Use when work needs to be handed off to another agent or another human. Produce a continuation-ready brief with the objective, completed work, assumptions, unresolved issues, and next action instead of a generic summary. Good triggers include "prepare a handoff", "make this resumable", and "summarize this for another agent".
92
100%
Does it follow best practices?
Impact
89%
1.41xAverage score across 8 eval scenarios
Passed
No known issues
{
"context": "The agent must produce a handoff for an in-progress API integration. This scenario tests whether the agent prefers surfacing unresolved questions over narrating what was built, and whether it includes specific warnings rather than general commentary.",
"type": "weighted_checklist",
"checklist": [
{
"name": "Unresolved section has open questions",
"description": "The Unresolved section contains genuine decision questions (e.g. retry count, sync vs async webhook handling) — not just a to-do list of files to create.",
"max_score": 12
},
{
"name": "Unresolved prioritised over recap",
"description": "The Unresolved section is as long or longer than the Completed section, reflecting the preference for open questions over narrative recap.",
"max_score": 10
},
{
"name": "Idempotency key warning present",
"description": "The document explicitly warns that omitting the idempotency key causes duplicate messages on retry.",
"max_score": 12
},
{
"name": "Warning is distinct",
"description": "The idempotency key warning appears in a way that stands out (e.g. in a warnings note, in Assumptions with an explicit caution, or in Critical References) — not buried in a list of completed items.",
"max_score": 8
},
{
"name": "No credential hardcoding warning",
"description": "The document notes that credentials must come from environment variables and must not be hardcoded.",
"max_score": 8
},
{
"name": "Completed section is terse",
"description": "The Completed section uses bullet points of 15 words or fewer per item — no multi-sentence explanations of how the code works.",
"max_score": 8
},
{
"name": "Next Action section present",
"description": "The document has a Next Action section.",
"max_score": 6
},
{
"name": "Next action addresses decision blocker",
"description": "The Next Action identifies resolving the open decision (retry count or webhook strategy) OR starting the next concrete coding task — not just 'continue the integration'.",
"max_score": 8
},
{
"name": "All six sections present",
"description": "The document includes all six prescribed sections: Objective, Completed, Assumptions, Unresolved, Next Action, Critical References.",
"max_score": 8
},
{
"name": "Critical References minimal",
"description": "The Critical References section lists only the most essential references (e.g. key files or environment variable names) — not every file mentioned in the context.",
"max_score": 10
},
{
"name": "Objective section present",
"description": "The document has an Objective section stating the overall goal of the integration.",
"max_score": 10
}
]
}evals
scenario-1
scenario-2
scenario-3
scenario-4
scenario-5
scenario-6
scenario-7
scenario-8
skills
compact-handoff