🗺️ Skill: Context Distiller (v1.1.0)
Executive Summary
The context-distiller is the master of high-fidelity information management for AI swarms. In 2026, the success of a mission depends on the quality and density of the context provided to the agent. This skill focuses on Automated Context Packing, building Symbolic Project Maps, and managing Agent Memory Rehydration to ensure that every session starts with maximum intelligence and minimum token noise.
📋 Table of Contents
- The Distillation Protocol
- The "Do Not" List (Anti-Patterns)
- Automated Context Packing (Repomix)
- Symbolic Project Mapping
- Agent Memory & Rehydration
- Hierarchical Inheritance
- Reference Library
🛠️ The Distillation Protocol
Before initiating a new mission or subproject, the Distiller MUST:
- Codebase Scan: Use
rgandlist_directoryto map the active module's boundaries. - Essence Extraction: Apply the Impeccable Distill logic—identify the 20% of code that provides 80% of the value. Strip away "Noise" (boilerplate, unused imports, redundant logic).
- Symbol Indexing: Generate a list of critical types and interfaces.
- Inheritance Audit: load master rules from
docs/AGENTS.md. - Local Rehydration: Create or read
.gemini/GEMINI.mdfor mission-specific context. - Context Packing: Bundle all findings into a structured Markdown artifact.
🚫 The "Do Not" List (Anti-Patterns)
| Anti-Pattern | Why it fails in 2026 | Modern Alternative |
|---|---|---|
| Thin Context | Leads to hallucinations and generic code. | Use High-Fidelity Packing. |
| Token Bloat | High latency and poor reasoning. | Use Semantic Filtering. |
| Flat History | Agent loses track of past decisions. | Use Memory Rehydration. |
| Manual Symbol Hunt | Slow and prone to missing definitions. | Use Symbolic Project Maps. |
| Ignoring Rules | Inconsistent architecture. | Use Hierarchical Inheritance. |
📦 Automated Context Packing
We use Repomix and gitingest to feed the models:
- Structure: Group files by domain (Logic, Types, Tests).
- Optimization: Exclude noise (node_modules, dist, git).
- Security: Mandatory secret scrubbing before ingestion.
See References: Context Packing for workflows.
🐘 Symbolic Project Mapping
When projects are large, don't read everything—use a map.
- JSON Maps: Indexing every export and its file path.
- Symbolic RAG: fetching only relevant files based on symbol dependency.
📖 Reference Library
Detailed deep-dives into Information Engineering:
- Impeccable DNA: High-fidelity design standards.
- Context Packing: Bundling artifacts for LLMs.
- Symbolic Mapping: Navigating large codebases.
- Memory Rehydration: Persistent mission context.
- Inheritance Models: Global vs Local rules.
Updated: January 22, 2026 - 21:40