agent-sort

Classifies ECC components into DAILY and LIBRARY buckets using repo evidence.

Updated Mar 22, 2026
One-click install
npx skills add https://github.com/diazMelgarejo/orama-system --skill agent-sort-diazmelgarejo
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-sort
Source: https://github.com/diazMelgarejo/orama-system/tree/main/.cursor/.agents/skills/agent-sort
Command: npx skills add https://github.com/diazMelgarejo/orama-system --skill agent-sort-diazmelgarejo

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Full ECC installs load every skill, rule, and hook regardless of what a project actually uses, creating noisy context and stale configurations. This Skill builds an evidence-backed install plan so a repo only loads the components that match its real stack. ## Core Features & Use Cases - Evidence-Based Classification: Sorts skills, commands, rules, hooks, and extras into DAILY (always loaded) and LIBRARY (searchable on demand) buckets, with every DAILY decision citing concrete repo evidence like file extensions, lockfiles, and framework configs. - Parallel Review Passes: Splits the audit across six passes (agents, skills, commands, rules, hooks/scripts, extras) that can run as parallel subagents or sequentially. - Install Plan and Verification: Produces a DAILY inventory, LIBRARY inventory, install plan, and verification report, plus an optional skill-library router for searchable access to demoted components. - Use Case: A TypeScript/Next.js repo inherited a full ECC install including Python and Django rules. Run this Skill to demote off-stack components to LIBRARY, keep TypeScript rules in DAILY, and verify no stale hooks remain active. ## Quick Start Ask the agent to sort this repo's ECC components into DAILY and LIBRARY buckets and produce an evidence-backed install plan.

Frequently Asked Questions about agent-sort

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

FAQPage Schema
How do I trim an ECC install to only what my repo needs?

Run an evidence-based classification pass that sorts every ECC skill, command, rule, hook, and extra into DAILY or LIBRARY buckets. Each DAILY decision must cite concrete repo evidence such as file extensions, package.json, or framework configs.

What is the difference between DAILY and LIBRARY components?

DAILY components load every session because they match the repo's active language, framework, or workflow. LIBRARY components stay accessible through search or a router skill but are not loaded by default, reducing context overhead.

Can the review passes run in parallel with subagents?

Yes, the review splits into six passes covering agents, skills, commands, rules, hooks/scripts, and extras, which can run as parallel subagents. If subagents are unavailable, the same passes run sequentially with identical results.

Does demoting a component to LIBRARY delete it?

No, LIBRARY means the component remains installed and reachable through search, a skill-library router, or selective manual use. It is only removed from the default loaded surface, not deleted from the project.

When should I not use evidence-based ECC sorting?

Avoid it when a repo genuinely needs the full ECC bundle or when the stack is still undecided, since classification depends on concrete evidence like lockfiles and configs. Greenfield projects without established tooling lack the evidence base this approach requires.