---
mw_bundle: 1
id: Ih0eUczw
title: "Phase 2 strategy: connectors, replacements, first-principles"
url: https://memory.wiki/b/Ih0eUczw
document_count: 3
updated: 2026-05-15T17:43:33.084Z
analysis_generated_at: 2026-05-15T17:43:33.084Z
analysis_stale: true
source: "memory.wiki"
---
# Phase 2 strategy: connectors, replacements, first-principles

> Three working notes from a strategy review session on 2026-05-15. Native AI integrations roadmap, what current surfaces to replace, first-principles drift check.

**Intent:** Capture three companion strategy thoughts so they live as one shareable URL.

> ⚠ _Analysis may be stale — one or more member docs were edited after the last analysis run. Re-run the canvas to refresh._

## Summary

These three strategic documents form a comprehensive analysis of mdfy's transition from URL-based sharing to native AI platform integrations. The collection evaluates foundational principle alignment, maps improvement opportunities through native skills, and provides a framework for replacing existing product surfaces with more effective alternatives.

## Themes

- strategic alignment assessment
- native AI platform integration
- product surface evolution
- cross-platform user experience

## Cross-document insights

- The cross-AI structural moat is actually at risk from native skills if framed incorrectly - positioning as 'support every AI' dilutes the core value proposition of 'one URL works in 3 AIs'
- Current high-maintenance surfaces like the Electron desktop app and Chrome extension's AI capture mode are strategic dead ends that should be replaced rather than enhanced
- The zero friction principle is weakening specifically around 'friction to use well' despite maintaining 'friction to try', indicating a concerning strategic drift
- Bundle scope deserves equal marketing billing with Hub scope since AGENTS.md fit demonstrates bundle-level value that current messaging underemphasizes

## Key takeaways

- Strategic drift is occurring specifically around the authored-not-extracted principle and zero friction to use well, requiring immediate course correction
- Native AI skills offer bidirectional read-write capabilities and cross-platform reach that current URL-paste approach cannot match
- High-maintenance current surfaces should be strategically replaced rather than incrementally improved, with Electron desktop app and Chrome extension AI capture as primary candidates

## Open questions / gaps

- Competitive analysis missing - no evaluation of how native skills positioning affects competitive differentiation beyond internal principle alignment
- User adoption metrics and transition planning absent - unclear how users would migrate from current surfaces to native alternatives
- Resource allocation and timeline considerations not addressed for implementing the native skills roadmap

## Notable connections

- **doc:dEgO6Qml** ↔ **doc:LpLbS250** — Principles assessment identifies zero friction weakening that native skills directly address through improved user experience
- **doc:LpLbS250** ↔ **doc:NpXe_CnP** — Native skills capabilities inform which current surfaces become obsolete and should be replaced rather than maintained
- **doc:dEgO6Qml** ↔ **doc:NpXe_CnP** — Strategic principle of zero friction supports aggressive surface replacement decisions to reduce maintenance overhead

## Concepts (this bundle)

- **LLM-native design**
- **Cross-AI strategy**
- **Authored not extracted**
- **Zero friction**
- **Graph in response**
- **Native AI skills**
- **Surface replacement**

## Concept relations

- **Native AI skills** ↔ **Zero friction** — friction reduction
- **Cross-AI strategy** ↔ **Native AI skills** — strategic tension
- **Surface replacement** ↔ **Native AI skills** — better alternatives

## Documents

### 1. [Native skills + connectors: what improvements are possible](https://memory.wiki/LpLbS250)
Native skills and connectors on Claude, ChatGPT, and Gemini would enable bidirectional read/write access, mobile coverage, in-AI autocomplete search, and auto-capture of conversations, moving beyond the current URL-paste-only approach. The highest-leverage implementation prioritizes ChatGPT GPT+Actions (near-zero cost), Claude Skill for mobile coverage, and Claude Code hooks for real-time updates, with simultaneous shipping creating a demonstrable cross-AI workflow artifact.
*sections:* What changes at the "layer above AI" level: | Today (URL / Chrome ext only) | With native skill / connector | | …

### 2. [Native skills vs current surfaces — what should we replace](https://memory.wiki/NpXe_CnP)
The document recommends replacing the Electron desktop app with three lighter macOS-native pieces (PWA install, Share Sheet extension, QuickLook plugin) and migrating the Chrome extension's AI-capture functionality to native skills in Claude, ChatGPT, and Gemini to reduce maintenance burden while expanding reach across platforms.
*sections:* Obvious replacement candidates (cost > value today): | Current surface | Replacement | Why | | Partial replacement / depends on usage: | Current surface | Alternative | Verdict | | Keep as-is: | Surface | Reason | | Strongest single recommendation: Drop the Electron desktop app → "mac-native triplet." | Second recommendation: Migrate Chrome ext's AI-capture path to native skills incrementally. | Re-prioritised order (combining build + replace decisions): 1. ChatGPT GPT + Actions — relieves Chrome ext AI-selector maintenance for ChatGPT users

### 3. [First-principles check: are we drifting?](https://memory.wiki/dEgO6Qml)
The product is drifting from its core principle that URLs and markdown are the fundamental unit: feature breadth is growing faster than spine consolidation, and native skill positioning risks framing mdfy as a multi-AI tool rather than maintaining that one URL works everywhere. Three recovery moves are needed: add PR self-checks that prioritize URL value over alternative access paths, lock native skill positioning to emphasize the URL as the on-ramp, and promote bundle composition equally with hub in launch messaging.
*sections:* The 8 first principles: 1. LLMs read markdown natively. (empirical) | Per-principle assessment: | Principle | Alignment | Comment | | Biggest single drift risk: Feature breadth is growing faster than spine consolidation. | Three concrete recovery moves: 1. Add a self-check to every PR: "Does this make the URL more valuable, or just add another way to reach it?" The first kind compounds. The second is breadth wi | One-line summaries: What's working: Layered architecture on a markdown-URL foundation. Each new feature deepens that layering, not flattens it. | …


_Digest view — follow any link above to fetch that doc's full markdown. Add `?full=1` to this URL for the concatenated payload._