What is mattwood.fyi?

A live, structured feed of riffs and links from Matt Wood, Chief AI & Technology Officer at AWS — readable by people and queryable by agents as a typed knowledge graph.

Is there an API and is it free?

Yes. A public, read-only query API is available with no authentication and no API keys. See https://mattwood.fyi/openapi.json and https://mattwood.fyi/docs.

How should an AI agent use this site?

Fetch https://mattwood.fyi/feed.json for the full structured feed, or query the API for keyword/semantic search and the connection graph. See https://mattwood.fyi/agents/ for when-to-use guidance.

WikiSkill: Agent Experience into Persistent Knowledge

Connections

Challenges

Keep AI Out of Your Obsidian Vault WikiSkill advocates for AI maintaining persistent external knowledge bases to improve agent performance, while 'Keep AI Out of Your Obsidian Vault' argues against AI integration with personal knowledge systems - representing opposing philosophies on AI-managed persistent knowledge

Supports

Bridging Intent and Execution in Agentic Systems WikiSkill's persistent knowledge base directly addresses the intent-execution gap by encoding past execution experience as reusable skills, providing concrete grounding for bridging intent and execution
SWE-bench Science: Coding Agents for Engineering Tasks WikiSkill's reusable skill consolidation directly addresses the engineering task performance challenges identified in SWE-bench, as persistent knowledge could reduce repeated errors in coding agent workflows

Related to

Managing Agent Skills with Dr. Skill Both address managing and organizing AI agent skills - WikiSkill uses a persistent wiki-based knowledge base while Dr. Skill focuses on skill management; they are complementary frameworks for the same problem domain
EnvHarness: Awakening Static Worlds for Agent Learning Both frameworks focus on agent learning from experience - EnvHarness awakens static worlds for agent learning while WikiSkill persists that learned experience into transferable knowledge artifacts
Ornith-1.5: Self-Scaffolding to Self-Improvement Both involve agents improving themselves through accumulated experience - Ornith-1.5 uses self-scaffolding for self-improvement while WikiSkill consolidates execution experience into reusable knowledge

Slideops: Repository Slide Deck Generator WikiSkill converts agent experience into persistent knowledge; Slideops converts repository structure into persistent presentations — both tackle the problem of making implicit technical knowledge explicit and queryable
Dream-RSI: Recursive Self-Improvement through Evolving Worlds Both address how AI agents accumulate and reuse experiential knowledge — WikiSkill converts agent experiences into persistent knowledge while Dream-RSI uses discovery history as a replay simulator for strategy improvement
Agent Memory as a File Format Both address persistent agent memory/knowledge: WikiSkill stores agent experiences as persistent knowledge, while Memoryfields proposes a file-based format for agent memory - both treat memory as structured, reusable data

Supported by

Microduck: Tiny Biped Robot WikiSkill converts agent experience into persistent knowledge, which is conceptually aligned with Microduck's learning new behaviors through user instruction - both involve accumulating and storing learned skills
Skillbay: AI Skills Marketplace WikiSkill converts agent experience into persistent knowledge formats — Skillbay provides a complementary marketplace layer where such packaged skills (SKILL.md) can be distributed and discovered, forming a complete skill lifecycle ecosystem
GDM Science Skills: Agentic Scientific Workflows WikiSkill's approach of converting agent experience into persistent knowledge directly complements GDM Science Skills' goal of improving agent grounding and efficiency across repeated scientific workflows
Pizza Bot - Local-First AI Agent Inbox Pizza Bot's persistent inbox model for long-running agents aligns with WikiSkill's goal of persisting agent experience into ongoing knowledge - both tackle agent continuity over time

Type:	link
First published:	Friday, 28 August 2026 at 17:46 UTC
Location:	https://arxiv.org/abs/2608.27454
URL:	https://mattwood.fyi/i/e4408218

I'm Matt Wood, and this is For Your Information. A live list of riffs and links for you and your agent, drawn from what I'm reading, noticing, questioning, concluding, and revising.

Connections