diff --git a/skills/fieldtest/SKILL.md b/skills/fieldtest/SKILL.md index 05d86b1..5664fe9 100644 --- a/skills/fieldtest/SKILL.md +++ b/skills/fieldtest/SKILL.md @@ -98,7 +98,7 @@ Hand the agent the carrier (see Handoff Contract). The agent: compiler torture-test. Toy problems find toy bugs. 3. For each task: - drafts the program in `.ailx` Surface form, - - saves it as `examples/fieldtest___.ailx`, + - saves it as `examples/fieldtest/__.ailx`, - runs `ail check` and `ail build` and `ail run`, - records the experience: what the agent reached for, what it had to back out of, what the diagnostic said, what surprised it, diff --git a/skills/fieldtest/agents/ailang-fieldtester.md b/skills/fieldtest/agents/ailang-fieldtester.md index b5a74e1..0eb3008 100644 --- a/skills/fieldtest/agents/ailang-fieldtester.md +++ b/skills/fieldtest/agents/ailang-fieldtester.md @@ -111,12 +111,12 @@ For each example, in this order: 1. Draft the program in `.ailx` Surface form. Reach for the milestone's new surface where it fits naturally — but do not contort an example to use a feature that doesn't fit. -2. Save as `examples/fieldtest___.ailx`, - e.g. `examples/fieldtest_22_1_eq_rational.ailx`. +2. Save as `examples/fieldtest/__.ailx`, + e.g. `examples/fieldtest/22_1_eq_rational.ailx`. 3. Run, in this order: ```bash - ail check examples/fieldtest_<...>.ailx - ail build examples/fieldtest_<...>.ailx -o /tmp/ft_ + ail check examples/fieldtest/<...>.ailx + ail build examples/fieldtest/<...>.ailx -o /tmp/ft_ /tmp/ft_ ``` Note: if your repo invokes `ail` as `cargo run -p ail --` instead, @@ -140,7 +140,7 @@ The canonical form is `.ail.json`. You do NOT hand-write it. After each `.ailx` runs cleanly, generate the JSON via: ```bash -ail render --json examples/fieldtest/<...>.ailx > examples/fieldtest_<...>.ail.json +ail render --json examples/fieldtest/<...>.ailx > examples/fieldtest/<...>.ail.json ``` (or whichever subcommand `ail --help` lists for the surface→json