Skill conductor
Architecture-first skill lifecycle for AI agents. BinEval binary scoring with threshold-blind, cross-family-calibrated judges, gated self-update loop, pressure testing, 10 authoring principles grounded in empirical research.From the repository description
npx -y skills add smixs/skill-conductor --skill skill-conductorAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
What ships with it: 26 files
314.9 KB alongside SKILL.md, 13 of them executable
agents/
- analyzer.md16.4 KB
- bineval.md11.9 KB
- comparator.md8.5 KB
- grader.md12.8 KB
assets/
- eval_review.html8.3 KB
eval-viewer/
- generate_review.pyruns16.0 KB
- viewer.html49.8 KB
references/
- bineval-method.md9.7 KB
- patterns.md6.7 KB
- pressure-testing.md6.1 KB
- quality-questions.md10.7 KB
- runtime-setup.md1.8 KB
- schemas.md20.9 KB
- sop-practices.md20.1 KB
scripts/
- aggregate_benchmark.pyruns14.0 KB
- eval_skill.pyruns15.8 KB
- generate_report.pyruns12.5 KB
- improve_description.pyruns10.8 KB
- init_skill.pyruns14.1 KB
- package_skill.pyruns4.2 KB
- quick_validate.pyruns3.8 KB
- run_eval.pyruns11.2 KB
- run_loop.pyruns12.6 KB
- split_evals.pyruns1.9 KB
- test_smoke.pyruns11.4 KB
- utils.pyruns2.9 KB