<< All versions
Skill v1.0.0
currentLLM-judged scan90/100sakanaai/ai-scientist-v3/edit-program
──Details
PublishedOctober 22, 2026 at 08:50 PM
Content Hashsha256:d375e68d20ef0ee6...
Git SHAdf8313889a00
──Files
Files (1 file, 2.2 KB)
SKILL.md2.2 KBactive
SKILL.md · 37 lines · 2.2 KB
version: "1.0.0" name: edit-program description: Edit a program for next experimentation.
What the skill is about
Create the next program variant safely for iterative optimization experiments.
When to use the skill
- After reviewing the latest evaluation results (or at the very beginning).
- When you want to test a new idea without overwriting previous attempts.
What to do
- Find the next unused program index
<idx>from{{RESULTS_DIR}}/program_<idx>. - Clone the full previous program project (
program_<idx-1>) into the newprogram_<idx>with the trusted clone utility:
${TASK_PYTHON:-$WRAPPER_PYTHON} -I -m src.investigation.program_clone --from "{{RESULTS_DIR}}/program_<idx-1>" --to "{{RESULTS_DIR}}/program_<idx>"- The utility creates the destination and applies the
program_spec.tomlcopy rules without carrying evaluator artifacts. - For every source after
program_0, the utility refuses to clone until canonical evaluation and mirrored rubric artifacts prove the previous iteration is complete. - Do not use
cp,cp -r,cp -a,rsync, or any other recursive copy. If the trusted clone fails, stop the attempt and report the error; do not fall back to another clone method.
- Edit code under
{{RESULTS_DIR}}/program_<idx>/src/**(and updateprogram_spec.tomlif you change entrypoint or language). - Keep all older
program_<idx>directories unchanged. - Never edit
{{TASK_DIR}}/evaluate.pyor{{TASK_DIR}}/capture.py. - Before creating
program_<idx>, ensure previous evaluatedprogram_<idx-1>already has:
metrics.jsoncorrect.jsonprogram_<idx-1>/rubric_status.json{{RESULTS_DIR}}/rubric_status.jsonmirrored to that latest evaluated artifact
- If latest rubric status has
overall_pass: true, stop; do not create another program directory. - Single-attempt evaluation cap: never create/evaluate beyond
program_{{MAX_PROGRAM_EVALS_PER_ATTEMPT}}.
Example usage
bash
${TASK_PYTHON:-$WRAPPER_PYTHON} -I -m src.investigation.program_clone --from "{{RESULTS_DIR}}/program_2" --to "{{RESULTS_DIR}}/program_3"# edit {{RESULTS_DIR}}/program_3/src/** (and {{RESULTS_DIR}}/program_3/program_spec.toml if needed)