Show HN: Skillroll – pure Markdown evals for any skill using a Dungeon Master
Source: Show HN ·
Maintaining agentic skills alway felt like a chore due to how hard it was to test them. Writing evals is just too complex to do for every small skill, So I wrote Skillroll - an eval framework that can test any skill using only an eval.md How? instead of setting up an intricate eval environment, you write a short world description, run a Dungeon Master agent that simulates that world, and route all tool calls to that agent. each eval.md is a test case with a "world description", "agent prompt and "judgement criteria" for an llm judge to consider when rating pass/fail. I think Skillroll is espec
Frequently Asked Questions
What is Show HN: Skillroll – pure Markdown evals for any skill using a Dungeon Master?
Show HN: Skillroll – pure Markdown evals for any skill using a Dungeon Master is a tool discovery curated from Show HN. Maintaining agentic skills alway felt like a chore due to how hard it was to test them. Writing evals is just too complex to do for every small skill, So I wrote Skillroll - an…
How can I access or experience this?
You can experience this content directly on its original host (Show HN) by clicking the "Open Original" button.
Where does this content come from?
Curated from Show HN by the OnSuggest team to surface the most interesting and serendipitous content on the web.
More like this
All Developer tools discoveries →Show HN: Claudette - Mistral models in Claude Code
Claude Code + Mistral = 🧡. Contribute to raed667/claudette development by creating an account on GitHub.
Show HN: Snippai – an open-source, promptless Mathpix alternative
Snip Anything Solve Everything. Contribute to xyTom/snippai development by creating an account on GitHub.
Show HN: Canban – Kanban and Workflow and Herdr Workbench for CLI Agents
Canban = Kanban + herdr workbench. Contribute to jjyr/canban development by creating an account on GitHub.
Show HN: SecondGlow – use a 5K or 4K iMac as a monitor for an Apple Silicon Mac
Use your 27-inch 5K or 21.5-inch 4K iMac as an external monitor for your Mac with Apple silicon. One cable, USB or Thunderbolt. Free for 7 days.
Show HN: Fondue – A meeting where everyone talks at once
Goal for this session A public Fondue demo for Hacker News readers, on one question: if you could pause AI development worldwide for five years, would you? So far two people would probably pause and …
Show HN: I built a free, Python micro-learning platform with real Python tasks
Learn Python from zero with explanations, quizzes, and real coding exercises. Build small programs in your browser. Complete beginner course free; no account or setup required.