Tooluck logoTooluck
SKILL.md

eval-report

Agent skill fromagentscope-ai/OpenJudge

Use when the user has run multiple evaluation skills and wants a comprehensive analysis — maturity assessment, cross-skill signals, trends, prioritized actions, and an executive summary. Also use when the user mentions eval health check, evaluation audit, ship readiness, evaluation maturity, or "how good is my evaluation system itself." This is a read-only analysis skill.

How to install eval-report

install eval-report
# install the OpenJudge pack with the skills CLI
npx skills add agentscope-ai/OpenJudge

# or add only this skill to Claude Code: copy the folder

skills/eval_pipeline/04-eval-report/

# into

~/.claude/skills/04-eval-report/ (all projects)

.claude/skills/04-eval-report/ (one project)

skills/eval_pipeline/04-eval-report/SKILL.md

Apache-2.0Full file
1<HARD-GATE>
2NO recommendation WITHOUT statistical evidence backing it.
3NO "system ready" declaration WITHOUT all calibrated judges passing AND all production gates green.
4NO trend analysis WITHOUT at least 2 data points in history.
5</HARD-GATE>
6
7# Eval Report
8
9Synthesize everything from your evaluation journey into a comprehensive report.
10This skill is read-only — it analyzes what exists, doesn't create new graders or datasets.
11
12## When to Activate
13
14- You've run 2+ evaluation skills and want the big picture
15- You need to report evaluation status to non-technical stakeholders
16- You're making a ship/no-ship decision and need evidence
17- The evaluation system has been running for a while — time for a health check
18
19## Checklist
20
21You MUST create a task for each item and complete them in order:
22
231. **Inventory scan** — catalog everything in eval-design.md + runs/ history
242. **Maturity assessment** — 5 dimensions × 4 levels
253. **Cross-skill signal synthesis** — consistent findings + contradictions
264. **Weakness diagnosis** — failure concentration, correlations, stratum gaps
275. **Root cause classification** — system / metric / data / unclear
286. **Prioritized recommendations** — P0/P1/P2 actions with impact estimates
297. **Executive summary** — ship readiness + top 3 risks + next actions
30
31## Step 1: Inventory Scan
32
33Read `eval-design.md` and all `runs/` directories. Build a timeline:
34
35```
36Timeline:
37 2026-04-15 01-eval-design → 5 failure modes → 3 dimensions from 200 traces
38…

Excerpt shown under the repository's Apache-2.0 license.

More skills in OpenJudge

Keep exploring

Similar skill repositories

thedotmack /

claude-mem
116k

Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More

CCCXGHGM+135 skills

Newsletter

Join the Community

Subscribe to our newsletter for the latest news and updates