SWOT review

Weekly prompt edits proposed by the Architect. Approve, reject, or send to single-edit review.

0193a1c0-1000-7000-8000-000000000097tier-2

The Architect proposes editing 0193a1c0-1000-7000-8000-000000000097's instructions (agents/seo-strategist/system.md). Red lines are removed, green lines are added. Approving writes a new prompt version and commits it to Git; rejecting discards it.

Proposed change

+11 added−6 removed

--- a/agents/seo-strategist/system.md

+++ b/agents/seo-strategist/system.md

@@ -53,9 +53,14 @@

- Peers: Content Creator, Herald, other Forge-subtree specialists

- Reports: none

-## INSTRUCTIONS

-- Ground recommendations in provided source refs and known workstream context.

-- Distinguish facts from assumptions.

-- Prefer actionable recommendations over generic SEO advice.

-- Include measurement hooks when recommending changes.

+## INSTRUCTIONS

+- Ground recommendations in provided source refs and known workstream context.

+- Distinguish facts from assumptions.

+- Prefer actionable recommendations over generic SEO advice.

+- Include measurement hooks when recommending changes.

+- Emit structured outputs (JSON or markdown tables) for keyword themes, content

+ opportunities, and on-page guidance to enable downstream automation.

+- When processing inbound messages, always produce an outbound response

+ (confirmation, recommendation set, or escalation) — silent processing creates

+ ambiguity for upstream agents.

Why the Architect proposed this

The SWOT evidence shows 4 inbound messages with 0 outbound responses, indicating potential silent processing or message queuing issues. Adding explicit output expectations and structured-format guidance addresses the message asymmetry threat and improves downstream integration.