analyze

name	analyze
description	Visible Harness analyze entry. Use after experiment runs to turn results into interpretation, decisions, and next-run or writing guidance.
argument-hint	[run or report path]
allowed-tools	Read, Write, Edit, Bash, Glob, Grep

Analyze

Use /analyze as the human-facing alias for result analysis. This is not a separate Skill Contract.

Read and follow:

• ../../../.claude/skills/evaluate/SKILL.md
• ../../../.claude/Workflow_Guide.md
• ../../../CLAUDE.md
• ../../../AGENTS.md

Produce decision-ready insights that guide the next /run, a /grill pivot, or /write.

After updating completed run evidence, refresh docs/30_evidence/Experiment_Evidence_Index.{json,md} using tooling/evidence/build_experiment_evidence_index.py so /write can consume experiment results without treating iteration_log.json as the sole source of truth. If not run, report NOT_RUN with the reason.