Enhanced Just-In-Time document loading system that discovers, loads, and caches relevant documentation based on user intent and project context. Use when users need specific documentation on demand.
Purpose: Load relevant documentation on-demand based on user intent and context.
Primary Tools:
Trigger Patterns:
The system recognizes documentation needs through several patterns:
Question-Based Triggers:
Technology-Specific Triggers:
Domain-Specific Triggers:
Pattern-Based Triggers:
The system retrieves documentation from multiple sources in priority order:
Local Project Documentation (Highest Priority):
Official Documentation Sources:
Community Resources:
Real-Time Web Research:
Intent Analysis Process:
Source Prioritization:
Context-Aware Caching:
Content Quality Evaluation:
Relevance Ranking:
Authentication Implementation Workflow:
Database Optimization Workflow:
New Technology Adoption Workflow:
Network Failures:
Content Quality Issues:
Relevance Mismatches:
Caching Strategy:
Efficient Loading:
Batch Processing:
Multi-Source Aggregation:
Context Persistence:
Proactive Loading:
Agents:
Skills:
Commands:
| Rationalization | Reality |
|---|---|
| "I already know where the docs are, JIT loading is unnecessary" | JIT docs discover context you did not know existed. Manual lookup misses cross-references. |
| "Loading all docs upfront is simpler than on-demand" | Upfront loading wastes tokens on irrelevant content. JIT loads only what matches the current intent. |
| "The cached version is recent enough" | Stale caches serve stale answers. Validate cache freshness before using cached documents. |
| "This task does not need documentation" | Every non-trivial task benefits from context. JIT docs surface relevant constraints proactively. |
| "I will find the right doc by browsing the directory" | Directory browsing is O(n). JIT matching by intent keywords is O(1) for the user. |