How do I install the Eval Report skill?

Run npx skillmds@latest add hoangsonww/eval-report-2 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.

Is Eval Report safe to use?

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.

Which AI agents work with Eval Report?

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.

Is Eval Report free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Eval Report?

hoangsonww (@hoangsonww) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Eval Report by hoangsonww — Agent Skill

Name: Eval Report
Author: hoangsonww

Eval Report

Emit a Markdown weekly digest of briefing quality scores (coverage, composite stats, axis medians, per-day table). Use when the user asks for a "weekly report", "eval summary", or "quality digest" for a specific date range.

hoangsonww Updated Sep 21, 2026

File contents

Eval — Weekly Markdown Report

Pull the trailing N-day window from eval/store.sqlite and emit a Markdown digest suitable for publishing to Notion / Teams / Slack, or for committing under logs/eval-reports/.

How to invoke

make eval-report D=YYYY-MM-DD W=7                            # 7-day window to stdout
make eval-report D=YYYY-MM-DD W=14 OUT=logs/eval-week.md     # write to file

Direct invocation:

python3 eval/report.py --as-of YYYY-MM-DD --window 7 --out logs/eval-week.md

Behavior

Fetch all eval_runs rows in [as_of - window + 1, as_of].
Pick the latest run per card_date (so re-runs don't double-count).
Compute coverage (N / window days judged), composite min/max/median, and per-axis medians.
Emit:
- H1 header with the date range
- Coverage + composite stats
- Axis medians table
- Per-day detail table (date, composite, F/N/D/S/C, judge model, truncated notes)

When to use

Monday morning summary across the previous 7 days.
Investigating a drift alert (make eval-drift) — the per-day table shows which axes are dragging.
After a re-baselining workflow, to confirm the new judge/prompt produces consistent quality.

What to tell the user

If OUT is set, mention the file path and a quick cat or preview command. If piping to stdout, show the digest verbatim (the user can scroll the terminal). For Notion/Teams publishing, point at scripts/notify-teams.sh or the Notion MCP — the harness intentionally does not publish on its own.

Frequently asked questions