, MCP, memory and audit replay built in.

Orbi — the factory that builds and operates AI software factories. GitHub Issues in, releases and runnable system out

Open-source AI agent harness in native Rust — GUI, CLI, headless, and webapp from one binary. Multi-provider, MCP, skills, plugins, agent teams.

The SDK for browser agents. Interact, search, extract, and fetch any site reliably across the web

Agent-native shopping for extreme value: verifiable same-product price evidence, checkout, orders, delivery, and after-sales.

The extensible power-user platform for Google Antigravity. Adds a native In-App Browser, animated Desktop Pets, revamped Gemini UI, and custom BYOK Gemini Pro k…

Open-source, single-binary, self-hosted AI agent — your models and data stay on your machine. A coding agent on par with Claude Code and a personal assistant li…

Your pocket agent. Local-first AI agents on iOS and Android — real workspaces, tool execution with approvals, and your choice of model (DSH · Claude Code · Code…

Bridge between QQ (SnowLuma OneBot v11) and DeepSeek Harness agents: social simulation, safe MCP tools, slang learning and more.

A 7×6 framework for agent architecture. 28 patterns, each placed at a coordinate, runnable Python code with verified engineering slices from Claude Code, Aider,…

针对 AI 自动化渗透 Agent 的新一代反制蜜罐，通过反向代理将API密饵载入真实业务、反向提示词注入等方式反制自动化渗透 Agent，实现多款主流通用Agent的反制上线控制。

Open-source, local-first AI agent for coding and real work. BYOK models, MCP, skills, plugins, workflows, and private knowledge bases.

A free AI-agent toolbox for Android, 一站式安卓AI Agent工具箱

Google Workspace CLI — one command-line tool for Drive, Gmail, Calendar, Sheets, Docs, Chat, Admin, and more. Dynamically built from Google Discovery Service. I…

Independent, unofficial CLI to edit CapCut and JianYing (剪映) projects — subtitles, timing, speed, volume, templates, cut long-form to shorts. No API needed, rea…