- Treat real external side effects as unsafe by default.
- Prefer synthetic company fixtures and mocked providers for fast local checks.
- Grade outcomes, not exact tool choices.
- Rubrics should include source traceability, freshness, hallucination resistance, cancellation behavior, and bounded-runtime behavior.
- Keep eval artifacts out of git unless they are stable fixtures.
Ycagent Research Eval
Design and run lightweight evals for the YC company research agent. Use when changing Trigger.dev tasks, E2B browsing, LLM providers, source crawling, extraction, or synthesis.
Ycagent Research Eval by arvindrk · fdcd842
npx skillmds@latest add arvindrk/ycagent-research-eval File contents
---name: ycagent-research-evaldescription: Design and run lightweight evals for the YC company research agent. Use when changing Trigger.dev tasks, E2B browsing, LLM providers, source crawling, extraction, or synthesis.---1. Treat real external side effects as unsafe by default.2. Prefer synthetic company fixtures and mocked providers for fast local checks.3. Grade outcomes, not exact tool choices.4. Rubrics should include source traceability, freshness, hallucination resistance, cancellation behavior, and bounded-runtime behavior.5. Keep eval artifacts out of git unless they are stable fixtures.
arvindrk/ycagent.ai/tree/main/.agents/skills/ycagent-research-eval commit fdcd8422ac
Frequently asked questions
Run npx skillmds@latest add arvindrk/ycagent-research-eval 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.
Design and run lightweight evals for the YC company research agent. Use when changing Trigger.dev tasks, E2B browsing, LLM providers, source crawling, extraction, or synthesis. It is listed under AI & ML on SkillMD.
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.
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.
Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.
arvindrk (@arvindrk) published this skill. Their other Agent Skills are listed on their SkillMD profile.