langchain-eval-engineering
Inspect an agent repository and optional traces, interview the user, write reviewed Task Specs, build and audit Harbor tasks, and bootstrap reusable project World Knowledge Skills. Use for agent evals, benchmark design, Task generation, controlled Environments, synthetic data, Verifiers, Harbor runs, calibration, or continuous benchmark maintenance.
Pinned to revision 8f4f0a4fee70, so it is the text this page describes rather than whatever the author pushed since.
Files
- skills/langchain-eval-engineering/SKILL.md
- skills/langchain-eval-engineering/agents/openai.yaml
- skills/langchain-eval-engineering/assets/task/Task.md.template
- skills/langchain-eval-engineering/assets/world-skill/SKILL.md.template
- skills/langchain-eval-engineering/references/calibration.md
- skills/langchain-eval-engineering/references/discovery.md
- skills/langchain-eval-engineering/references/environment-building.md
- skills/langchain-eval-engineering/references/examples/service-desk.md
- skills/langchain-eval-engineering/references/harbor.md
- skills/langchain-eval-engineering/references/multi-turn-simulation/guide.md
- skills/langchain-eval-engineering/references/multi-turn-simulation/harbor_example.py
- skills/langchain-eval-engineering/references/multi-turn-simulation/model_user.py
- skills/langchain-eval-engineering/references/multi-turn-simulation/runner.py
- skills/langchain-eval-engineering/references/patterns.md
- skills/langchain-eval-engineering/references/synthetic-data.md
- skills/langchain-eval-engineering/references/task-design.md
- skills/langchain-eval-engineering/references/task-implementation.md
- skills/langchain-eval-engineering/references/verifier-design.md
- skills/langchain-eval-engineering/references/world-knowledge.md
- skills/langchain-eval-engineering/scripts/compare_tool_schemas.py
- skills/langchain-eval-engineering/scripts/snapshot_sqlite_state.py
Every link opens the file at its source, pinned to the revision this page describes.