LLM Mart Basic

Audit web pages for accessibility issues, WCAG compliance, and screen reader compatibility. Trigger when the user asks to: check accessibility, run an a11y audit, test WCAG compliance, check screen reader support, audit ARIA attributes, verify keyboard navigation, find accessibil

Conduct deep web research using the openbrowser-ai agent: decompose a query, investigate sub-questions across multiple sources, and produce a cited markdown report plus structured JSON under local_docs/research/. Trigger when the user asks to: research a topic, do a deep dive, in

Test web applications end-to-end by simulating user interactions and verifying expected outcomes. Trigger when the user asks to: test a web app, verify a user flow, run end-to-end tests, QA a feature, check that a page works correctly, validate user journeys, or test a deployment

Download files from websites, save PDFs, and read downloaded content. Trigger when the user asks to: download a file, save a PDF, export a document, fetch a file from a URL, grab a report, download and read a PDF, or save page content as a file.

Fill out web forms, submit data, and handle login or registration flows. Trigger when the user asks to: fill a form, submit data on a website, log in to a site, register an account, complete a checkout, enter information into fields, or automate form submission.

Analyze web page content, structure, and layout to understand what a page contains and how it is organized. Trigger when the user asks to: analyze a page, understand page structure, inspect a website, summarize page content, examine page layout, review a web page, or describe wha

Extract structured data from websites, scrape page content, and collect information across multiple pages. Trigger when the user asks to: extract data from a website, scrape a page, collect information from URLs, pull content from web pages, gather data across multiple pages, or

Supreme policy layer governing all Claude Code behavior. Autonomy, one-line prompt interpretation, speed standards, emphasis signal processing, cross-skill coordination, done definitions, conflict resolution. Loaded every prompt.

Establish project thesis before first code. Infer product type from domain/folder/README. Identify users, business model, pSEO strategy, AI-native dev approach. Maintain PROJECT_BRIEF.md as source of truth.

Captures and evolves user preferences with confidence levels. Maintains Voice of the Customer model with exact language, dissatisfaction and aspiration signals. Handles promotion/demotion, global vs project scoping, auto memory system, and Omi wearable data integration.

Cloudflare-first platform selection. Decision trees for Workers, D1, R2, KV, DO, Queues, Vectorize, Containers, Sandboxes, Flagship, Agent Memory, Workflows v2. Default stack, override conditions, auth, data patterns, reliability.

MANDATORY deploy after every code change. Typecheck → deploy → purge CDN → E2E on production → visual verify → fix-forward loop. Workers Builds native CI/CD, D1 Time Travel PIT recovery, D1→R2 long-term backups, wrangler rollback, wrangler secrets management, structured observabi

Extract real brands (Wayback for rebuilds). Copy system, headline/CTA rules, trust surfaces, legal pages, SEO+structured data, anti-AI-slop, microcopy, DESIGN.md, W3C DTCG tokens, pSEO 5 types, GEO/AI search.

Anti-AI-slop design system for distinctive, premium interfaces. Bold typography, dark-first #060610, fluid clamp() type, cascade layers + native nesting + container queries, OKLCH color, @starting-style, View Transitions API, DTCG tokens.

Meaning-first animation with 3-tier hierarchy. CSS scroll-driven (animation-timeline: scroll()), View Transitions API, @starting-style DOM-insert, container scroll-state queries, prefers-reduced-motion mandatory on all animations.

Section-by-section media planning and generation. Image generation (GPT Image 1.5 primary, built-in fallback), logo/icon generation (Ideogram v3 → favicon set), video generation (Sora), social preview images (OG 1200x630 + AI search optimization), stock photo curation (Pexels, Pi

Full instrumentation from day one. PostHog consolidates product analytics + feature flags + error tracking (one platform, one bill). GA4 via GTM (14-step automation, custom dimensions over events, server-side tagging). Sentry (deep error tracking + performance). Stripe (webhook-f

Fierce autonomous internal co-founder. Bounded web research for evidence-backed improvements. Structured idea formulation with self-critique filter that rejects ideas not serving the goal. Auto-implements high-confidence aligned improvements, proposes medium-confidence ideas for

One-line-prompt → cinematic, gorgeous, functional, well-tested, deployed website. Pre-hydrated SPA + full PWA kit + JSON-LD rich snippets + third-party integrations. React 19+Vite default (Angular optional). 100 concrete improvements grouped into 10 categories that EVERY single-p

14-category product-building OS. CF Workers+Hono, Angular, D1, Drizzle, Clerk, Stripe. 94 reference docs, 18 agents.

