LLM Mart Basic

端到端测试（生成或执行 E2E 用例）

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

全自动 Bug 修复（定位→复现→修复→测试→文档）

国际化（i18n）

按设计文档和已有测试用例实现代码（带前置守卫、自检、handoff）

代码质量检查与自动修复

打印循环下一步应执行的命令（机器可读，供 loop 驱动）

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

新人引导 / 自动化生成用户手册

性能优化

创建 PRD 文档（自动化生成 + 自检 + handoff）

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

代码重构（保持外部行为不变，改善内部结构）

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

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）

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.

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

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

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

Treat an AI agent skill as both an instruction package and a software dependency: inspect what it says, what it runs, what it can access, and how it updates.

SMARTS arbitration — reconcile architectural artifacts against the scaffold and prior decisions; every variance resolved by an explicit, user-attributed choice.

Restructure code with behavioral parity proven through unmodified pre-existing tests, then refactor. No behavior change.

Cut a release the only sanctioned way — derive the target's declared version policy from the commit log, roll its changelog, compose an annotated tag, and optionally publish its exact declared assets. Takes the declared target's name as its only argument, or --dry-run to preview one with no write. The only path to a version tag.

Review a diff with the reviewer fleet, funneled to one triaged verdict. Targets the current working diff, a path, or an inbound GitHub PR.

Exploratory spike on a throwaway branch — answer a named question with disposable code. Never merges; exits to a findings note or {{CMD:feature}}.

Autonomous sprint — one interactive spec gate, then plan-to-PR execution with every auto-decision SMARTS-scored and logged. Hard gates remain true stops.

Daily repo hygiene — review the day's repo state, then perform the cleanups under per-action confirmation. Fast-forward only, never destructive without a yes.

Show the project's current state at a glance — stage, open tasks, open questions, overrides since the last checkpoint, current branch. Read-only.

Wire codeArbiter's statusline into ~/.claude/settings.json, or remove it.

The sanctioned task-board mutator — add a queued task, start one (flips to in-progress and stamps the date, minting a dotted ID on pick-up), or mark an in-progress task done. The only blessed write to open-tasks.md.

Opt-in lightweight STRIDE pass for a sensitive feature before implementation. Not a routine gate — invoke it when a change warrants security thought.

Deep, rarely-convened whole-codebase audit — eleven specialist lenses, a resumable on-disk audit log, findings filed as GitHub issues on approval. Expensive; estimates cost and STOPs before running. Never a required gate.

Watch a PR's CI to completion — diagnose on red, notify and offer the merge on green. Never auto-merges.

Copy a file OUT of a running sandbox box to the host — host-initiated egress only (docker cp). The reverse, a host→container bind, is impossible by construction.

Tear down a sandbox box — remove its container and named volume. --keep-volume leaves the volume; with no id, prune reclaims any leaked ca.sandbox=1-labeled object. Cached images are retained.

Run a single command inside a running sandbox box and capture a JSON result — exitCode, separate stdout/stderr, and a truncated flag past the byte cap. The scriptable exec seam.

Open an interactive shell inside a running sandbox box at /work/repo. Read-only root, non-root user, no host-FS access — explore the untrusted code interactively, then exit.

Pull an untrusted repo into an ephemeral, host-FS-isolated Docker container — clone into a named volume, build a dep-cached image, run under structural isolation. Network defaults to offline. Requires Docker and nixpacks.

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

Report the health of Architecture Decision Records — aged, unchallenged, supersession candidates, unresolved CONFIRM-NN. Read-only.

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