LLM Mart Basic
@llm-mart · Joined Jun 2026
Rename a skill across all its versions — transactional copy-verify-delete with platform context rebuild. Use when the user requests to "rename a skill."
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。
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.
Add remote HTTP or local stdio MCP servers to Claude Code, choose the right scope, protect credentials, verify the connection, and test with least privilege.
/search-products
Search products
Search the Autotask product catalog for products, services, or inventory items
/search-tickets
Search tickets
Search for tickets in Autotask PSA by various criteria
/time-entry
Time entry
Log time against tickets or projects in Autotask PSA
/update-ticket
Update ticket
Update fields on an existing Autotask ticket (status, priority, queue, due date)
/device-lookup
Device lookup
Find a device in Datto RMM by hostname, IP address, or MAC address
/resolve-alert
Resolve alert
Resolve an open alert in Datto RMM
/run-job
Run job
Run a quick job on a device in Datto RMM
/site-devices
Site devices
List all devices at a site in Datto RMM
/edit-doc-sections
Edit doc sections
Read, edit, and restructure sections of an IT Glue document
/find-organization
Find organization
Find an organization in IT Glue by name
/get-password
Get password
Retrieve a password from IT Glue (with security logging)
/lookup-asset
Lookup asset
Find a configuration item (asset) in IT Glue by name, hostname, serial number, or IP address
/search-docs
Search docs
Search IT Glue documentation by keyword or phrase
/account-summary
Account summary
Get a security posture summary for a RocketCyber customer account
/search-incidents
Search incidents
Search RocketCyber security incidents by account, status, severity, verdict, and date range
/find-secret
Find secret
Locate a Keeper record by description and return its UID and metadata without revealing any credential
/scope-audit
Scope audit
Report exactly what the connected Keeper KSM application can reach - folders, record counts, and record types - reading no credential values
/liongard-environment-summary
Liongard environment summary
Generate a detailed summary of a Liongard environment
/liongard-health-check
Liongard health check
Check Liongard connectivity and return system health summary
/check-mfa-status
Check mfa status
Audit MFA enrollment across all M365 users, highlighting accounts with no MFA
Paper trading simulator for Polymarket — built for AI agents. MCP server, live order books, strategy backtesting. Install: npx clawhub install polymarket-paper-…
1 views 0 likesAn SSH tool dedicated to addressing all pain points · (macOS/Windows/Linux/Android/iOS)
2 views 0 likesThe first AI agent harness native to the browser. A browser extension that runs a full agent loop where you already work: it drives your tabs, spins up sandboxe…
2 views 0 likesSmartLabel AI 2026: Auto-Annotate Any Object via LLM-Powered Prompt Parsing
2 views 0 likesLocal-first visual generation runtime and studio for people and coding agents, with reproducible image and video workflows across multiple providers.
0 views 0 likesScholar All-In-One: A research infrastructure for AI agents
0 views 0 likesGive your AI agent a real browser — with a human in the loop. Open-source MCP-native browser agent.
0 views 0 likes同花顺免费开源AI插件FQGate-agent(原插件名 tonghuasun-agent):为 Codex、Claude Code、DeepSeek 等 AI 工具提供本机 A 股实时行情、K 线、Level-2、资讯、账户查询与可选交易能力。
0 views 0 likesA non-linear AI agent workbench — session is a tree: branch anytime, and context follows the branch
0 views 0 likesProduction-grade AutoCAD MCP server for AI agents — 122 tools, dual COM (live AutoCAD) + headless ezdxf engines, ISO GD&T and dimension-tolerance validation for…
0 views 0 likesA DeepSeek coding agent harness: persistent shell, Ultra subagents, auto approval, Chrome MCP and session telemetry
0 views 0 likesWaku Waku! Waku Agent is a local-first AI agent harness you actually own, including loop, memory, eval, all in code built to stay legible as it grows.
0 views 0 likesRemote control for Claude Code, Codex, Grok, and Cursor on Mac or PC. View sessions, send tasks, and drive them remotely from your phone, PIN, or Ring. OpenClaw…
0 views 0 likes