LLM Mart Basic
@llm-mart · Joined Jun 2026
迭代复盘——读状态机历史出趋势报告
安全审计
交互式配置 PDLC(当前:状态栏 statusline 的启用/停用/展示项)
发布工作流(收评审通过的功能 → 跑测试 → bump VERSION → 更 CHANGELOG → tag)
管理 00_standards 规范型 surface 产物(add/edit/archive/index)
查看项目 PDLC 状态总览(读 docs/.pdlc-state/ 输出进度)
阶段内任务跟踪(创建/更新任务列表,附在工作流上)
TDD 测试先行(按设计文档生成失败的测试用例)
立测试地基(探测技术栈 → 验证并生成 test-commands.yml → 脚手架测试目录 → 接本地钩子)
UI/UX 设计
UI/UX 专业设计(PDLC 集成层,依赖 ui-ux-pro-max)
Answer questions about the AI SDK and help build AI-powered features. Use when developers: (1) Ask about AI SDK functions like generateText, streamText, ToolLoopAgent, embed, or tools, (2) Want to build AI agents, chatbots, RAG systems, or text generation features, (3) Have quest
Builds Python components using the compone framework for type-safe HTML/XML/RSS generation. Use when working with compone, creating Python components, generating markup in Python, or building framework-agnostic component libraries.
Use this when working in a project with devenv.nix, or when devenv.sh development environment setup, services, dependencies, or Nix packages are relevant.
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.
Analyze Hacker News thread sentiment from a provided HN thread URL.
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
Write clean, readable Pythonic code. Use this skill any time you write or change a Python file.
Predict protein 3D structures with AlphaFold2 via ColabFold — MMseqs2-accelerated MSAs, monomer and AlphaFold2-Multimer complex folding, and confidence-based validation (pLDDT, pTM/ipTM, PAE). Use when folding a protein sequence or complex from FASTA, generating a predicted struc
Build, slice, concatenate, read, and write AnnData annotated data matrices (obs, var, X, layers, obsm, uns) — the scverse data STRUCTURE, not an analysis pipeline. Use when creating or wrangling .h5ad/zarr files, managing cell and gene annotations, concatenating batches, or handl
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.
/session-learning-capture
Session learning capture
Capture and document session learnings
/setup-automated-releases
Setup automated releases
Setup automated release workflows
/setup-cdn-optimization
Setup cdn optimization
Configure CDN for optimal delivery
/setup-comprehensive-testing
Setup comprehensive testing
Setup complete testing infrastructure
/setup-development-environment
Setup development environment
Setup complete development environment
/setup-formatting
Setup formatting
Configure code formatting tools
/setup-kubernetes-deployment
Setup kubernetes deployment
Configure Kubernetes deployment manifests
/setup-linting
Setup linting
Setup code linting and quality tools
/setup-load-testing
Setup load testing
Configure load and performance testing
/setup-monitoring-observability
Setup monitoring observability
Setup monitoring and observability tools
/setup-monorepo
Setup monorepo
Configure monorepo project structure
/setup-rate-limiting
Setup rate limiting
Implement API rate limiting
/setup-visual-testing
Setup visual testing
Setup visual regression testing
/share-your-story
Share your story
Open the Build with Claude contribution guide for writing a community story
/simulation-calibrator
Simulation calibrator
Test and refine simulation accuracy with validation loops, bias detection, and continuous improvement frameworks.
/sprint-planning
Sprint planning
Plan and organize sprint workflows
/standup-report
Standup report
Generate daily standup reports
/start
Start
Initiates the task orchestration workflow using the three-agent system (task-orchestrator, task-decomposer, and dependency-analyzer) to create a comprehensive execution plan.
/status
Status
Check the current status of tasks in the orchestration system with various filtering and reporting options.
/svelte-a11y
Svelte a11y
Audit and improve accessibility in Svelte/SvelteKit applications, ensuring WCAG compliance and inclusive user experiences.
Open‑WebUI Tools is a modular toolkit designed to extend and enrich your Open WebUI instance, turning it into a powerful AI workstation. With a suite of over 15…
26 views 0 likesThe token-efficient agentic coding workbench. Built for a future where every token counts — it optimizes token usage at the agent-loop level, saving 70%+ on lon…
16 views 0 likesMCP server for controlling a real iPhone via macOS iPhone Mirroring...and any MacOs app. Screenshot, tap, swipe, type — from any MCP client.
10 views 0 likesOne desktop for all your AI coding Agent — Claude Code, Codex CLI & Gemini CLI. Auto-detect, one-click install, unified chat, file explorer, terminal & editor.…
21 views 0 likesPi — A cross-platform AI coding agent, bringing the Claude Code experience to your desktop. No environment setup, no terminal commands. Download and start codin…
12 views 0 likesDeepSeek Harness Desktop (dsh-desktop). EAC: Embracing All Creation (揽尽万象). Bundled Node.js runtime with full dsh-CLI kernel, one-click startup, 10 built-in UI…
13 views 0 likesA telegram bot for searching and auto-saving.
13 views 0 likes金蝶云星空 K3Cloud MCP Server,让 AI 助手(Claude Desktop、Claude Code、Cursor、Cline、Cherry Studio、Openclaw 等任意支持 MCP 协议的客户端)通过自然语言查询和操作金蝶 ERP 系统。
19 views 0 likesRewrite frontier research using allegorical structural mapping.
13 views 0 likesFree4Chat is a temporary collaboration fabric for Humans and Agents.
11 views 0 likesGive any AI agent a full desktop — it sees the screen, clicks, types, and runs apps like a human. Automate anything with a UI: browsers, legacy software, intern…
11 views 0 likesA personal AI agent that can work safely on your machine, remember useful context, and keep its data under your control.
11 views 0 likesA framework for AI-driven economic activity. Declarative, composable, observable, deterministic.
12 views 0 likesOpen-source, self-hosted customer support desk in a single binary. A lightweight alternative to Intercom, Zendesk, Chatwoot.
13 views 0 likes54 rigorous skills for Codex, OpenCode, and Pi: code review, security audit, feature development, frontend design, MCP tools, Hugging Face ML/training, and more…
18 views 0 likesA wonderful list of Game Development resources.
11 views 0 likesOpen Science Desktop — local-first, model-agnostic AI research workbench for macOS, Windows & Linux. Open-source Claude Science desktop alternative built on Tau…
11 views 0 likesLexora — Personal AI workspace built around Desktop / 以 Desktop 为核心的个人 AI 工作台
11 views 0 likesOpen-source, AI-native Evernote alternative with native MCP. Zero-cost on Cloudflare or self-hosted with Docker.
11 views 0 likesFull job-hunt Claude skill bundle — Job Description decoder + Resume builder (11 templates) + Behavioral Interview / story bank. Three self-contained sub-skills…
11 views 0 likes