/suede-newsroom

name: suede-newsroom
description: "Suede AI editorial pipeline for agent-run content: six roles with written contracts, one inspectable campaign record, and a distribution stage that gives every asset its own argument instead of a shorter draft. Use when content agents return generic, duplicated, or unsourced work, when one flagship piece has to carry a week of distribution and become the page search engines and AI answers cite, when someone asks to build an AI content team or one-person media company, or when a founder wants a weekly interview-led content system across personal and company accounts. NOT FOR: choosing topics, pillars, or clusters (use suede-content-strategy); platform mix, cadence, calendars, listening, or Instagram programs (use suede-social); running a stage on a schedule with state and stop conditions (use suede-marketing-loops); lane ownership for agents changing code (use suede-agent-teams); writing the flagship piece itself (use suede-ship-copy)."
metadata:
  version: 1.2.0

Suede Newsroom

Six chatbots pointed at the same brand are not a content team. A newsroom is the loop that connects them, and every arrow in it is a handoff with a contract:

idea -> research -> angle -> flagship -> distribution -> review -> performance -> playbooks

Break one arrow and the failure is predictable, not mysterious:

| Broken arrow | What ships instead | |---|---| | research never reaches the strategist | a generic angle any competitor could have written | | the writer never sees the evidence packet | claims that drift one step past what the source says | | distribution starts from the finished draft | five surfaces carrying the same shortened article | | performance never reaches the playbooks | the same mistake repeated at a higher cadence |

This skill owns the pipeline: who decides what, what travels between them, and how one idea becomes several assets that argue different things. Read `.agents/product-marketing.md` first if it exists: it holds product, audience, positioning, and proof, and nothing here restates it.

**Founder-led mode.** When the recurring source is a founder interview, voice note, or operator debrief, or when personal and company accounts need different jobs, read [references/founder-content-loop.md](references/founder-content-loop.md) before Step 1. It adds an intake contract and account lanes to this pipeline; the six role contracts, evidence gates, collision checks, approval boundary, and Keep/Test/Stop thresholds below remain unchanged.

Step 1: Put the campaign in a file, not a conversation

One record per campaign at `.agents/newsroom/<slug>.md`. It is the only thing that has to survive between roles, sessions, and restarts.

A conversation between roles has two failure modes a file does not: context dies on restart, and the next role has to infer which sentences were load-bearing. The record gives each role a predictable input and lets a human audit a campaign without reopening six sessions.

Keep it narrow, decisions and the evidence behind them. Drafts live beside it, not in it. The template and per-stage completion rules are in [references/campaign-record.md](references/campaign-record.md).

Step 2: Give each role one decision to own

The fastest way to ruin a multi-agent content team is to hand every role the same instruction: make great content. Each role gets one decision, one artifact, and a named point where it stops.

| Role | Owns | Returns | Hands to | |---|---|---|---| | Signal scout | whether an idea has a reason to exist now | scored candidates | researcher | | Researcher | what is verified versus inferred | evidence packet | strategist | | Strategist | the single editorial angle | angle brief | writer | | Writer | the deepest version of the idea | flagship piece | distribution | | Distribution | what each surface argues | asset set with entryways | editor | | Editor | whether the package holds together | approve, revise, or reject | human |

Every contract fills five fields: **owns**, **reads**, **returns**, **must not**, **done when**. Full text for all six, with the `must not` and `done when` clauses, is in [references/role-contracts.md](references/role-contracts.md). Copy them in verbatim; a paraphrased `must not` is how a writer starts picking angles.

**Thresholds that make the contracts checkable:**

• Scout returns at most three candidates, each with a decay window, and names a

rejection reason for every candidate it discarded. A run that approves everything it found did not filter anything.

• Researcher returns three to seven verified claims, a URL for every claim with

consequence, and an explicit `what the sources do not prove` list.

• Strategist returns exactly one recommended angle plus at least two named

rejected directions and why each is weaker. A menu pushes the decision back to the human, which is the decision this role exists to make.

• Distribution returns one entryway per asset and no entryway twice.
• Editor reviews the assets together in one pass, never one at a time.

Step 3: Gate every handoff

A stage is complete when every field it owns is filled and readable by the next role: not drafted, not discussed. Written into the record.

**Return-to-sender.** When a field the current stage needs is empty, the role sends the record back and names the field. It does not fill the gap with a plausible assumption. A pipeline whose roles patch each other's gaps produces confident output with no traceable source, which is worse than a stalled campaign because nothing signals the problem.

**Halt format.** Stop. Name the empty field and the stage that owns it in one line. Offer the human these options and wait: (1) supply the field now, (2) send the record back one stage for another attempt, (3) narrow the campaign until the field is unnecessary, or (4) kill it. Do not advance the record, and do not present a partial package as complete.

Two returns on the same field means the pipeline