Use when the user says /tes-bench, /tes:bench, or asks to plan, run, converge, inspect, or certify TES context-mesh benchmarks and behavior evidence.
How this skill is triggered — by the user, by Claude, or both
Slash command
/tilly-engineer-skills:tes-benchThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
`/tes-bench` is the preferred shared TES trigger for benchmark planning,
/tes-bench is the preferred shared TES trigger for benchmark planning,
fixture runs, convergence review, and behavior-evidence discussion.
/tes:bench is a compatible TES intent alias if the host reports it as an
invalid slash.
npm run benchmark:plan.npm run benchmark:run -- --backend fixture.npm run benchmark:converge only after run artifacts exist.Provides behavioral guidelines to reduce common LLM coding mistakes, focusing on simplicity, surgical changes, assumption surfacing, and verifiable success criteria.
Searches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.
npx claudepluginhub murillodutt/gate-pre-git --plugin tilly-engineer-skills