v0.8.2 to v0.9.1

+ version: 0.9.1

+ **The idea is the job, and it must be this brand's idea.** An ad idea is a real product fact or customer situation turned into one visible event the viewer gets at a glance (`references/ideas.md`), said the way this brand already talks and looks (`references/brand-profile.md`), built on a template at the creativity level the marketer chose (`references/levels.md`). Everything else serves that idea or protects the brand.

+ The proof that the work happened is the **concept board**, shown to the marketer before any render credits are spent. It cannot be skipped, shortened to "your choice", or replaced by a summary.

+ - **Setup.** Run the `marketing-guide` skill (`../marketing-guide/SKILL.md`) §1–2 only: connect, `gooseworks:get_started`, pick the brand, the workspace scope, and the current names of the brand-brain tools. If `get_started` shows a brand-setup or sign-in card, wait for its press; any other card: the Server hints bullet below.

+ - **Render tool.** No `ads_render` → stop before spending and say so; `ads_generate` rewrites your prompt through templates and is not a substitute.

+ - **Server hints.** Answers like "one short line and wait" or "recommend one plan" govern GooseWorks' own cards, setup, rights and spending. They never replace this playbook's research, board or critic.

+ - **Product identity.** A physical product needs real product photos (`brand_read` with `product_ids`). Software or a service: real UI screenshots and any brand character it owns (never a generated fake UI). The logo is never the identity image; it is placed after the render on every ad (no shell: the marketer's Step 2 choice). Missing photos or screenshots → ask in Step 2. Still none: a physical product stops at the board (no quotes) with an offer of the product-photos job; software goes ahead only with ideas that need no screen (type-led, the mascot).

+ - **Run memory.** The `run-memory` skill (`../run-memory/SKILL.md`), Start of run (§1–5) only: playbook `make-static-ads`, job `static ads`, subject the product's slug, cadence `ad hoc`, outcomes from the `picked` tags and `gooseworks:meta_read` `view: "performance"` matched to this playbook's creative ids. Its "since last time" note goes into the Step 2 message as one line (this replaces run-memory §4's 3–5 lines). Add every ad already made in this conversation to the history.

+ - **Files.** Work in `ads/batches/<YYYY-MM-DD>-<slug>/` in the brand's workspace: `profile.md`, `board.md`, prompts. The batch file `ads/batches/<YYYY-MM-DD>-<slug>.md` is started at Step 3 and filled in as you go (`references/reading-the-brain.md` §7).

+ - the claims contract: the `claims-gate` skill (`../claims-gate/SKILL.md`) §1. Never read claim statuses from the brain yourself;

+ - the product: the one the marketer named; none named → the one the latest performance report or request names, else the bestseller (confirm it in Step 2). Its record and photos, looked at;

+ - **how the brand already advertises:** its own ads (looked at, not listed), recent social posts, website and kit → `profile.md` (`references/brand-profile.md`);

+ - customer words (`references/reading-the-brain.md` §2), the angle bank (§3), and any performance report or open request (§4);

+ - history for the no-repeat test: the last 10 approved ads made in GooseWorks for this brand (`references/engine-notes.md`; fewer with no shell) and every live static (`references/brand-profile.md` §1).

+ Write what you actually read, with counts, at the top of the profile: "Read 14 reviews, 20 of ~300 live Meta ads, 15 X posts, the homepage." Name a skimmed source as skimmed and an unopened one as not checked.

+ **Done:** `profile.md` has every section of its template; the Read line names own ads, social posts, website and kit, each with a count or "not checked: <why>"; five product truths and up to five customer lines with sources (fewer, or "none found", when the sources hold fewer; never a made-up quote).

+ One message, in plain words, numbered as below, with each recommendation in **bold** so the marketer can accept it with one word. Open with the run-memory line, if any; end with "Reply 'go' to take every recommendation (claim lines need your own yes)."

+ 1. **How creative?** Close ("a proven ad layout with your words; safest"), balanced ("a new idea inside a proven layout") or bold ("the idea comes first, in your own style; most surprising"). Recommended: **balanced**. If the reply answers the rest but not this, ask this one again in one line before going on.

+ 2. **Angles:** the profile's angles first, then at most one new angle per five ads (one in any set of five or fewer), marked "new"; one recommended per ad; room to write their own. As a small table: angle · yours or new · the claim line it needs · recommended for ad #. Recommend only angles whose lines are already usable. This is the one home of the new-angle rule.

+ 3. **Claim lines that need approval:** put them in this message the way the `claims-gate` skill §4 says, at most five, including who approves, ending "Reply e.g. 'Yes, approve 1 and 3'." "Your choice" never approves a claim.

+ 4. **Logo:** on every ad (recommended) or none, and which file. Under about 300 px wide: ask for a bigger one, a transparent PNG if possible; use the small one if none comes. No logo file on record → ask for one. On a host that can't run scripts: offer a clear corner they fill themselves (recommended) or a model-drawn logo that may change.

