LLM Mart Basic

Choose simple, maintainable software designs by removing speculative complexity, comparing alternatives, and making explicit tradeoffs. Use for architecture, API, data-model, dependency, and scope decisions.

Implement software through small, repeatable, integrated vertical slices with clear exit criteria and honest verification. Use when a design is understood and code needs to be built or changed.

Review software with careful attention to correctness, maintainability, security, operations, and meaningful detail. Use for diffs, branches, pull requests, architecture decisions, or final quality checks.

Author a greenfield build blueprint in four gated stages — business logic, tech stack, logic-to-stack mapping, and a phase plan — each requiring explicit user approval before the next. Use when building a new project or a substantial new subsystem from scratch.

Step 0 of consequential software work under Monozukuri. Classify the task, assess its risk tier, choose execute or sensei mode, and compose the sequence of Monozukuri skills and the Definition of Done for it. Skip for trivial one-line edits, pure questions, and throwaway scripts.

Clarify software goals, constraints, stakeholders, and risks before consequential design or implementation work. Use for greenfield ideas, ambiguous requirements, architecture decisions, or changes where misunderstanding would be costly.

Prevent software mistakes through strong boundaries, safe defaults, meaningful tests, and mechanically enforced invariants. Use for TDD, validation, schemas, authorization, edge cases, regression coverage, or reliability-sensitive behavior.

Prepare software for responsible release, migration, deployment, rollback, and handoff with evidence about compatibility, health, ownership, and recovery.

Use when creating or updating AGENTS.md files, .github/copilot-instructions.md, or other AI agent rule files, onboarding AI agents to a project, standardizing agent documentation, or when anyone mentions AGENTS.md, agent rules, project onboarding, or codebase documentation for AI

Record a decision, document existing code, or file a supplied research material. Modes: document decision (ADR, RFC, or rule), document code (spec, doc, guide, or scenario for existing behavior), document research (only when a finished report or one external material is already i

First-time Archcore setup. Wires the host (MCP config, hooks, CLAUDE.md/AGENTS.md managed block), measures the authored context the repo already holds, then composes a first-day seed — stack rule, run guide, data-model, integrations, config, entry points, public surface, a linked

Plan a feature or initiative through a computed route: the conductor derives the canon delta and assembles the document package — from a zero-document null route for small fixes to an umbrella PRD with one spec per capability for large initiatives. Modes, named as the first word:

The pre-merge review of a branch in a project that records its specs, decisions, and rules in .archcore/. Run this first for 'review my branch', 'review the changes before merge', or 'review before merge': it checks the changed code against the project's recorded canon and the ch

Pull a Korean brand's published DESIGN.md from the ko-design-md catalog (getdesign.kr) and apply its design language — colors, typography, spacing, radius, components, do's & don'ts — to the UI you are building in the CURRENT project. Use this skill whenever the user wants to bui

Add a new design.md catalog entry to ko-design-md. Use this skill IMMEDIATELY when the user wants to onboard a new brand into THIS project's catalog — produce services/{slug}.md (Stitch v0.1 format) plus services/{slug}.tokens.json (token-card sidecar) plus public/preview/{slug}/

프리뷰 산문(public/preview/*/preview.html — 라이트·다크 한 파일의 캡션 등 글 전체)이 services/*.md 나 상류가 뒷받침하지 않는 주장을 하는지 대조·판정할 때 쓴다. 판정 근거의 등급, 상류(Claude Design 번들 또는 브랜드 발행물) 확인 절차, 슬러그별 상류 판정표, 그 되돌리기가 남긴 판정 규칙을 담는다. 프리뷰 산문을 고치거나 "md에 없다"를 근거로 프리뷰를 정정하려 할 때 반드시 먼저 읽을 것.

Plug-in web search, X (Twitter) search, and page fetch for models without native web access. Use whenever the task needs current information, external facts, source links, posts from X, or the content of a specific URL, and the active model/harness has no native search or fetch t

添加新的前端应用

添加新的微服务

旧项目接入 PDLC

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.

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.

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.

Open-source super AI assistant & Agent Harness. Plans tasks, runs tools and skills, self-evolves with memory and knowledge. Multi-model, multi-channel. Lightwei…

Open-source AI browser agent for web automation: a web browsing agent and computer-use agent in plain English. Browser MCP for Claude Code and Gemini CLI.

Agent-native trading terminal built on DeepSeek Harness. Crypto, US, CN and HK in one three-column GUI, 19+ hot-swappable connectors, dry-run by default with hu…

Open-source desktop and web coding agent with a first-party host and harness, durable sessions, model connections, streaming chat, and workspace tools.

OrcaReplay — Time travel for AI agents. Record, replay, fork, and debug any agent run with any model. Built by the OrcaRouter.ai team.

A complete toolkit for connecting R and LLMs

OpenSRE — the memory-first AI SRE. Self-hosted incident investigation with episodic memory, knowledge graph, web console, Slack & Teams. opensre.in

A desktop AI coding assistant that works with your local projects. Ally helps you understand code, edit files, search a workspace, manage tasks, and complete de…

【在线免费使用】 简单快速将SQL或DBML转换为美观的ER图（支持 Agent Skill）/ The best SQL to ER Diagram converter (Support Agent Skill).

Operation-bound protection for autonomous AI agents: contain and verify operations before committing changes, understand intent and risk across long-running wor…

Local-first AI coding agent desktop: Electron + Rust host core + pi Agent Harness + user-installable plugins

Local-only Go static analysis engine with a built-in MCP server. Gives AI coding agents deterministic structural awareness: call graphs, impact analysis, symbol…

Self-hosted AI agent workspace with tool calling, MCP, multi-model routing, sandboxed execution, multi-agent workflows, and LLM-authored 3D character animation…

Automated TDD enforcement for Claude Code

High-performance platform for building websites, e-commerce, and web applications—with Native AI, JavaScript development, and a marketplace for portable sites a…

Autonomous AI-agent orchestration engine for job discovery with decision traces, tool adapters, and production-grade run control.

Token efficient Claude Code full Python rebuild. AI Coding Agent in 310K LoC Python.

OPC — One Person Company. A full team in a single Claude Code skill. Adaptive agent orchestrator with 21 built-in roles, 6 flow templates, and adversarial quali…

Open-source, secure environment with real-world tools for enterprise-grade agents.

MCP server for AI-powered GitHub project management — agent orchestration, PRD-to-issues pipeline, sprint planning, and multi-agent swarm coordination