merge

Combine pipe-format result blocks into one deduplicated unified output.

Updated Feb 20, 2026
One-click install
npx skills add https://github.com/supertyrelle/pelley --skill merge-supertyrelle
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: merge
Source: https://github.com/supertyrelle/pelley/tree/main/skills/merge
Command: npx skills add https://github.com/supertyrelle/pelley --skill merge-supertyrelle

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill removes the manual work of reconciling scattered investigation results by combining multiple context blocks into one clear, deduplicated view.

Core Features & Use Cases

  • Deduplication: Detects repeated findings across parallel runs and keeps the richest version.
  • Source Attribution: Preserves every contributing source so merged results remain traceable.
  • Confidence Handling: Upgrades confidence when multiple inputs confirm the same item.
  • Pipeline Reconstruction: Rebuilds provenance across chained workflows so the final output reflects how the result was formed.
  • Use Case: After running several /gather passes on different code areas, use this Skill to consolidate the evidence into a single prioritized report.

Quick Start

Use the merge skill to combine all pipe-format findings in context, deduplicate overlaps, and return one unified result.

Frequently Asked Questions about merge

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

FAQPage Schema
How do I deduplicate overlapping findings from parallel pipeline runs?

To deduplicate overlapping findings from parallel pipeline runs, use a consolidation skill that combines multiple pipe-format result blocks into one unified output. It detects repeated findings across scattered contexts and keeps the richest version.

What is the best way to merge scattered investigation results while preserving source attribution?

Merging scattered investigation results while preserving source attribution requires a tool that rebuilds pipeline provenance. This ensures every contributing source remains traceable within the final deduplicated output.

Can I upgrade confidence levels when multiple parallel analysis runs confirm the same evidence?

Yes, you can upgrade confidence levels when multiple parallel analysis runs confirm the same evidence. The merge process automatically upgrades confidence when multiple inputs validate the same item.

Does the deduplication process support topic filtering for specific conversation contexts?

The deduplication process does support optional topic filtering for specific conversation contexts. This allows you to narrow the consolidation scope when combining scattered findings from parallel gather runs.

When should I not use automated consolidation for parallel gather passes?

You should not use automated consolidation for parallel gather passes when your conversation context lacks pipe-format result blocks. The skill specifically requires this structured format to reconstruct provenance and deduplicate overlaps correctly.