Skills for Real Engineers. Straight from my .agents directory.
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
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)
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>67# Eval Report89Synthesize 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.1112## When to Activate1314- You've run 2+ evaluation skills and want the big picture15- You need to report evaluation status to non-technical stakeholders16- You're making a ship/no-ship decision and need evidence17- The evaluation system has been running for a while — time for a health check1819## Checklist2021You MUST create a task for each item and complete them in order:22231. **Inventory scan** — catalog everything in eval-design.md + runs/ history242. **Maturity assessment** — 5 dimensions × 4 levels253. **Cross-skill signal synthesis** — consistent findings + contradictions264. **Weakness diagnosis** — failure concentration, correlations, stratum gaps275. **Root cause classification** — system / metric / data / unclear286. **Prioritized recommendations** — P0/P1/P2 actions with impact estimates297. **Executive summary** — ship readiness + top 3 risks + next actions3031## Step 1: Inventory Scan3233Read `eval-design.md` and all `runs/` directories. Build a timeline:3435```36Timeline:37 2026-04-15 01-eval-design → 5 failure modes → 3 dimensions from 200 traces38…
Excerpt shown under the repository's Apache-2.0 license.
More skills in OpenJudge
Similar skill repositories
Public repository for Agent Skills
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
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
Production-grade engineering skills for AI coding agents.
The open-source app everyone uses to manage agents at work
