CtrlK
BlogDocsLog inGet started
Tessl Logo

markusdowne/handoff-integrity-check

Validate agent handoff packets and resume readiness using schema, freshness, and replay checks. Use when tasks pause/resume across sessions, agents, or humans — including when a user wants to continue where they left off, hand off to another agent, resume a previous task, or pick up an interrupted workflow. Includes explicit untrusted-content/prompt-injection guardrails for third-party inputs.

100

1.31x
Quality

100%

Does it follow best practices?

Impact

100%

1.31x

Average score across 3 eval scenarios

SecuritybySnyk

Advisory

Suggest reviewing before use

Overview
Quality
Evals
Security
Files

task.mdevals/scenario-1/

Resume Readiness Audit for Database Migration Handoff

Problem Description

A backend engineering team has been working on a large database migration project. The lead engineer had to step away mid-task and left a handoff packet for the next engineer (or agent) picking up the work. Before the incoming engineer resumes the migration, they need confidence that the handoff is in good shape and safe to act on.

Your job is to validate the handoff packet they left behind and produce a structured audit report. The team uses a standard handoff integrity process and expects a formal report that another engineer can read to quickly understand whether the work is safe to continue.

Output Specification

Produce a file called handoff-audit.md containing your validation report. The report should cover every check you performed, the result of each check, an overall classification of the handoff's health, any recovery steps needed, and a recommendation about whether it is safe to escalate (resume) the work.

Also include a brief audit-log.txt noting the steps taken during validation (one line per step).

Input Files

The following files are provided as inputs. Extract them before beginning.

=============== FILE: inputs/handoff.json =============== { "objective": "Migrate the orders table from PostgreSQL 12 to PostgreSQL 15, applying the new partitioning scheme", "completed": [ "Audited existing schema for deprecated column types", "Created pg_dump backup of production orders table", "Drafted migration SQL with partitioning DDL", "Tested migration script against staging environment" ], "unresolved": [ "Confirm zero-downtime cutover window with the SRE team", "Verify pglogical extension compatibility on target cluster" ], "assumptions": [ "Maintenance window approved for Friday 22:00–02:00 UTC", "DBA will be on-call during cutover" ], "next_action": "Schedule a 30-minute review meeting with the SRE team to confirm the cutover plan before Friday", "risks": [ "Replication lag may delay cutover if pglogical setup takes longer than estimated", "Rollback requires restoring from pg_dump which adds ~45 min downtime" ], "updated_at": "2026-03-28T18:00:00Z", "resume_token": "handoff-orders-migration-v3-20260328" }

evals

scenario-1

criteria.json

task.md

SKILL.md

tile.json