+ 5. **Product, how many ads (recommend 5), placements and ratios** (Meta or Instagram: 4:5 feed recommended; 9:16 for Stories and Reels and 1:1 only if they say), destination link, any live offer and, if an ad will show it, the price. Missing product photos or UI screenshots: ask for them here.

+ 6. **Paid reads**, only if there's no browser and nothing imported: the one "up to N credits" ask from the `spend-gate` skill (`../spend-gate/SKILL.md`) branch B.

+ 7. **Every conflict** the profile found, with your recommendation.

+ "Your choice" or "just give me the images" takes every recommendation (balanced, no new claims); say what you chose on the board. No other questions until the board.

+ **Done:** one message sent; the answers, or "recommended", recorded in `board.md`.

+ Run the `make-static-ads-concept-grid` skill (`../make-static-ads-concept-grid/SKILL.md`): angle → message → visual idea → style → template, the tests, and a fresh critic.

+ **Done:** `board.md` has one row per ad that passed the tests, with the critic's notes and what changed; the batch file is started.

+ Run the `make-static-ads-ad-copy` skill (`../make-static-ads-ad-copy/SKILL.md`).

+ **Done:** every slot of every ad has its final words; each ad has primary texts A and B, link headline, description, CTA and destination.

+ Run the `make-static-ads-compose` skill (`../make-static-ads-compose/SKILL.md`): one prompt per ad and ratio (`references/prompts.md`).

+ **Done:** each prompt passed the read-back in `prompts.md` §5, with its image list.

+ Pass A of the `make-static-ads-claims-extract` skill (`../make-static-ads-claims-extract/SKILL.md`) and the `ad-policy-check` skill (`../ad-policy-check/SKILL.md`) on each prompt and its copy. A cut line goes back to Step 4 or 5 and through this check again. A cut that needs a new approval goes on the board as a cut, never into the ad.

+ **Done:** every span is keep, quote or cut; no cut words remain; policy passed or its flags are on the board.

+ `gooseworks:ads_render` with `dry_run: true` for every ad and ratio. Show the board as `references/handoff-format.md` §2 says, each quote exactly as given (never your own total). The marketer's yes covers the quotes shown plus one retry per ad and ratio, each at that ratio's quoted price; the `spend-gate` skill applies to anything beyond that.

+ Changes at this gate, then show only the changed ads with their new quotes for a yes:

+ - a template swap → Steps 4–6 for that ad (its words follow the new slots), and the set's style and no-repeat tests again;

+ - a changed angle, message or idea → Steps 3–6 for that row, critic included; a level change (it applies to the whole set) → Steps 3–6;

+ - an edited line → Steps 5–6; a newly approved claim → `claims-gate` §4–5 first, then Steps 4–6;

+ - an added ratio → Steps 5–6 for that ratio; a dropped ad needs no new quote.

+ Submit nothing that wasn't quoted and approved as shown. "Finals only" shortens delivery, not this message.

+ Submit the exact quoted requests and wait for them (`references/engine-notes.md`, Polling). Then run the `make-static-ads-render-review` skill (`../make-static-ads-render-review/SKILL.md`).

+ Hand over as `references/handoff-format.md` §3 says; finish the batch file and the tags. Ask which ads the marketer prefers; offer copy variants for those. Save lasting human feedback through the `save-learning` skill (`../save-learning/SKILL.md`). Run `run-memory` End of run (§6–7) on every exit, including a stop or partial run.

+ **Done:** the marketer has one image per ad with its copy; the batch file, tags and run record are saved, or a failed save is reported.

+

+ | More ads | Same steps; earlier ads are history for the no-repeat test. In the same conversation, reuse the level, logo, placements and claim approvals already given (never a spend yes: every new ad gets its own quote); ask only what is new. |

+ | Rotation request (a `Rotation needed:` line, `references/reading-the-brain.md` §4) | Keep the winner's angle, make new executions through the full steps, and answer `Rotation ready:` under the request line. |

+ | Same image, different text or font | The `make-static-ads-copy-variants` skill (`../make-static-ads-copy-variants/SKILL.md`). |

+ | Header or social graphic | The `make-static-ads-graphic-request` skill (`../make-static-ads-graphic-request/SKILL.md`). |

+ Claims through `claims-gate` before public copy; the marketer's yes to the exact quotes before paid work; human words only for preferences, ratings and launch.

+ The board, the batch file, tagged creatives (the logo version of each, or the kept render on a host without scripts) and the run record. Agent verdicts go in tags and the batch file; render feedback carries only the marketer's own words.

+ Every delivered ad comes from a board row with a reason to exist, passed its claims and policy check, was rendered within the approved quotes, and was judged against its protected choice and the product's identity. Failures and anything not checked are said plainly.