Agent skill
core-context-management-learning-from-past-work
Sub-skill of core-context-management: Learning from Past Work (+2).
Install this agent skill to your Project
npx add-skill https://github.com/vamseeachanta/workspace-hub/tree/main/.claude/skills/_core/context-management/learning-from-past-work
SKILL.md
Learning from Past Work (+2)
Learning from Past Work
The skill tracks patterns across sessions:
# .claude/state/context-patterns.yaml
patterns:
frequently_referenced:
- ".claude/docs/agents.md" # 45 loads
- ".claude/docs/execution-patterns.md" # 32 loads
rarely_used:
- "verbose section X" # 0 references in 30 days
*See sub-skills for full details.*
## Daily Analysis Tasks
1. **Size Check**: Validate all CLAUDE.md files against limits
2. **Pattern Analysis**: Analyze git commits for instruction patterns
3. **Usage Tracking**: Check which docs were loaded
4. **Suggestion Generation**: Create improvement proposals
5. **Report Generation**: Output daily health report
## Improvement Workflow
- Validate sizes → Report violations
- Analyze patterns → Identify redundancy
- Check usage → Find unused content
- Generate suggestions → Propose changes
- Apply approved changes → Update files
- Commit → Track improvements
---
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
vamseeachanta/workspace-hub
gsd-complete-milestone
Archive completed milestone and prepare for next version
vamseeachanta/workspace-hub
gsd-reapply-patches
Reapply local modifications after a GSD update
vamseeachanta/workspace-hub
gsd-verify-work
Validate built features through conversational UAT
vamseeachanta/workspace-hub
gsd-thread
Manage persistent context threads for cross-session work
vamseeachanta/workspace-hub
clinical-trial-protocol
Generate clinical trial protocols for medical devices or drugs through a modular, waypoint-based architecture with research-only and full protocol modes.
vamseeachanta/workspace-hub
single-cell-rna-qc
Performs quality control on single-cell RNA-seq data (.h5ad or .h5 files) using scverse best practices with MAD-based filtering and comprehensive visualizations.
Didn't find tool you were looking for?