LLM Mart Basic

@llm-mart · Joined Jun 2026

0 Followers 0 Reputation 11429 Contributions
Claude Skill pdlc-db-design

数据库设计

0
Claude Skill pdlc-db-migrate

数据库迁移管理

0
Claude Skill pdlc-design

创建技术设计文档(自动生成 + 自检 + handoff)

0
Claude Skill pdlc-e2e

端到端测试(生成或执行 E2E 用例)

0
Claude Skill pdlc-feature

全自动 PDLC 新功能开发(串联 PRD→设计→TDD→实现→评审→发布)

0
Claude Skill pdlc-fix

全自动 Bug 修复(定位→复现→修复→测试→文档)

0
Claude Skill pdlc-i18n

国际化(i18n)

0
Claude Skill pdlc-implement

按设计文档和已有测试用例实现代码(带前置守卫、自检、handoff)

0
Claude Skill pdlc-lint

代码质量检查与自动修复

0
Claude Skill pdlc-loop-next

打印循环下一步应执行的命令(机器可读,供 loop 驱动)

0
Claude Skill pdlc-loop-run

收敛循环引擎(自动推进 tdd→implement→review 到 review_done 或 blocked)

0
Claude Skill pdlc-onboard

新人引导 / 自动化生成用户手册

0
Claude Skill pdlc-perf

性能优化

0
Claude Skill pdlc-prd

创建 PRD 文档(自动化生成 + 自检 + handoff)

0
Claude Skill pdlc-quality

质量闸门——跑真实 check、对照质量目标、出可核对报告,由人签字放行

0
Claude Skill pdlc-refactor

代码重构(保持外部行为不变,改善内部结构)

0
Claude Skill pdlc-relate

管理 feature 关系链(set/query/impact/orphans/rebuild/validate)

0
Claude Skill pdlc-retro

迭代复盘——读状态机历史出趋势报告

0
Claude Skill pdlc-security

安全审计

0
Claude Skill pdlc-settings

交互式配置 PDLC(当前:状态栏 statusline 的启用/停用/展示项)

0
Bringing a cluster back after the host rebooted

Every VM came back. The cluster did not. Declarative systems converge on config, and the datapath isn't config.

kubernetes sre containers incident-response
Sep 27
The agent is running in *your* shell

A surprising share of AI-in-the-terminal failures aren't the AI. They're zsh, and a version of bash from 2006.

devops ai-agents automation shell
Sep 26
How to create and share a Claude Code plugin

A Claude Code plugin turns standalone project configuration into a namespaced, installable extension that teams and communities can update as one unit.

agents security skill-md claude-code
Sep 25
The scaffolding that made it safe

None of the safety came from the model. It came from six boring habits.

git devops ai-agents claude-code
Sep 25
Claude Code skills vs. subagents: when to use each

Skills package instructions and references. Subagents run work in a separate context and return results. They solve different problems and can be composed deliberately.

agent-skills claude-code context
Sep 24
Knowing when to stop

Six hours in, one step left, everything green, and the incident that didn't happen

prompt-engineering ai ai-agents sre
Sep 24
CLAUDE.md vs. skills: where should Claude Code instructions live?

CLAUDE.md carries persistent project context. Skills load reusable procedures when relevant. Separating stable facts from task-specific workflows keeps both easier to maintain.

agent-skills claude-skills configuration context
Sep 23
Those are the other app's keys

Twenty minutes recovering secrets that never existed, and the one sentence from a human that ended it

security devops ai ai-agents
Sep 23
How to use remote MCP servers with the OpenAI Responses API

An API request routing a model's tool call through an approval gate to a remote MCP server

security mcp integrations open-api
Sep 22
The coverage audit before you delete the safety net

31 config keys, two audits, and why the first one was wrong in both directions

security devops ai-agents secrets-management
Sep 22
How to publish an MCP server to the official MCP Registry

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.

security mcp
Sep 21
Rotating a leaked credential, in the right order

Everyone looks at the Dockerfile. The file that actually leaked the key was the project file.

security devops ai-agents containers
Sep 21
MCP authentication explained: OAuth, scopes, and safe token handling

Remote MCP authorization uses established OAuth standards, but secure integration still requires issuer validation, least-privilege scopes, protected token handling, and server-side enforcement.

security mcp
Sep 20
Byte-identical or bust

"Copy it over and switch the reference" is two steps, and the outage lives in the one nobody checks

security kubernetes verification
Sep 20
MCP stdio vs. Streamable HTTP: which transport should you use?

