work-iq-signalboard

Work IQ Signalboard

Turn trustworthy 28-day Work IQ counts into a polished dashboard. Finish the run even when an optional source is unavailable; never fill a gap with an estimate.

Workflow

1. Confirm that Work IQ read access and Python execution are available. If Work IQ is missing, state what must be connected and stop. Never fabricate data.

2. Read both references before querying:

   • references/harness-playbook.md defines the exact query order, known harness failures, timestamp partitioning, throttling recovery, minimal selections, and file-path rules.
   • references/safe-schema.md defines the only accepted JSON contract and reconciliation checks.

3. Query Calendar, Mail, and Teams chats in that order over a rolling 28-day window. Follow the playbook exactly. In particular:

   • never request subjects, bodies, attendees, names, addresses, locations, filenames, or URLs;
   • never trust a page length that equals the harness's 10/50/100-item cap;
   • never use a rejected $skip or $skiptoken as the only paging strategy;
   • keep batches at eight calls or fewer and retry every throttled call;
   • default Teams to chats only and label that scope honestly.

4. Build the closed JSON object from complete counts only. Preserve measured zeros, but use source coverage—not zero—to represent missing data. Require each four-week series to reconcile with its 28-day total. Do not add work modes, collaboration shapes, focus classifications, fragmentation estimates, after-hours assumptions, or synthetic scores.

5. Write the aggregate object to a temporary safe-signalboard.json. Resolve the installed skill directory from the absolute resource path supplied by the skill loader; do not search the filesystem or assume the current working directory. Replace the example skill path below with that resolved path, initialize both variables, and verify them before rendering. Never run the later commands with an empty variable or the literal example path.