Create a one-page brief for a creator you have already selected, with format-specific hooks, approved claims, disclosure, deliverables, timing, and a proposed rights request. It also drafts short gift and paid outreach messages for a human to send.
Writes a one-page brief for one creator you have already picked: hook ideas in their format, at most three approved must-say lines, never-says, the disclosure for their platform, deliverables, timeline, the usage-rights ask and two examples. Adds a short first-message draft (gift and paid versions) for you to send. Use alone when you already have the creator, their best fitting post and the goal; otherwise run work-with-creators.
Run score Not tested
See how to installReview the instructions the agent will receive before you install.
Reads: the shortlisted creator's verdict and best on-brief post; the plan and goal; product records (facts); every claim-like line cleared through the claims-gate skill (../claims-gate/SKILL.md) (signed-off claims only; with no sign-off it asks the human for the few lines needed) and every dont/must fact; brand voice and kit only for the brand's own lines (never to rewrite the creator); campaign_read dates if a campaign drives it; ../work-with-creators/references/creator-brief.md.
Does:
Fill every section of the brief, in order, on one page — the UGC-for-ads variant when the role is ugc-for-ads (hook variants as deliverables, shot list, CTA, raw footage, one creative revision), the seeding variant for gift-only creators (no required deliverable).
Must-says: at most three, each a signed-off claim quoted exactly (candidates from an unsigned brain never qualify). Lines not cleared by the claims gate are cut and listed with the proof that would restore them. Press-quote claims are cited as the publication's words, never as the creator's own experience. Product facts are neutral (format, size, ingredients, use) — never efficacy wording lifted from product pages.
Never-says: claims that are not signed off, banned words, regulated-category words, competitor names.
Hook angles written for this creator's format and style, from their own content — angles, not lines to read.
Disclosure lines for the creator's platform and market from ../ad-policy-check/disclosure.md (in the ad-policy-check skill) — or the UGC-for-ads variant (brand-account ads; partnership label when run from the creator's handle; honest-use line). Mark a brief "not ready until you approve: <lines>" only when its message depends on lines the human hasn't approved; a brief on neutral facts and honest use is ready.
Rights ask marked "proposed, pending contract"; [LINK], [CODE] and contact as placeholders for the human.
Examples: one of the creator's own fitting posts, one category winner for format (never a brand ad to copy).
Self-check before saving: one page; no script (UGC: hook variants and a shot list, still no read-out script); no claim that is not signed off in the key message, angles, must-says, can-cite, UGC hook variants or CTA; disclosure present; deliverables and dates concrete.
First message per ../work-with-creators/references/first-message.md: gift and/or paid version for this pick, short, a specific first line, one ask, no price, no claims beyond what the gate cleared; appended to the brief as "First message — draft, you send it".
Writes: creators/<date>/briefs/<handle>.md (brief + first-message drafts).
When: in the free draft, for the top 2–5 picks (fewer when the free read was thin — a short brief for a well-read pick beats long briefs for guesses) (claim lines awaiting sign-off marked so); for the rest after the founder approves names.
Rules: one brief per creator. Never invent an offer, a claim, a code or a price. Never send anything — the human sends every message.
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
The supplied material contains only placeholder text for the skill’s purpose, inputs, steps, and completion criteria. It does not provide enough information to describe a task or result reliably.
Research supported advertising angles using buyer context, current product facts, customer language, and observed ads. Turn the evidence into static ad, video, or copy ideas, matching video concepts to available recipes. Scores rank ideas for testing; they do not predict results.
Analyze campaign data from Google, Meta, and LinkedIn to find strong and wasteful spend. The skill checks funnel performance and test results, then recommends which campaigns to pause, scale, or test and how to shift budget across channels.
Compare ad spend and signups with downstream outcomes to calculate the cost of each qualified lead. The skill checks tracking coverage, accounts for how long leads need to mature, and groups creatives into actionable categories with confidence notes.
Prepare the intake for a Meta ad campaign by reviewing available brand information first, stating reasonable assumptions, and asking only questions whose answers could affect budget, claims, or legal exposure. It records stable brand facts, a campaign brief, and what was asked versus assumed.
Review ad copy, image text, visuals, and people against platform and brand category rules. It suggests honest fixes and needed disclosures, then flags issues requiring human or legal review, with a separate result for each ad and platform.