LLM Mart Basic

Prepare commercial proposals and client responses - structure, pricing presentation, and persuasive framing. Use for quotes, offers, and project proposals.

Run the full release-readiness gate - code review, security, performance, tests, docs, and metrics in one orchestrated pass with a go/no-go verdict. Use before releases, merges to main, or client deliveries.

Build and evaluate RAG corpora - ingest, chunk, embed, index, and spot-check retrieval quality. Use when creating knowledge bases for agents.

Listed real-estate skill for the Trading Agent OS. REITs and foncières by country. No invented listing prices.

Assemble recurring or one-off business reports - data, charts, narrative, and formatted output (PDF/DOCX/Markdown) - from multiple sources. Use for weekly/monthly reports and study deliverables.

Respond to RFPs, RFQs, tenders, and cahiers des charges - compliance matrix, requirement mapping, and structured answers. Use for formal procurement responses.

Run RiskLens on any plan, launch, product, hire, strategy, or decision. Assumes it already failed 6 months from now and works backward to find every reason why. Produces a revised plan with blind spots exposed. Use for /risklens, "run risklens", "risklens this", "what could kill

Prepare salary and package negotiation for a specific offer - market range, anchors, counters, and email drafts. Use before answering a recruiter on compensation.

Generate sales offers, quotes, and commercial proposals with pricing options and decision-ready framing. Use when a qualified prospect asks "send me something".

Orchestrate any web scraping job to delivery - static, paginated, infinite-scroll, mass crawl, sitemap, JS pages via browser. Export datasets until done.

Write scrapers with the official Scrapling 0.4.14 API (Fetcher, StealthyFetcher, DynamicFetcher, sessions, Spider templates, adaptive CSS). Default framework in the Scraping module. Fall back to the scrape tool or browser only when Scrapling is the wrong tool.

Handle secrets safely via env vars, Vault, AWS Secrets Manager, or encrypted stores - never paste keys into chat, commits, or logs. Use when configuring APIs, CI, or cloud credentials.

Hunt for leaked credentials - hardcoded API keys, tokens, private keys, passwords and connection strings in code, config, logs and git history. Use for /unmask, pre-commit secret sweeps, or "did we leak a key?" questions.

Run a full application security audit - auth flows, input validation, secrets handling, injection surfaces, dependency risks, and hardening. Use for /fortify, pre-release security reviews, or "is this safe?" questions.

Recover from tool failures and flaky commands with intelligent retries, alternate tools, and clear fallbacks. Use when exec, network, or MCP calls fail mid-task.

Write search-optimized articles that read naturally - proper structure, intent match, and internal links, without keyword stuffing. Use for blog posts, guides, and landing page copy.

Pull real SEO metrics (search volume, keyword difficulty, SERP, backlinks) from DataForSEO or Semrush when API credentials are present. Use before inventing volumes; fall back to qualitative methods when keys are missing.

Track rankings, traffic signals, technical errors, and competitor changes over time, with scheduled checks and alerts. Use to maintain SEO performance after fixes.

Audit technical SEO - indexation, sitemap, robots.txt, Core Web Vitals hints, redirects, canonical tags, and crawl errors. Use when a site underperforms in search or before a relaunch.

Run shell commands with strict limits - prefer workspace sandbox, avoid privileged ops, and quote unsafe output. Use whenever exec is required.

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.

`crabbox shard` forks a [checkpoint](checkpoint.md) into `--count` leases

`crabbox share` grants other people access to an existing lease through the

`crabbox ssh` resolves a lease and prints a ready-to-run `ssh` command for it.

`crabbox status` prints the current state of a lease: its slug, provider,

`crabbox stop` ends a single lease. For coordinator-backed and direct cloud

`crabbox sync-plan` prints the local sync manifest and its size hotspots

`crabbox tunnel` opens one foreground SSH local port-forward to a resolved

`crabbox unshare` removes sharing rules from a coordinator-backed lease. It is

`crabbox usage` reports lease cost and usage estimates from the broker, broken down by user, organization, or the whole fleet.

`crabbox verify` checks a signed run receipt produced by `crabbox run --attest`.

`crabbox vnc` prints (or opens) the connection details for a desktop-capable

`crabbox warmup` leases a box and waits until it is ready: it provisions (or

`crabbox watch` runs a command on a warm lease, then watches the local

Linux portal viewers default to **Match window**: only the connected controller

`crabbox whoami` calls the broker's `/v1/whoami` endpoint and prints the

Vet a new or changed third-party dependency for license, provenance, and supply-chain risk before any install runs.

Inspect ADR health read-only; optionally select one ADR with --adr N.

{{SKILL_ENTRY:decision-lifecycle}}

Assemble the governance record for a range — commits, overrides, ADRs, sprint auto-decisions, open questions, checkpoint findings — into one dated audit packet. Read-only.

Lightweight Q&A about the project — answer from context and return, no routing, no state change.

Offline-first Python AI agent that runs a tiny research business: quotes each job against its own costs, collects via Stripe, fulfils with NVIDIA Nemotron, pays…

DSH 插件 · 注入式优化器 0.8（主线）：你照常说话，它在你发送后,AI接收前把"这一轮到底要什么"理清楚，再把这份理解交给工作 AI(上下文注入) —— 原话不改写，条条带逐字依据。含控制界面（档位/权限/模型/上下文/只读工具）、拦截浮层（思维层+产出层）与真实 token 用量。可明显提升大多数模型的发挥稳…

Reliable AI Skill + MCP toolkit for agent-driven desktop CAD automation.

Curated real-world use cases for Hermes Agent — the self-improving AI agent from Nous Research. Backed by primary sources.

AI Agent 教学仓库 | 系统化 LangChain、RAG、LangGraph、MCP 全栈实战代码 | 万字博客详解 | 开源可运行示例 | 从零构建智能体

从 0 复刻 WorkBuddy-style 桌面 AI 助手 Harness：24 章 Python 教程，覆盖 Agent Loop、工具调用、记忆系统、Sidecar、沙盒审计、DeepSeek/OpenAI 评测轨迹

MCP server and CLI tools for web search and crawling, built on SearXNG and Crawl4AI

Delta MCP is a free app that sits between your AI apps and their MCP servers: one program per task instead of one tool call per step, up to 24.1× fewer tokens i…

Ava turns any Android 5+ device into a voice-first Home Assistant kiosk. Native C++ under the hood, so a 10-year-old tablet still listens, talks, and runs the h…

Roblox Studio macOS Window Capture Fix 2026: Real Screenshot Tool Instead of Magenta Playtest Glitch

LabTether