| name | intelligence/pattern-recognition |
| description | Use when analyzing recurring behaviors, identifying trends, or spotting anti-patterns across code, architecture, strategy, content, or behavior. Distinguishes patterns (good recurring solutions) from anti-patterns (recurring problems). Default skill for Starlight Sage and Starlight Sentinel. |
| type | substrate |
Pattern Recognition
"What has happened before will happen again. Recognize the pattern, master the game."
When This Skill Activates
- Analyzing recurring behaviors, identifying trends, spotting anti-patterns
- Keywords: "pattern", "recurring", "similar", "trend", "anti-pattern"
- Default for: Starlight Sage, Starlight Sentinel
What This Skill Does
Identifies recurring patterns across code, architecture, strategy, content, and behavior. Distinguishes between patterns (good recurring solutions) and anti-patterns (recurring problems).
Procedures
Procedure 1: Pattern Identification
- Observe the current situation
- Query vaults for similar past situations
- Identify structural similarities
- Name the pattern (use existing pattern names when applicable)
- Document the pattern's characteristics
- Assess confidence in pattern match (High/Medium/Low)
- Recommend action based on pattern
Procedure 2: Anti-Pattern Detection
- Identify symptoms of potential problems
- Query Technical Vault for known anti-patterns
- Check if current approach matches anti-pattern characteristics
- If match: document the anti-pattern and its typical consequences
- Provide the known solution/alternative
- Assess severity (Critical/High/Medium/Low)
Procedure 3: Trend Analysis
- Collect data points over time
- Identify direction (increasing, decreasing, stable, cyclical)
- Assess rate of change
- Project trajectory
- Identify inflection points
- Recommend action based on trend
Integration Points
- Vault: All vaults (patterns exist everywhere)
- Agents: Sage (teaching patterns), Sentinel (anti-patterns), All (pattern awareness)
- Transmissions: Broadcast newly identified patterns
Quality Criteria
- Is the pattern clearly named and described?
- Is the confidence level appropriate?
- Is the pattern actionable (not just interesting)?
- Have anti-patterns been checked?
