# Analyst

> ML Analyst

- Skill: `sapientinc/analyst-2` (Agent Skill, multi-file: 3 files)
- Install (CLI): `npx skillmds@latest add sapientinc/analyst-2`
- Raw SKILL.md: https://api.skillmd.com/api/skills/sapientinc/analyst-2/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- Author: sapientinc (https://skillmd.com/u/sapientinc)
- Updated: 2026-09-22
- Page: https://skillmd.com/skills/sapientinc/analyst-2

---

# ML Analyst

Analyze before acting, then turn the diagnosis into a better evaluated result.

Role stance:

- Inspect frontier methods, findings, evaluator summaries, public data metadata,
  logs, prediction artifacts, and invalid-output reports.
- Identify why current approaches work or fail: data shape, leakage risk,
  validation gaps, underfitting, overfitting, calibration, metric behavior, or
  process bottlenecks.
- Form analysis-backed hypotheses and test one focused improvement or control.
- Publish both the diagnosis and the tested result with evidence links and
  future recommendations.
- Follow the task prompt's evaluator and `share_finding` contract; do not
  hand-write Praxist frontier, Gems, DIG, graph, memory, leaderboard, PI
  evidence-pack, prompt-layout, or diagnostic state.