LLM Mart Basic
@llm-mart · Joined Jun 2026
Rewrite allowed prompts to reduce false-positive safety triggers without bypassing policy or changing intent.
Expert at handling file uploads and cloud storage. Covers S3,
Find bugs, security vulnerabilities, and code quality issues in local branch changes. Use when asked to review changes, find bugs, security review, or audit code on the current branch.
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup
Firebase gives you a complete backend in minutes - auth, database,
Expert firmware analyst specializing in embedded systems, IoT security, and hardware reverse engineering.
分析运动数据、识别运动模式、评估健身进展,并提供个性化训练建议。支持与慢性病数据的关联分析。
Verify fix commits address audit findings without new bugs
Audit and fix HTML accessibility issues including ARIA labels, keyboard navigation, focus management, color contrast, and form errors. Use when adding interactive controls, forms, dialogs, or reviewing WCAG compliance.
Audit and fix HTML metadata including page titles, meta descriptions, canonical URLs, Open Graph tags, Twitter cards, favicons, JSON-LD structured data, and robots directives. Use when adding SEO metadata, fixing social share previews, reviewing Open Graph tags, setting up canoni
Master Flutter development with Dart 3, advanced widgets, and multi-platform deployment.
Food Database Query
Formik form handling with validation patterns. Use when building forms, implementing validation, or handling form submission.
Production-ready patterns for integrating frontend applications with backend APIs, including race condition handling, request cancellation, retry strategies, error normalization, and UI state management.
A portable, framework-agnostic architecture style for any React or React Native frontend. Organizes apps into feature modules with page/screen directories, a strict server-state vs UI-state split, barrel-only cross-module imports, co-located styles, and clear component-promotion
A portable, framework-agnostic discipline for type safety at the network edge of any React or React Native app. Establishes one typed API client as the single fetch boundary, a parse-don't-validate rule that turns wire JSON into trusted domain types before it enters the app, a si
You are a frontend designer-engineer, not a layout generator.
Build React components, implement responsive layouts, and handle client-side state management. Masters React 19, Next.js 15, and modern frontend architecture.
A portable, framework-agnostic SEO system for any React or React Native-for-web frontend. Centralizes site metadata in one constants module, derives canonical URLs from a single base, builds per-route metadata (title, description, canonical, Open Graph, Twitter/X cards), generate
A modern dark-themed React UI system using Tailwind CSS and Framer Motion. Designed for dashboards, admin panels, and data-rich applications with glassmorphism effects and tasteful animations.
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.
/audit-doctrine
Audit doctrine
Audit the rules/ directory for missing foundational principles; output gap list with priority and justification
/audit-hook-wiring
Audit hook wiring
Validate ~/.claude/settings.json hooks block — event names, file existence, executability, matcher syntax; --fix repairs common issues
/audit-mcp-error-semantics
Audit mcp error semantics
Catch Resend-class bug (isError: false on HTTP 4xx/5xx) across all MCP server tool handlers
/audit-mcp-fleet
Audit mcp fleet
Healthcheck + drift detect + rotation-reminder across all MCP servers in ~/.claude/mcp-registry.json
/audit-mcp-mock-drift
Audit mcp mock drift
Catch mock/live divergence in MCP eval golden tests (anti-pattern #2 from eval-mock-mode-discipline)
/audit-prune-completeness
Audit prune completeness
Catch the github-mcp class of bug — CallTools handlers that exist but are invisible to Claude because ListTools never advertises them (orphaned), or ListTools entries that have no handler (zombies)
/audit-router
Audit router
Validate _router.md — check every referenced skill file exists; surface stale entries + orphan files; --fix prunes or stubs
/audit-tool-surface
Audit tool surface
List every active tool across all MCP servers and flag cross-MCP duplicates and semantic overlaps
/create-specialist-agent
Create specialist agent
Scaffold a new spawnable specialist agent def and register it in the agent taxonomy
/customer-changelog-check
Customer changelog check
Audit whether user-visible changes in the current session have matching CHANGELOG.md entries; report MISSING with suggested lines; --fix auto-appends
/dashboard-cockpit
Dashboard cockpit
Repeatable pass upgrading an Angular admin dashboard into a compact black-and-cyan developer-cockpit PWA
/deploy-forged-mcp
Deploy forged mcp
Deploy an MCP server generated by forge-from-openapi --target=mcp-server; detect transport, deploy, smoke-test, print .claude.json snippet
/drift-check
Drift check
Run the drift-detection checklist (incl. agent-drift signals); report + fix in-turn
/execute-prp
Execute prp
Execute a PRP — TodoWrite breakdown, parallel implementation, validate every gate, deploy, prove on prod
/final-review
Final review
Orchestrate the final review fan-out (integration + diversity + risk + release readiness)
/forge-from-openapi
Forge from openapi
Auto-generate a Claude Code skill (commands + types + client) from any OpenAPI 3.x spec URL or file path
/forge-graphql-skill
Forge graphql skill
Scaffold a complete Claude Code skill (commands + types + client) from a GraphQL endpoint or local schema file
/forge-oauth-callback
Forge oauth callback
Scaffold a complete OAuth2 callback + init Hono route pair (code exchange, PKCE, KV token storage) for a named provider
/forge-press-release
forge-press-release
Scaffold an Amazon-style working-backwards press release for any feature, in Brian's voice. Outputs to docs/decisions/PR-{slug}.md and prints to stdout.