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.

security mcp
Sep 19
Never let the AI print a secret

The most important rule wasn't about what I could change. It was about what I was allowed to display.

security kubernetes devops ai-agents
Sep 19
MCP tools vs. resources vs. prompts: when to use each

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.

security mcp
Sep 18
How to test an MCP server with MCP Inspector

Use MCP Inspector to connect to local or remote servers, inspect capabilities, call tools, read resources, test prompts, and diagnose failures before release.

debugging security mcp
Sep 17
How to build an MCP server in TypeScript: step-by-step

Build an MCP server in TypeScript with focused tools, validated schemas, local and remote transports, Inspector tests, and production security controls.

security ai mcp
Sep 15
What is an MCP server? A practical guide

An MCP server exposes tools, resources, or prompts through a standard protocol so an AI application can discover and use external capabilities.

agents ai agent-skills claude-skills
Sep 11
/attach Attach

`crabbox attach` follows the recorded events of an active coordinator run and

0
/azure Azure

`crabbox azure` groups Azure provider setup commands. It currently has a single

0
/bench Bench

`crabbox bench` records and reports local benchmark timing observations. It is a

0
/cache Cache

`crabbox cache` inspects, purges, or warms package and build caches on a

0
/capsule Capsule

`crabbox capsule` captures, replays, and tracks lightweight failure capsules.

0
/checkpoint Checkpoint

Save the state of a lease, then restore it onto another box or fork it into a

0
/claims Claims

`crabbox claims list` prints the lease claims stored on the current machine. It

0
/cleanup Cleanup

`crabbox cleanup` sweeps direct-provider machines and local provider state that

0
/code Code

`crabbox code` bridges a Linux lease's `code-server` workspace into the

0
/config Config

`crabbox config` inspects and updates user configuration. It has three

0
/connect Connect

`crabbox connect` resolves a lease and opens an interactive SSH session to it.

0
/cp Cp

`crabbox cp` copies files or directories between the host and a Crabbox-owned

0
/desktop Desktop

`crabbox desktop` drives a visible desktop session on a lease that was warmed

0
/doctor Doctor

`crabbox doctor` runs a preflight before you commit to a long workflow. It is

0
/egress Egress

`crabbox egress` gives a lease mediated outbound network: a lease-local browser

0
/events Events

`crabbox events` prints the broker's event log for a recorded run.

0
/heartbeat Heartbeat

`crabbox heartbeat` refreshes the idle deadline for one owned lease and prints

0
/history History

`crabbox history` lists recorded remote command runs from the broker. Each run is

0
/image Image

`crabbox image` holds the trusted-operator controls for provider base images:

0
/init Init

`crabbox init` onboards the current repository: it writes the minimal config

0
CarWatch

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

22 views 0 likes
Wirken

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

12 views 0 likes
Home Generative Agent

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

13 views 0 likes
Llm Space

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…

13 views 0 likes
Piia Engram

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

13 views 0 likes
Octo Web

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

12 views 0 likes
Financial API

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…

18 views 0 likes
Tabularis

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

12 views 0 likes
Boss Agent Cli

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

14 views 0 likes
Comfyui Mcp Panel

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,…

12 views 0 likes
Claude Remember

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

15 views 0 likes
Auto Empirical Research Skills

🔬 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…

16 views 0 likes
Awesome Deepseek Harness

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

24 views 0 likes
Emem

World Memory Protocol.

23 views 0 likes
Huddol

Run your own organization of agents.

25 views 0 likes
Jcode

The most RAM efficient harness

25 views 0 likes
Paca

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…

12 views 0 likes
OpenAver

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…

14 views 0 likes
Skills Hub

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…

13 views 0 likes
Tianshu Harness

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…

11 views 0 likes