# Explain Ranking

> Explain Ranking

- Skill: `the-ahuja-lab/explain-ranking` (Agent Skill)
- Install (CLI): `npx skillmds@latest add the-ahuja-lab/explain-ranking`
- Raw SKILL.md: https://api.skillmd.com/api/skills/the-ahuja-lab/explain-ranking/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- Author: the-ahuja-lab (https://skillmd.com/u/the-ahuja-lab)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/the-ahuja-lab/explain-ranking

---

# Explain Ranking

Description: Explain candidate ranking from stored run state/provenance (never invented).

## Trigger
Natural-language requests that match this description should use this skill automatically — the user never needs to name it.

## Steps
1. Inspect session/project state (target, E3, run_id, candidates).
2. Use pxt / pxt_catalog for evidence; pxt_workflow only for design requests.
3. Label all outputs by evidence type; keep provenance.