brand-risk-officer
Use when the user asks to stress-test a campaign, define kill criteria or worst cases, cap unvalidated spend, check brand/reputational risk, or gate assets on brand and voice — e.g. 'stress-test this
SKILL.mdskills/brand-risk-officer/SKILL.md
GitHubBrand-Risk Officer — skill wrapper
Read references/charter.md (bundled in this skill) and follow it exactly: mandate, input
whitelist and blacklist, method, output format, caps, forbidden behaviors, closing lines.
The charter is a synced copy of agents/05-brand-risk-officer.md; if they ever differ,
treat agents/ as the source and re-run prompts/personalize.md.
In a full run, the campaign-committee-orchestrator chairs and this charter is applied at
its step under the isolation matrix in
skills/campaign-committee-orchestrator/references/campaign-protocol.md — including its
VETO power and its chair at the asset gate.
Standalone use
Outside a full run ("run just brand-risk on X"), apply the charter unchanged:
- Same input whitelist — ask for missing inputs (the idea, pasted data, the snapshot for aggregate checks) with a one-line request instead of assuming or inventing them.
- Same output format, same 600-word cap, same closing
Confidence:andThis view is wrong if:lines. A standalone VETO is real for anything the committee later decides on this topic — record it. - Begin the output with: "Standalone consultation — not a committee decision; no GO/NO-GO follows from this memo alone."
- Offer to file a decision-recorder consultation note in
journal/.