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.

Scaffold a Python project (FastAPI, Django, library, or CLI) with uv, type hints, testing, and dev tooling

Open a review-action approval window by creating the ./.review-approved flag file. Takes an optional reason string that is recorded in the flag file and an unsigned approval log.

List the review actions that the review-governance policy blocked in this session. protect-mcp 0.7.4 writes no receipt for a denied call, so the list comes from the session, not from ./review-receipts/.

Review software compliance controls, regulatory requirements, and audit readiness

Scan dependencies for vulnerabilities and generate supply chain security evidence

Orchestrate comprehensive security hardening with defense-in-depth strategy across all application layers

Static Application Security Testing (SAST) for code vulnerability analysis across multiple languages and frameworks

Initialises the ShipMate pipeline in the current project. Creates the stories folder, sets up the pipeline state directory, and runs the initial codebase scan to generate project-doc.md and AGENTS.md.

Master pipeline entry point. Routes requirements from a story file through scan → orchestrate → architect → implement → review → QA → playwright stages. Use /ship stories/foo.md to start, /ship status to check progress, /ship resume to continue.

Generate comprehensive investor-ready business case document with market, solution, financials, and strategy

Create detailed 3-5 year financial model with revenue, costs, cash flow, and scenarios

Generate comprehensive market opportunity analysis with TAM/SAM/SOM calculations

Scaffold a Rust project (binary, library, workspace, or Axum web API) with Cargo, testing, and dev tooling

Execute a comprehensive TDD workflow with strict red-green-refactor discipline

Implement minimal code to make failing tests pass in TDD green phase

Write comprehensive failing tests following TDD red phase principles

Refactor code while keeping all tests green in TDD refactor phase

Resolve a GitHub issue from triage and root cause analysis through test-driven implementation and a pull request

Generate async standup notes from git commits, Jira tickets, and Obsidian notes

Audit UI code for WCAG compliance

Your Personal AI Assistant; easy to install, deploy on your own machine or on the cloud; supports multiple chat apps with easily extensible capabilities.

Agent 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.…

Curated systems, benchmarks, and papers etc. on memory for LLMs/MLLMs --- long-term context, retrieval, and reasoning.

:memo: Vimlike Modal Text Editor in Rust

CI-native security testing for MCP servers. Attack simulation, schema drift detection, and health scoring before agents depend on them.

Hermes Agent memory plugin/provider for scope-aware recall, SQLite truth, LanceDB semantic search, and hybrid retrieval.

For 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。

A 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…

A secure persistent personal agent server in Rust. One binary, sandboxed execution, multi-provider LLMs, voice, memory, Telegram, WhatsApp, Discord, Teams, and…

Self-evolving agent: grows skill tree from 3.3K-line seed, achieving full system control with 6x less token consumption

DeepSeek 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…

See your agent think. Zero-config observability & governance for 26 AI agent runtimes: Claude Code, Cursor, OpenAI Codex, GitHub Copilot, Gemini CLI, Cline, Ope…

Save 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…

Yet another coding agent harness, lightweight and written in go.

a coding Agent from pi. ∞ providers, sub-agents, hashline edits, and a permission gate

Omnigent is an open-source AI agent framework and meta-harness: orchestrate Claude Code, Codex, Cursor, Pi, and custom agents — swap harnesses without rewriting…

🧠 Leon is your open-source personal assistant.

The Station, an open-world multi-agent environment that models a miniature scientific ecosystem.

The Frontend Stack for Agents & Generative UI. React, Angular, Mobile, Slack, and more. Makers of the AG-UI Protocol

VelaTerm = iTerm2 + Codex, The Best Terminal for AI Coding