seed-resolution

Name: seed-resolution
Availability: InStock
Author: Allen

Select the best seed URL per queue item and output a strict JSON decision set.

Updated Aug 23, 2026

Search Tags:#data-pipeline #json-output #seed-resolution #semantic-queue #url-selection #llm-task

Ready to run

npx skills add https://github.com/AllenZhou/MIRISE --skill seed-resolution

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: seed-resolution
Source: https://github.com/AllenZhou/MIRISE/tree/main/agents/uae-knowledgebase-builder/skill/seed-resolution
Command: npx skills add https://github.com/AllenZhou/MIRISE --skill seed-resolution

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill reads the semantic queue produced by resolve-seed-urls --prepare and outputs a strict JSON decision set containing the best seed URL per item, enabling deterministic downstream processing.

Core Features & Use Cases

Per-item URL selection: choose one best_url from candidates for each queue item.
Strict JSON output: output conforms to schema_version, queue_run_id, generated_at, and decisions.
LLM-task integration: can serve as a unified llm-task entry point for seed resolution tasks.
Use Case: Given a semantic_queue.json with multiple candidate URLs per item, produce a decisions file ready for state_db update or downstream ingestion.

Quick Start

Run the seed-resolution task using the unified llm-task entry to generate the decisions JSON.

Frequently Asked Questions about seed-resolution

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

FAQPage Schema

How do I select the best seed URL from a semantic queue for downstream processing?▼

To select the best seed URL from a semantic queue, you evaluate candidate URLs per item and output a strict JSON decision set. This ensures deterministic downstream processing by enforcing that the chosen best_url is drawn directly from the item's provided candidates list.

What is the required JSON schema for seed resolution decision outputs?▼

The required JSON schema for seed resolution outputs includes schema_version, queue_run_id, generated_at, and decisions fields. This strict JSON decision set conforms to the seed_resolution_schema.json and ensures deterministic downstream ingestion.

How do I generate a JSON decision set from resolve-seed-urls --prepare outputs?▼

To generate a JSON decision set from resolve-seed-urls --prepare outputs, run the seed-resolution task using the unified llm-task entry. This processes the semantic queue and selects one best_url from candidates for each queue item.

Can I use an arbitrary URL as the best_url in a seed resolution task?▼

No, you cannot use an arbitrary URL in a seed resolution task. The skill strictly enforces that the best_url must be drawn directly from the item's candidates[].url list provided in the semantic queue.

Does the seed resolution task integrate with the llm-task entry point?▼

Yes, the seed resolution task integrates with the llm-task entry point. It serves as a unified entry for seed resolution tasks, processing the semantic queue to produce a decisions file ready for state_db update.

What happens if my JSON output does not conform to the seed_resolution_schema.json?▼

If your JSON output does not conform to the seed_resolution_schema.json, deterministic downstream processing will fail. The skill enforces strict JSON schema conformance, requiring schema_version, queue_run_id, generated_at, and decisions fields to validate the data pipeline.