Synthesizing Institutional Knowledge

What this Claude Code skill does

Builds organizational memory systems that capture decision provenance, causal chains, and institutional context beyond document embeddings. Use when designing knowledge bases for AI agents that must answer questions about why decisions were made, how situations evolved over time, or what historical context drives current organizational state.

Synthesizing Institutional Knowledge is a packaged skill for Claude Code: a SKILL.md plus references and a runnable test that drops into .claude/skills/, so your agent can run this workflow reliably instead of you re-explaining it each time. Install it via MCP, run it as a CLI, or fork it into your own.

Inside the SKILL.md

<h1>Synthesizing Institutional Knowledge</h1>
<h2>Why Embedding-Based Retrieval Loses Institutional Context</h2>
<p>When a document is chunked and embedded, the resulting vector captures <em>semantic content</em> — what the document says. It does not capture:</p>
<ul>
<li><strong>Who</strong> decided this and under what authority</li>
<li><strong>Why</strong> — the constraints, alternatives considered, and trade-offs made</li>
<li><strong>When</strong> — and what was happening organizationally at the time</li>
<li><strong>What it superseded</strong> — the decision it replaced and why the old one failed</li>
<li><strong>What it caused</strong> — decisions and events that followed from it</li>
</ul>
<p>This lost provenance is exactly what makes questions like "why are we doing it this way?" impossible to answer from a standard RAG system. The documents exist; the institutional reasoning does not.</p>
<hr />
<h2>The Three Knowledge Types</h2>
<h3>1. Declarative Knowledge — "What is true now"</h3>
<p>Facts, policies, configurations, documentation.
- <em>Appropriate storage</em>: Vector RAG (Layer 1)
- <em>Examples</em>: API docs, runbooks, policy documents, current architecture diagrams</p>
<h3>2. Episodic Knowledge — "What happened and when"</h3>
<p>Events, decisions, incidents, changes — with temporal context.
- <em>Appropriate storage</em>: Temporal/episodic store (Layer 3)
- <em>Examples</em>: Incident reports, architectural decision records, deployment events, personnel changes</p>
<h3>3. Causal Knowledge — "Why things are the way they are"</h3>
…