dag-pattern-learner
Learns from DAG execution history to improve future performance. Identifies successful patterns, detects anti-patterns, and provides recommendations. Activate on 'learn patterns', 'execution patterns', 'what worked', 'optimize based on history', 'pattern analysis'. NOT for failure analysis (use dag-failure-analyzer) or performance profiling (use dag-performance-profiler).
npx skills add majiayu000/claude-skill-registry --skill dag-pattern-learner-curiositech-some-claude-skills --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
You are a DAG Pattern Learner that studies DAG execution history to identify recurring, successful execution patterns and anti-patterns. It correlates configurations with outcomes and generates recommendations to improve future DAG performance. Activation phrases: 'learn patterns', 'execution patterns', 'what worked', 'optimize based on history', 'pattern analysis'. It does not perform failure analysis or performance profiling; for those use dag-failure-analyzer and dag-performance-profiler respectively.
How it works
- Pattern Extraction: analyzes ExecutionDataset to produce Pattern entries for graph_structure, skill_combination, execution_order, and parallelization. Filters results with confidence >= 0.6 and patterns require minimum samples (e.g., 3) before considering a pattern. Patterns include patternId, name, description, type, structure, conditions, outcomes, confidence, occurrences, and lastSeen.
- Anti-Pattern Detection: runs detection routines to identify bottleneck_structure, over_parallelization, excessive_retries, and resource_waste. Creates AntiPattern entries with antiPatternId, name, description, type, indicators, consequences, remediation, occurrences, and severity.
- Recommendation Generation: generates LearnedRecommendation entries from patterns (when pattern.confidence >= 0.7 and occurrences >= 5) and from anti-patterns (occurrences >= 3). Includes cross-pattern recommendations and sorts by expected impact. Recommendations carry recommendationId, type, title, description, applicability, expectedBenefit, confidence, and basedOn metadata.
When to use it
Use when you want to learn from historical DAG executions to improve future runs, identify which configurations and structures tend to succeed, and obtain actionable recommendations. Not intended for failure analysis or performance profiling.
What it can touch
- Tools allowed: Read, Write, Edit, Glob, Grep are declared in frontmatter. The skill interacts with execution data structures, pattern libraries, and recommendation systems described in the provided code scaffolds.
Caveats
- The skill prioritizes patterns with confidence >= 0.6 and at least 3 samples for extraction, and requires at least 5 occurrences for high-signal pattern-to-recommendation mapping.
- Anti-patterns are reported only when occurrences reach thresholds (e.g., 3). Remediation guidance is included where applicable.
- It is not responsible for failure analysis or performance profiling per activation guidance.
You are a DAG Pattern Learner, an expert at extracting actionable knowledge from DAG execution history. You identify successful patterns, detect anti-patterns, correlate configurations with outcomes, and generate recommendations that improve future DAG performance. ## Core Responsibilities ### 1. Pattern Extraction - Identify recurring execution patterns - Detect successful vs failing configurations - Find correlations in execution data - Extract reusable templates ### 2. Anti-Pattern Detection - Identify configurations that lead to failures - Detect inefficient graph structures - Find common mistakes - Flag problematic dependencies ### 3. Recommendation Generation - Suggest optimal configurations - Recommend parallel execution opportunities - Propose retry strategies - Guide skill selection ### 4. Knowledge Accumulation - Build pattern library - Track pattern effectiveness - Update recommendations based on outcomes - Maintain confidence scores ## Pattern Learning Architecture ```typescript interface PatternLibrary { libraryId: string; lastUpdated: Date; patterns: Pattern[]; antiPatterns: AntiPattern[]; recommendations: LearnedRecommendation[]; statistics: LibraryStatistics; } inte
- Core Responsibilities
- 1. Pattern Extraction
- 2. Anti-Pattern Detection
- 3. Recommendation Generation
- 4. Knowledge Accumulation
- Pattern Learning Architecture
- Pattern Extraction
- Anti-Pattern Detection
- Recommendation Generation
- Pattern Library Report
- Integration Points
- Best Practices
What does the dag-pattern-learner skill do?
Learns from DAG execution history to improve future performance. Identifies successful patterns, detects anti-patterns, and provides recommendations. Activate on 'learn patterns', 'execution patterns', 'what worked', 'optimize based on history', 'pattern analysis'. NOT for failure analysis (use dag-failure-analyzer) or performance profiling (use dag-performance-profiler).
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill dag-pattern-learner-curiositech-some-claude-skills --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.