Use when validating an intent classifier or ranking independently eligible account and contact records from supplied evidence.

Use when reviewing supplied dated evidence for recent account signals, buying-context changes, or a manual weekly pulse.

Use when deciding whether supplied outbound copy passes relevance, recipient-fit, evidence, eligibility, consent, policy, and operational gates.

Use when reviewing experiment results against a declared hypothesis, primary metric, and decision rule.

Use when investigating a market trend, category narrative, industry shift, or competing interpretation from supplied or authorized research evidence.

Use when summarizing pipeline counts, supplied movements, risks, and review priorities from an offline snapshot or comparison period.

Use when drafting one bounded follow-up after a supplied meeting record is marked no-show.

Use when deciding whether supplied account and conversation evidence makes a sales meeting appropriate.

Use when deriving a reusable messaging voice profile from user-approved writing samples or explicit approved voice guidance.

Use when preparing a reviewable sales handoff brief from supplied account, contact, and interaction records for a next owner.

Use when applying supplied account and contact ICP gates to records or auditing eligibility decisions before scoring or outreach.

Use when mapping supplied roles or stakeholder evidence into buyer, user, champion, and blocker personas for an offer or account.

Work on the `snb-worktime-webui` project in the SNB repository: a Go application with an embedded web UI for calculating employee worktime from Windows session snapshots and workstation or network activity windows. Use when adding features, fixing bugs, adjusting parsing rules, changing calculation logic, refining the web UI, updating Windows build flow, or integrating new telemetry sources for this specific project.

Use when mapping supplied contact identities to buyer personas, verifying current roles and employers, or identifying missing stakeholder coverage.

Use when deriving evidence-backed outreach angles for a supplied contact from verified account context and dated research.

Use when drafting a bounded reply to a supplied prospect objection after contact-specific outreach gates are known.

Use when drafting finite evidence-backed follow-ups while treating clear negative replies and stop requests as terminal.

Run an explicitly requested execution, independent critique, and revision workflow for a task or artifact, with evidence-backed scoring, category floors, a brief security screen, and at most three review rounds. Use only when the user invokes $critic-loop or explicitly requests this bounded critic workflow; do not add it to ordinary reviews.

Use when converting a supplied interaction or reply into a structured CRM-note draft without changing an external record.

Use when preparing review-only scheduling copy after meeting appropriateness and explicit consent are independently established.