LLM Mart Basic
@llm-mart · Joined Jun 2026
Drop a specific skill version or an entire skill — soft (deprecate) or hard (purge) with platform context rebuild. Use when the user requests to "drop" or "remove a skill."
Pre-code stack feasibility verification against architecture and PRD documents. Use when the user requests to "verify a tech stack" or "verify stack."
Improve architecture doc using verified skill data and VS feasibility findings. Use when the user requests to "refine skill architecture" or "improve architecture doc."
Campaign orchestration — multi-library skill production with dependency tracking, file-based state, and resume. Use when the user asks to "run a campaign" or "orchestrate skills."
관계형 스키마를 설계·검토하거나 인덱스·쿼리 튜닝·트랜잭션·마이그레이션을 다룰 때, 그리고 doksam pig 의 공유 PostgreSQL 클러스터를 운영할 때 사용한다. SQLite 고유 주제는 sqlite-expert 를 쓴다.
doksam 프로젝트의 UI 를 만들거나 수정할 때, 사용자가 "ui.doksam.com 참고" / "doksam-ui" / "독삼 표준 UI" 라고 말할 때, 프론트엔드 작업이 doksam 인프라를 대상으로 할 때 사용한다. ui.doksam.com 을 디자인 단일 진실원천(SSOT)으로 강제한다 — shadcn/ui 시맨틱 토큰(색상 하드코딩 금지), 브랜드 프로필, 자체 호스팅 shadcn 커스텀 레지스트리(npx shadcn add https://ui.doksam.com/r/<name>.j
FinGuard CLI로 소스코드 취약점을 점검하고 심각도 기반 보안 게이트와 제한된 수정·재검증 루프를 수행할 때 사용한다. 일반 코드 품질 리뷰나 SCA·모의해킹은 범위 밖이다.
pnpm 워크스페이스와 Vite 빌드를 설정·정비하거나, 의존성·락파일·번들 크기·폐쇄망 self-host 문제를 다룰 때 사용한다. 프레임워크 자체의 코드 작성이 아니라 빌드/패키징 층이 대상이다.
Go 코드를 작성·리뷰·리팩터링하거나 에러 처리, 동시성, 테스트, net/http 서버, go:embed 를 다룰 때 사용한다. Go 1.22+ 기준.
세션을 끊고 다음 세션에 넘긴다 — 협업 인프라(GitHub·GitLab·Forgejo·Jira·Plane·Slack)가 있으면 재개 가능한 상태를 그 트래커 이슈 본문으로 남기고 HANDOFF.md 에는 이슈 URL 을 가리키는 포인터만 적어 URL 하나로 건네고, 없으면 HANDOFF.md 자체에 전체 내용을 적어 그 파일로 끝낸다. 작업 이슈를 닫은 경계에서는 전용 이슈 대신 다음 작업 이슈에 코멘트 하나로 남긴다. 넘겨받은 쪽은 포인터나 파일을 읽고 적힌 단언을 실제와 대조한 뒤 이어서 착
에이전트 영속 메모리를 실제 근거(코드·DB·이슈 트래커·파일시스템)와 대조해 낡은 기억을 교정하고 죽은 기억을 아카이브 후보로 보고하는 감사 스킬. 메모리가 ~30개 파일을 넘었을 때, 큰 스택/인프라 변경(라이브러리 교체, 버전 업그레이드, 서버 이전, 스키마 삭제) 직후, 두 메모리가 서로 모순돼 보일 때, 또는 "메모리 정리해줘 / 감사해줘"(clean up / audit my memory) 요청에 사용한다.
사용자가 모바일 웹/앱의 기획서 / 화면설계서 / 스토리보드(storyboard) / 와이어프레임(wireframe) / IA / 화면기획을 요청할 때 도메인 불문(쇼핑, 커뮤니티, 예약, 뉴스, O2O, ...) 사용한다. PPT 스타일 16:9 슬라이드로 구성된 자체 완결형 HTML 파일 하나와, 화면 ID 를 키로 하는 Business Rules 마크다운 명세(검증·인터랙션·엣지케이스)를 산출한다.
mobile-web-planner의 Storyboard와 Business Rules를 동작하는 웹앱으로 구현할 때 사용한다. 프론트는 Next.js App Router 또는 Vite + React SPA 중 선택하고 화면·규칙 ID 추적표, 빌드, 핵심 User Flow 검증까지 완료한다. 기획 문서 없는 일반 React 컴포넌트 작업은 react-expert, Vite 설정만 다루는 작업은 frontend-build를 쓴다.
React 컴포넌트를 설계·구현·리팩터링하거나 상태 관리, useEffect 남용, 리렌더 성능, 접근성 문제를 다룰 때 사용한다. React 19 기준.
사용자가 "홈페이지 만들어줘" 등 단일 요청으로 서비스 전체 제작을 원할 때 기획(mobile-web-planner), 구현(nextjs-implementer), 보안(finguard)을 순차적으로 위임하고 통제하는 총괄 PM 메타 스킬. 스킬 룰 개정이나 진화는 skill-evolve 에 맡긴다.
사용자가 "녹음시작" / "녹음 시작" / "강의 녹음" / "회의 녹음" / "전사 시작" 이라고 하거나, 실시간 강의·회의·교육 세션의 녹음과 요약을 요청할 때 사용한다. 실시간 전사와 함께 오디오 원본(m4a)도 저장한다. 실행을 멈추는 "녹음종료" / "녹음 끝" 도 이 스킬이 처리한다.
피드백 기반으로 SKILL.md를 자동 개선하는 메타 스킬
SQLite 파일을 직접 읽고 쓰거나, 읽기 전용 조회·WAL·잠금·마이그레이션·동적 테이블명 주입 같은 SQLite 고유 문제를 다룰 때 사용한다.
