Claude Skills by fruggr

Drive the inter-LLM functional test harness for this MCP server. Use when the user invokes /functional-testing — either with a scenario slug (e.g. `01-namespace-readonly`) or `all`. Reads STATE.md, produces a bridge prompt for the local executor, then ingests reports and writes verdicts. Never reads `expected.md` until the executor has already pushed its report.

Create a functional validation plan for a feature or bugfix. Use whenever you author an implementation plan, finish a feature/bugfix with runtime-observable behaviour, or prepare a PR that needs independent end-to-end validation — even when validation isn't explicitly asked for.

Execute a functional validation plan and report the findings. Use whenever you're asked to validate, QA, functionally verify, or check a feature/bugfix on a branch, or you're handed a functional validation plan to run — even when the skill isn't named.