skills.rest
Connsulting
ConnsultingOFFICIAL
Explore all skills by this author →
GitHub

consolidate-actions

Execute merge, archive, delete, rescope, and get operations on stored learnings.

1|1|Updated Jan 12, 2026
Search Tags:#knowledge management#SQLite#backup#merge#archive#learnings#consolidation
One-click install
npx skills add https://github.com/Connsulting/claude-code-plugins --skill consolidate-actions-connsulting
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: consolidate-actions
Source: https://github.com/Connsulting/claude-code-plugins/tree/main/plugins/compound-learning/skills/consolidate-actions
Command: npx skills add https://github.com/Connsulting/claude-code-plugins --skill consolidate-actions-connsulting

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Accumulated learning documents become redundant or mis-scoped over time, and manually merging, archiving, or deleting them risks data loss. This Skill performs consolidation operations on learnings with automatic backups before any destructive action. ## Core Features & Use Cases - Merge Learnings: Combine multiple learning documents into a single file with preserved source attribution, tag aggregation, and optional dry-run preview. - Safe Deletion and Archiving: Delete or archive learnings with automatic backups stored in date-stamped directories under the archive folder. - Scope Management: Move learnings from repo scope to global scope, updating both the filesystem location and SQLite index entries. - Use Case: After a discovery pass flags five overlapping learnings about JWT patterns, run the merge action with a dry run to preview the result, then execute the merge to produce one consolidated document while the originals are backed up. ## Quick Start Ask the AI to merge the learnings with the given IDs into a single document named jwt-patterns using a dry run first to preview the changes.

Frequently Asked Questions about consolidate-actions

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I merge multiple learning documents into one file?▼

Run the merge action with comma-separated document IDs and a kebab-case name, for example merge --ids=id1,id2 --name=jwt-patterns. The script creates a combined document with source attribution, backs up the originals, and removes them from the index.

How can I preview a merge before executing it?▼

Use the --dry-run flag with the merge action to see what would happen without making changes. It returns the target path, files that would be deleted, source count, and resulting scope as JSON.

Are deleted learnings recoverable after running delete?▼

Yes, all destructive operations create backups in a date-stamped directory under the configured archive folder before removing files. Backups preserve the original content, and the SQLite entry is removed only after file operations succeed.

Can I move a learning from repo scope to global scope?▼

Yes, the rescope action moves a learning to the global directory and updates its metadata and index entry with a new ID. Rescoping back to a repo is not supported because it requires specifying a target repo path.

Why does the merge action fail with an error about document count?▼

Merge requires at least two valid document IDs; it returns an error if fewer than two documents are found. Verify the IDs using the get action first, since IDs must come from the consolidate-discovery output.

Related Skills

Explore More Software Engineering Skills→
flonatflonat
127

consolidate-memory

Consolidates MEMORY.md files by pruning duplicates, merging overlaps, and removing stale knowledge.

Community
Advanced
MSamiulHasnatMSamiulHasnat
1

AgentDB Vector Search

Index embeddings and perform context-aware similarity queries for document retrieval.

Community
Advanced
automatedigitalautomatedigital
1

github-code-review

Automate code reviews for local git changes and GitHub pull requests.

Official
Intermediate
Nomadiction8991Nomadiction8991

organizar-documentacao

Audit Git changes and normalize Markdown into a Diátaxis-aligned structure.

Community
Advanced