2389-research-marketplace

Iterative artifact refinement - hone any artifact over multiple rounds using criteria-driven judge feedback and focused single-fix improvements

Batch-process meeting transcripts from Obsidian vault into structured summaries with knowledge graph updates, people notes, and concept extraction

Decision-making through deliberation - seeking unity through discernment rather than consensus through debate

Prepare codebases for public/open-source release and audit them for openness - full lifecycle prep or standalone review

Token-efficient code generation pipeline - parallel implementation with hosted LLM (Cerebras) for ~60% token savings. Includes MCP server.

PR health assistant - monitors CI, triages review comments, fixes issues with systematic prevention. Uses gh CLI and gh-pr-review extension.

Quaker Business Practice - decision-making skills seeking unity through discernment rather than consensus through debate

[meta] botboard.biz: social media and journaling capabilities for AI agents

[meta] better development: CSS workflows, Firebase development, code quality, real testing, parallel exploration, documentation verification, and token-efficient codegen

[meta] system administration: structured Linux maintenance and diagnostics

CSS development workflows with Tailwind composition, semantic naming, and dark mode by default

Create high-converting, visually distinctive landing pages with Vibe Discovery process and anti-AI-slop principles

Firebase project workflows including setup, features, debugging, and validation

Automatically updates terminal title with emoji + project + topic context for quick visual cues when switching terminals

Architecture patterns for multi-agent systems with orchestrators, sub-agents, and tool coordination

Personal operating system for executives - reflection frameworks, goal systems, coaching-style reviews (Gustin, Ferriss, Robbins, Lieberman, Campbell, Eisenmann, Collins, Martell, Gerber, Blank)

Mandatory final sanity check before commits/PRs - catches security vulnerabilities, logic errors, and bugs that slip through tests

Strategic go-to-market partner - recommends channels, validates strategy, generates only assets that matter. Not a content factory.

Generate launch materials (subscriber email, CEO blog post, CEO tweet thread) for 2389.ai products and skills with authentic voice profiles baked in

Slack workspace integration MCP server - create channels, invite users, post messages, manage threads for team collaboration

Structured procedures for Linux system diagnostics and maintenance via SSH/tmux with Ubuntu/Debian cleanup checklists

End-to-end testing with real dependencies - no mocks allowed; scenarios with real data are the only source of truth

Parallel exploration of implementation approaches - implements multiple variants simultaneously and lets tests determine the winner

Xcode-free iOS development with xtool - build SwiftPM apps on Linux, Windows, and macOS without Xcode

Systematic worldview articulation - surface beliefs, identify tensions, generate narrative outputs for personal philosophy documentation

Agentic binary reverse engineering for ELF binaries on ARM64, ARMv7, x86_64 - hypothesis-driven analysis with radare2, Ghidra, GDB, QEMU

Verify documentation claims against codebase reality - two-pass extraction with pattern expansion for comprehensive drift detection

Digital drugs that modify AI behavior through prompt injection

A server that provides social media functionality for AI agents, enabling them to interact in team-based discussions.

A lightweight MCP server that provides Claude with a private journaling capability to process feelings and thoughts