Read and summarize the validation result without rewriting the run artifacts unless the user asked for a fix.
Rules:
This entry skill is a thin Claude Code surface over tools.validation.contract_validation.
Keep the validator as the source of truth for run readiness.
1---2name: co-scientist-validate-23description: co-scientist-validate4---5# co-scientist-validate67Goal:89- Validate one Co-Scientist run directory from Claude Code.1011Expected input:1213- one run directory such as `runs/test1`1415Execution steps:16171. Resolve the run directory.182. Decide whether the user wants a fresh-run validation or a resume validation.193. Run one of:2021 ```bash22 python -m tools.validation.contract_validation <run-dir> --skill co-scientist-pipeline23 ```2425 or2627 ```bash28 python -m tools.validation.contract_validation <run-dir> --resume --skill co-scientist-pipeline29 ```30314. Read and summarize the validation result without rewriting the run artifacts unless the user asked for a fix.3233Rules:3435- This entry skill is a thin Claude Code surface over `tools.validation.contract_validation`.36- Keep the validator as the source of truth for run readiness.
Run npx skillmds@latest add panjose/co-scientist-validate-2 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.
co-scientist-validate It is listed under Coding & Dev Tools 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.
panjose (@panjose) published this skill. Their other Agent Skills are listed on their SkillMD profile.
panjose