aiwg/tools/eval/datasets/tool-use/multi-step-chain.yaml

Deployment tool and support utility for AI context. Copies agents, skills, commands, rules, and behaviors into the paths each AI platform reads (Claude Code, Codex, Copilot, Cursor, Warp, OpenClaw, and 6 more) so one source of truth works across 10 platfo

id: tool-use-multi-step
dimension: tool-use
difficulty: intermediate
prompt: |
  I need to find all files that import "lodash", then check if each file
  also uses the "merge" function from lodash. List the sequence of tool
  calls you would make with their parameters.
expected:
  tool_calls:
    - tool: Grep
      params_contain:
        pattern: "lodash"
    - tool: Read
scoring:
  correct_tool: 0.4
  correct_params: 0.4
  no_hallucination: 0.2