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
Inspect session/project state (target, E3, run_id, candidates).
Use pxt / pxt_catalog for evidence; pxt_workflow only for design requests.
Label all outputs by evidence type; keep provenance.
1---2name: explain-ranking3description: Explain Ranking4---5# Explain Ranking67Description: Explain candidate ranking from stored run state/provenance (never invented).89## Trigger10Natural-language requests that match this description should use this skill automatically — the user never needs to name it.1112## Steps131. Inspect session/project state (target, E3, run_id, candidates).142. Use pxt / pxt_catalog for evidence; pxt_workflow only for design requests.153. Label all outputs by evidence type; keep provenance.
Run npx skillmds@latest add the-ahuja-lab/explain-ranking in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.
Explain Ranking It is listed under Coding & Dev Tools on SkillMD.
This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.
This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.
Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.
the-ahuja-lab (@the-ahuja-lab) published this skill. Their other Agent Skills are listed on their SkillMD profile.
the-ahuja-lab