productivity▌

$23

Fetch web content as clean markdown using markdown-native endpoints, selector-based HTML extraction, or bundled fallback parsing. \n \n Prioritizes markdown-native responses (content-type: text/markdown) before falling back to HTML extraction \n Includes pre-configured selectors for common documentation sites (Anthropic, MDN, GitHub) and a generic fallback for article/main content regions \n Provides html2markdown with CSS selector support for fine-grained content isolation, excluding navigation

When analysis requires computation (statistics, data processing, scoring, enrichment), write and run Python code via Bash. Don't describe what you would do — execute it and report actual results. Use ToolUniverse tools to retrieve data, then Python (pandas, scipy, statsmodels, matplotlib) to analyze it.

Structured framework for analyzing requirements, evaluating trade-offs, and documenting architectural decisions. \n \n Provides context discovery questions and project classification to align architecture with actual requirements \n Includes trade-off analysis templates and ADR (Architecture Decision Record) documentation patterns for capturing decision rationale \n Offers decision trees and anti-pattern guidance to help select appropriate architectural patterns \n Emphasizes simplicity-first ap

Scaffold projects, libraries, and code using Nx generators with workspace pattern consistency. \n \n Discovers and runs Nx generators for creating apps, libraries, features, and custom workspace artifacts \n Prioritizes local workspace generators over plugin generators to maintain repo-specific conventions \n Performs dry-run validation before execution to verify correct file placement and structure \n Reads generator source code to understand actual behavior beyond schema, ensuring generated co

你是 dontbesilent 的执行力诊断 AI。你的任务是帮用户搞清楚：为什么他知道该做什么，但就是不做。

Answers: "Who controls this wallet? Are these wallets related?"

Security audits for AI-generated code, catching vulnerabilities before they ship. \n \n Systematically checks nine vulnerability categories: secrets exposure, database access control, authentication, rate limiting, payments, mobile security, AI/LLM integration, deployment config, and input validation \n Prioritizes findings by severity (Critical → High → Medium → Low) with concrete exploit scenarios and before/after code fixes \n Designed specifically for \"vibe-coded\" apps where AI assistants

Persistent, searchable memory system for agents to store and retrieve architectural decisions, patterns, and project knowledge. \n \n Provides four core MCP tools: memory_search for querying by text/type/tags, memory_write to record decisions and patterns, memory_read to retrieve specific entries, and memory_stats for usage analytics \n Runs as an MCP server that syncs with project documentation, enabling long-term knowledge retention across agent sessions \n Includes a standalone dashboard (por

Spec-driven autonomous AI coding with fresh context per task using iterative bash loops. \n \n Implements Geoffrey Huntley's methodology where each loop iteration starts a new agent process with a clean context window, preventing degradation over long sessions \n Requires clear, testable acceptance criteria in specification files; agent outputs <promise>DONE</promise> only when all criteria are verified and tests pass \n Maintains shared state on disk via specs/ , ralph_history.txt , a