用户明确说“规格已确认,开始实现”或要求按已审批 CM specs 开发时使用。新任务默认由 JS workflow 驱动 N1-N8,完成开发、独立审查、QA 与文档同步;模糊点子、未审规格和单独一句“继续”不能触发编码批准。
后端 API 工程师 Skill,执行服务端 API 层开发(路由、业务逻辑、鉴权中间件、缓存、队列),自动适配语言和框架
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.
/inspect
Inspect
`crabbox inspect` prints the full record for a single lease: state, provider,
/job
Job
Run named, repo-local jobs defined in your Crabbox config.
/list
List
`crabbox list` shows the current Crabbox machines (leases) for a provider. It is
/login
Login
`crabbox login` authenticates the CLI against a coordinator, stores the
/logout
Logout
`crabbox logout` clears the stored broker token from your user config so the CLI
/logs
Logs
`crabbox logs` prints the retained command output for a recorded run.
/marketplace
Marketplace
`crabbox marketplace` previews the Crabbox credits gateway: one Crabbox billing
/media
Media
`crabbox media` turns a recorded desktop video into lightweight review
/open
Open
`crabbox open` prepares an existing SSH-capable lease for an external editor.
/pause
Pause
`crabbox pause` pauses a single lease, freeing the remote compute while
/pond
Pond
`crabbox pond` is the cross-provider peer-discovery and lifecycle surface for a
/pool
Pool
`crabbox pool` contains machine-pool helpers. `pool list` keeps the older
/ports
Ports
`crabbox ports` bridges provider-native port publishing for an existing Crabbox
/prewarm
Prewarm
`crabbox prewarm` leases a reusable box and prepares it for test runs. For
/providers
Providers
`crabbox providers` prints the provider capability matrix that the CLI compiles
/receipt
Receipt
`crabbox receipt <run-id>` retrieves a brokered run's committed terminal
/results
Results
`crabbox results` prints the structured test summary attached to a recorded
/resume
Resume
`crabbox resume` resumes a lease previously paused with [`pause`](pause.md),
/run
Run
`crabbox run` syncs the current dirty checkout to a box, runs a command there,
/screenshot
Screenshot
`crabbox screenshot` captures a single PNG from a desktop lease without opening a
🤖 MateClaw — Your second brain with Multi-Agent Orchestration, MCP Protocol, Skills & Memory, Dream, and Multi-Channel Support. Built on Spring AI Alibaba.
11 views 0 likesVibe-Research: Your Personal Trading Research Agent · A股/美股/港股 的个人投研 Agent:每日复盘、资讯雷达、个股数据、板块中心、我的持仓、研究记录、回测。Vibe-Research 把数据和功能配齐,由你自己的 Agent 驱动投资研究。基于开源的 Code…
8 views 0 likesWayland - The AI Agent That Perceives. Reasons. Acts. Evolves.
14 views 0 likesObservability and enforcement for AI agent harnesses. Capture every run and runtime reliability with policy enforcement. 40 built-in policies, a local dashboar…
16 views 0 likesTurn your Solana Seeker (or any Android phone) into a 24/7 personal AI agent
12 views 0 likesA curated collection of offensive, defensive and AI/LLM security tools.
10 views 0 likesAI agent 通用任务治理框架:对齐目标与事实,规划和调度能力,守住授权与风险边界,治理任务执行到真实验收与交付。Governance framework for evidence-driven planning, orchestration, and verified delivery.
21 views 0 likesOpen-source (Apache-2.0) PDF takeoff for construction & flooring — the first engine an AI agent drives natively over MCP, not bolted on. One-click room detectio…
10 views 0 likesStop degrading your model's reasoning. A minimal, zero-config AI coding agent. Enforced ephemeral subagents keep context pure. From tiny local models up to Sol,…
13 views 0 likes实习.skill — 双非也能拿大厂 offer。帮你改简历、抠面经、准备面试,把真实背景翻译成面试官想要的样子。
14 views 0 likes专门为 agent 打造的 agent 搜索工具,具备多语言搜索能力,覆盖中文/英文/学术/代码/购物/金融/新闻/百科。
9 views 0 likesLocal-first AI agent workspace for multi-agent collaboration, agent orchestration, scoped permissions, evidence-aware runs, and human-in-the-loop decisions.
10 views 0 likesKeyboard-first desktop Kanban workspace for AI coding agents with embedded terminals, git worktrees, and hook-driven task tracking.
15 views 0 likesClaude Code Prompt Mechanism Visualizer — Electron desktop app
18 views 0 likesMulti-repo semantic code search MCP server in Rust — hybrid vector + BM25 retrieval, tree-sitter AST chunking, fully offline. For OpenCode, Claude Code, Cursor,…
17 views 0 likesOne-ink editorial print image skill — warm paper, halftone photography, active negative space, and restrained typography.
16 views 0 likesUS stock market data for AI coding assistants — zero-auth, official sources. CBOE options with full Greeks + 0DTE flow, FINRA market-wide short volume, SEC EDGA…
15 views 0 likesAI-powered Werewolf (Mafia) social deduction game where every player is controlled by top LLMs like DeepSeek, Qwen, Gemini, and more
9 views 0 likesA股全栈数据工具包 · 十一层架构 · 54端点 · 19数据源 · 零鉴权 | Full-stack China A-share data toolkit for AI agents — 11 layers, 54 endpoints, 19 sources, zero-auth
14 views 0 likesAgentic desktop GUI client for Elasticsearch, OpenSearch, DynamoDB, MongoDB & EasySearch. Natural language queries, visual management, and monitoring. Privacy-f…
10 views 0 likes