Eval Author — Development skill for Claude Code
Draft a new eval case (eval/cases/ .json) + scaffold its golden folder, golden_pending until captured on the VM.
How to install Eval Author
Installs to ~/.claude/commands/dynamics365ninja-d365fo-mcp-server-eval-author.md
mkdir -p ~/.claude/commands && curl -fsSL https://raw.githubusercontent.com/dynamics365ninja/d365fo-mcp-server/HEAD/.claude/commands/eval-author.md -o ~/.claude/commands/dynamics365ninja-d365fo-mcp-server-eval-author.md Restart Claude Code, or start a new session, for it to be picked up.
What Eval Author does
description: Draft a new eval case (eval/cases/.json) + scaffold its golden folder, golden_pending until captured on the VM. argument-hint: allowed-tools: Agent, Bash, Read, Edit, Write, Grep, Glob
Launch the **eval-author** subagent (Task tool, `subagent_type: eval-author`) to draft a new case for the eval catalog.
What to author: **$ARGUMENTS**
The subagent carries the authoring contract (mirror existing cases at the tier → dr
Alternatives in Development
- HERO Anti OverDefense — HERO = Hashing · Edge cases · Rubrics · Overbuild — the four shapes coding agents over-defend in 333 ★
- State Analyzer — You are a terminal state analyzer for Omux 94 ★
- Generate Ddd — Generate DDD components 63 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Eval Cases
Grow an eval case set from the placeholder rows to a real 15-25 - harvest genuine cases out of the repository
Agtmls New Skill
Scaffold a new AgtMLS skill with its metadata and both eval cases.
New Client
Onboard a client — scaffold a profile in the working project and seed its eval cases.
Eval Init
Scaffold an eval from the bundled eval template into the repo's evals/ project (shared _env.py and cache once
Warden Select
Measure pending token-warden candidate rules for an agent on the golden suite, evict or activate them, and rec
Init Cases
Разовый прогрев — case-mapper для активных дел без knowledge-map.md. Готовые карты не трогает
Related Agents
Think Research Framework
Researches a named thinking method, grades its evidence honestly on the seven-tier model, assesses overlap aga
Eval Implementer
Implementer role of the D365FO agent eval loop. Runs ON THE VM (mcp-server in full mode + C# bridge) against t
PDF Docx Generator
WRITE-access implementer for the resume/export domain — PDF/DOCX rendering, layout, fonts, pagination, golden