Calibrate assessment rubrics by reviewing agent work in GitHub/GitLab PRs and feeding human comments back into the rubric. Use this skill when the user wants to: - Calibrate, tune, or sanity-check assessment criteria / dimensions of a benchmark - Review trial diffs alongside the LLM-as-a-Judge scores in a PR/MR - Investigate why judge scores feel off, too harsh, too lenient, or misaligned with how a human would grade the code - Pull review comments back from PRs/MRs and turn them into concrete rubric edits Even if the user doesn't say "calibrate" — if they're worried the LLM judge's scores diverge from human judgment, or want to align scores with a real developer's opinion before freezing a benchmark, this skill applies.
Internal skill for developing and maintaining nasde-toolkit itself. Use this skill when: - Making changes to nasde-toolkit source code (CLI, runner, evaluator, config, agents) - Refactoring or adding features to the toolkit - Fixing bugs in the evaluation pipeline - Updating dependencies or integration points (Harbor, Opik, `claude` / `codex` CLI subprocess backends) This skill defines the verification protocol that must be followed after any significant change.
Create coding agent benchmarks for evaluation with nasde. Use this skill when the user wants to: - Create a new benchmark project (set of tasks for evaluating coding agents) - Add tasks to an existing benchmark - Create or modify agent variants (configurations that control agent behavior) - Set up assessment dimensions and scoring criteria - Verify that a new benchmark's Docker environment and tests work Even if the user doesn't say "benchmark" — if they're talking about creating coding challenges for AI agents or setting up evaluation criteria, this skill applies.
Design, refactor, analyze, and review code by applying the principles and patterns of tactical domain-driven design. Triggers on: domain modeling, aggregate design, 'entity', 'value object', 'repository', 'bounded context', 'domain event', 'domain service', code touching domain/ directories, rich domain model discussions.
Surgical code refactoring to improve maintainability without changing behavior. Covers extracting functions, renaming variables, breaking down god functions, improving type safety, eliminating code smells, and applying design patterns. Less drastic than repo-rebuilder; use for gradual improvements.
Run coding agent benchmarks and verify results with nasde. Use this skill when the user wants to: - Run a benchmark (all tasks, single task, specific variant) - Re-run assessment evaluation on existing trial results - Check or verify results in Opik (traces, feedback scores, experiments) - Troubleshoot a failed benchmark run - View or compare trial results Even if the user doesn't say "benchmark" — if they're talking about running evaluations, checking scores, or analyzing agent performance, this skill applies. After every run that uses --with-opik, ALWAYS verify results via Opik REST API — don't wait for the user to ask.
Design, refactor, analyze, and review code by applying the principles and patterns of tactical domain-driven design. Triggers on: domain modeling, aggregate design, 'entity', 'value object', 'repository', 'bounded context', 'domain event', 'domain service', code touching domain/ directories, rich domain model discussions.
Design, refactor, analyze, and review code by applying the principles and patterns of tactical domain-driven design. Triggers on: domain modeling, aggregate design, 'entity', 'value object', 'repository', 'bounded context', 'domain event', 'domain service', code touching domain/ directories, rich domain model discussions.