From agent-harness
Define and run validation before PR handoff or task completion.
How this skill is triggered — by the user, by Claude, or both
Slash command
/agent-harness:validation-gateThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Validation should prove the changed behavior, not just produce a green command.
Validation should prove the changed behavior, not just produce a green command.
Choose validation in this order:
Record:
Projects can add .agent-harness/required-checks.txt with one shell command per line. Harness hooks
and agents should treat those commands as required before completing [harness] tasks.
Guides creation, editing, and verification of skills for AI coding agents using test-driven development with subagent scenarios. Use when authoring or debugging skills.
npx claudepluginhub majiayu000/agent-harness --plugin agent-harness