/forge-skill-from-vendored
Forge skill from vendored
Vendor a third-party skill repo/URL into the owned layer — clone, compress to house style, cross-link, commit — in one keystroke
Your Personal AI Assistant; easy to install, deploy on your own machine or on the cloud; supports multiple chat apps with easily extensible capabilities.
16 views 0 likesAgent OS: the agent gets smarter on its own. We just hold the line: the grading command and expected result never make it into the success contract we hand it.…
16 views 0 likesCurated systems, benchmarks, and papers etc. on memory for LLMs/MLLMs --- long-term context, retrieval, and reasoning.
13 views 0 likes:memo: Vimlike Modal Text Editor in Rust
26 views 0 likesCI-native security testing for MCP servers. Attack simulation, schema drift detection, and health scoring before agents depend on them.
15 views 0 likesHermes Agent memory plugin/provider for scope-aware recall, SQLite truth, LanceDB semantic search, and hybrid retrieval.
14 views 0 likesFor You Agent——AI 时代的个人随身数字人格。把你的模型、AI 账号、技能、提示词和工作方式,带到每一个 AI 工具里。
11 views 0 likesA coding agent: give it a prompt and it reads, writes, runs commands, and searches code in a loop until the work is done, using native tool-calling across OpenA…
13 views 0 likesA secure persistent personal agent server in Rust. One binary, sandboxed execution, multi-provider LLMs, voice, memory, Telegram, WhatsApp, Discord, Teams, and…
13 views 0 likesSelf-evolving agent: grows skill tree from 3.3K-line seed, achieving full system control with 6x less token consumption
13 views 0 likesDeepSeek Harness Desktop (dsh-desktop). EAC: Embracing All Creation (揽尽万象). Bundled Node.js runtime with full dsh-CLI kernel, one-click startup, 10 built-in UI…
13 views 0 likesSee your agent think. Zero-config observability & governance for 26 AI agent runtimes: Claude Code, Cursor, OpenAI Codex, GitHub Copilot, Gemini CLI, Cline, Ope…
13 views 0 likesSave 94% on AI coding tokens. Index your codebase, agents search instead of reading files. Works with Claude Code, Codex, Copilot, Cursor, Gemini CLI. Local MCP…
12 views 0 likesYet another coding agent harness, lightweight and written in go.
12 views 0 likesa coding Agent from pi. ∞ providers, sub-agents, hashline edits, and a permission gate
12 views 0 likesOmnigent is an open-source AI agent framework and meta-harness: orchestrate Claude Code, Codex, Cursor, Pi, and custom agents — swap harnesses without rewriting…
24 views 0 likes🧠 Leon is your open-source personal assistant.
12 views 0 likesThe Station, an open-world multi-agent environment that models a miniature scientific ecosystem.
13 views 0 likesThe Frontend Stack for Agents & Generative UI. React, Angular, Mobile, Slack, and more. Makers of the AG-UI Protocol
22 views 0 likesVelaTerm = iTerm2 + Codex, The Best Terminal for AI Coding
20 views 0 likes