agent-skills/create-plan/evals/evals.json
2026-07-29 17:45:19 +07:00

47 lines
2.8 KiB
JSON

{
"skill_name": "create-plan",
"evals": [
{
"id": 1,
"prompt": "Plan OAuth support for this application and leave an implementation-ready handoff, but do not change code.",
"expected_output": "Runs the pi-subagents dependency gate, delegates bounded local and external research where relevant, resolves material user questions, produces a stable-ID plan under .plans/, and iterates fresh independent plan review until clear or blocked. It does not implement.",
"files": []
},
{
"id": 2,
"prompt": "Review and improve .plans/cache-migration.md before anyone implements it.",
"expected_output": "Loads the existing unimplemented plan, verifies pi-subagents and required roles, inspects repository evidence, runs fresh plan reviewers, dispositions every finding, revises accepted items, re-reviews material changes, and leaves the plan Ready or explicitly Blocked.",
"files": []
},
{
"id": 3,
"prompt": "Research the current SDK docs and create a rollout plan for upgrading our integration.",
"expected_output": "Requires the researcher role in addition to the core planning roles, uses authoritative version-matched external evidence plus local context, asks about material migration choices, and produces an evidence-backed reviewed plan with exact validation commands and recovery guidance.",
"files": []
},
{
"id": 4,
"prompt": "Create an implementation plan for the authentication refactor.",
"expected_output": "Before repository research, checks for the active subagent tool, runs doctor, and lists executable roles. If pi-subagents or a required role is missing, it stops with the exact dependency problem and directs the user to their existing package-management method. For a declarative or Nix-managed setup it requires a configuration change, rebuild, and Pi restart; it never runs pi install, npm installation, or silently falls back.",
"files": []
},
{
"id": 5,
"prompt": "Implement the approved authentication plan now and run the tests.",
"expected_output": "Does not route to create-plan because this is implementation work; it uses an implementation workflow instead.",
"files": []
},
{
"id": 6,
"prompt": "Audit the code that was just merged against the original implementation plan.",
"expected_output": "Does not route to create-plan because the target is completed implementation; it uses code review or plan-compliance review instead.",
"files": []
},
{
"id": 7,
"prompt": "Briefly explain what dependency injection means.",
"expected_output": "Does not route to create-plan because the request is a small conceptual explanation without an implementation handoff.",
"files": []
}
]
}