LLM Mart Basic

根据真实业务与数据处理事实生成隐私政策和服务条款页面草稿。支持明确输入与结果回读。Use to draft website privacy

把重复操作封装成通用 Skill，并按需提供宿主 slash command 适配入口。支持明确输入与结果回读。Use to turn a

将已有 clone 连接到用户自己的 GitHub 仓库并保留来源与历史。支持明确输入与结果回读。Use to publish a cloned

生成 changeset 草稿并提供编辑入口，审阅后验证版本计划。支持明确输入与结果回读。Use to create a changeset

根据实际包变更生成 changeset，并按请求更新版本与 CHANGELOG。支持明确输入与结果回读。Use to manage package

从已核实的社区地址或仓库列出可访问的 XBTI 人格测试案例。支持明确输入与结果回读。Use to browse a gallery of

用真人尽调思路校验用户提出的事实命题：拆解可验证问题、检索一手资料、 交叉验证证据链，并给出带置信度和不确定边界的结论。 Trigger when the user asks to fact-check, verify a claim, confirm whether something is true, source-check an answer, or mentions "事实校验", "帮我确认", "这是真的吗", "verify this", "fact check", "source check", "due diligence".

Create learner-friendly English subtitles with level-aware glosses and

Use when the user asks to find and download a film, series, or long video. 以 aria2 为默认传输后端，完成多源测速、续传、容量预检、版本核验与字幕验收；也适用于“帮我下载这部电影”。

面向中国大陆网站的一站式备案与上线 Skill Kit：当用户说“办 ICP 备案”“做公安联网备案”“备案后绑定域名”或 "handle China website filing" 时，按权威页面完成材料、审核、域名切换、合规展示与巡检留痕。

给纯文本模型"看图"：调用智谱 GLM-4V-Flash（免费）把图片转成文字描述。当用户要求描述/识别/读取图片，或任务里出现图片文件（截图/图表/照片）而当前模型无法直接看图时，优先调用本 skill。需要图片磁盘路径，可附带具体问题。

把需求、现有界面与真实素材落实为有辨识度、交互一致的前端，覆盖页面、组件、导航、GSAP 展示及图片音视频。触发：设计前端、界面不够专业、制作交互案例集；design or refine a frontend UI.

面向公众号、网站、App、策划案、海报等真实发布场景，为读者可见文本建立受众、品牌角色、组件惯例与信息可见性门禁。Use when generating, editing, rendering, publishing, or reviewing audience-facing copy for brand and context fit.

把单人照片用 gpt-image-2 重绘成身份保真的 Riso 头像，并检查五官、手指、饰品与圆形裁切。Use when the user asks“做成 Riso 人像”“生成孔版印刷头像”or “create a Riso portrait”。

从产品与品牌事实出发，独立推导适合当前产品的定位、叙事与视觉，并完成 Landing Page 实现、响应式和生产回读；适用于创建官网、品牌官网重构、产品价值不清或视觉与产品不匹配。

Initialize or refactor a frontend project to use TanStack Query as the unified server-state layer. Use when the user asks to install TanStack Query, initialize query infrastructure, migrate ad hoc fetch/invoke/useEffect request state, standardize query keys, or make app network r

Use when the user asks for "App生成器", "生成 Web App", "生成 Tauri App", "生成原生 macOS App", "Finder Quick Action", "只创建 web", or to standardize an existing app with branding, CI/CD, native integration, and Lovinsp where applicable.

为 Electron 桌面应用设计、实现和验证增量自动更新，覆盖 macOS Sparkle、签名、appcast、发布产物与失败拦截。用户提到增量更新、Sparkle、检查更新、appcast、DMG 更新或 delta updater 时使用。

Publish or submit a validated Skill. Default to the LovStudio official website, run lov-skill-pricing automatically, and use other channels only when explicitly named.

重置 Obsidian 缓存，解决卡在 "Loading cache..." 的问题。 当用户说 "obsidian 卡住"、"loading cache"、"obsidian 打不开"、"重置 obsidian 缓存" 时触发。 Trigger when the user mentions Obsidian startup hangs, cache reset, or "Loading cache".

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.

{{SKILL_ENTRY:refactor}}

{{SKILL_ENTRY:release}}

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.

{{SKILL_ENTRY:security-architecture}}

{{SKILL_ENTRY:tribunal}}

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.

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

Record user-decided ADRs or inspect their health read-only. Preserve attribution and acceptance evidence.

Atom Agent, Open-Source Governed AI Agent Platform for Self-Hosted Automation

The agent engineering intelligence harness, optimized tools, memory system, subagents and mixture of models packages ⚚

Sesori iOS/Android app and the Sesori Bridge CLI — drive Claude, Codex, OpenCode, Cursor, Pi, OMP, Hermes coding sessions from your phone

🧠 RepoBrain (formerly Antigravity) — Give your repo a brain. ChatGPT for your codebase: works in Claude Code, Cursor, Codex, Windsurf & more.

Use ChatGPT (Codex), Claude, and Grok (X Premium) subscriptions as DeepSeek Harness LLM providers — OAuth login in the web UI, no API keys

Latitude is the open-source AI monitoring platform.

Open-source AI browser agent for Chrome and Firefox (monorepo) 🧠

Official Model Studio CLI（阿里云百炼 CLI）built for AI Agent frameworks, exposing models, search, multimodal, and workflow capabilities as structured tool calls.

Curated DeepSeek Harness (DSH) plugins, extensions, tools, skills, clients, runtimes, integrations, and verified references — English and Chinese.

Turn papers, code, and docs into presentation-ready, natively editable PPTX in Codex / Claude Code. Native charts and equations, speaker notes, click-build anim…

Grix : Work with agents like talking to people.

Local First Ai Agent. Optimized for Local Ai models. Long context window. Proper tools callings. Runs privately on your device.

Model Context Protocol server that integrates AgentQL's data extraction capabilities.

AI that ships your tickets.

Metadata-driven CLI for AI Agent Bots — 48 operations across 7 domains, structured JSON envelope I/O, zero interactive prompts.

An open-source, extensible, self-hosted agent workspace with multi-runtime support for Codex, Claude Code, and more, plus reusable local apps for custom interfa…

Open-source Windows desktop client and GUI for DeepSeek Harness — zero-setup installer with Codex, plugins, skills, SSH, mobile remote access, and 11 skins.

The open-source AI workbench for scientific research

DeepSeek-native AI coding agent for your terminal. Engineered around prefix-cache stability — leave it running.

A Fully free agentic browser driver for AI , few tools, full control, real stealth, top-tier token efficiency.