Designs a coordinated multi-channel campaign or product launch around one story — objective, message, channel sequencing, timeline, assets, and the checklist that gets it out the door. Use this to plan a launch or campaign, sequence a go-to-market push, pressure-test a campaign before committing budget, or turn a product change into a coordinated set of activity. For ongoing channel programs rather than a bounded push, use `marketing-planning`.
The English summary is being prepared. Showing the original description.
See how to installReview the instructions the agent will receive before you install.
A campaign is a bounded push around one story. If it has no end date and no single story, it is a program, not a campaign, and it should be planned as one.
Every campaign carries exactly one idea. Channels change the format; they never change the meaning. Campaigns that say slightly different things on each channel produce no compounding — the audience sees three impressions and remembers none.
Write the story as a sentence before anything else: for whom, what changes, why now. If it takes a paragraph, it is not ready and the campaign will not hold.
The "why now" is the part most campaigns skip and the part that produces urgency. Without it you are asking people to act on something that would be equally true next quarter.
One primary number with a date, and the leading indicator that will move first. Campaigns with several equal objectives cannot be sequenced, because every tradeoff has an argument on both sides.
State what you are not optimizing for. A launch optimizing for signups will make choices that cost brand, and that is fine — as long as it was chosen.
Pick channels by where the audience already is and which formats you can actually produce well. Two channels executed properly beat five done adequately, and the fifth channel usually consumes the attention that would have made the first two work.
Sequence them. Most campaigns run everything at once and learn nothing:
Work backward from the launch date, and place the asset freeze at least several days before anything ships. Campaigns slip because copy is still being edited while ads are being trafficked.
Front-load anything with a dependency you do not control — press, partners, legal review, app-store approval. These are what actually move launch dates.
Plan the two weeks after launch as deliberately as the launch itself. Most campaigns are designed as a spike and produce one.
List every asset by channel with owner and due date. Derive them from the one story rather than writing each independently — independently written assets drift, and the drift is invisible until they are seen side by side.
A campaign amplifies an offer; it cannot rescue a weak one. Before planning channels, check the offer itself: is the value obvious, is the risk to the buyer low, and is there a reason to act now that is not manufactured?
The levers, in rough order of effect: what is included, the risk reversal (guarantee, trial, pilot), the payment structure, and only then the price. Discounting is the weakest of these and the most reached for, and it trains the audience to wait for the next discount.
If the offer only works with urgency attached, the urgency is doing the work and it will not survive contact with a considered buyer.
references/sources.md in this skill lists the outside authorities that settle the questions
here — what each one is authoritative for, and what you may do with it. Check them before
answering on anything they cover, and cite what you used. Most are free to read and not free
to reproduce; the use note on each is binding.
The story in one sentence, objective and leading indicator, channels with sequencing rationale, timeline with the freeze date, asset list with owners, risks with fallbacks, and what is explicitly out of scope.
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.
Designs and audits who can reach what — authentication, authorization models, privileged access, service credentials, and joiner-mover-leaver process. Use this to design a permissions model, run an access review, reduce standing privilege, handle offboarding, set up SSO or MFA, manage service and machine credentials, or diagnose why permissions have sprawled.
The English summary is being prepared. Showing the original description.
Concentrates marketing and sales effort on a named set of accounts rather than on volume — qualifying whether the model fits your economics at all, building the account list and the buying group inside each, tiering effort against account value, coordinating so the account experiences one campaign rather than several, and measuring account progression instead of leads. Use this to decide whether to run an account-based program, build one, or work out why an existing one produces activity and no pipeline.
The English summary is being prepared. Showing the original description.
Gets new users from signup to first real value — signup flow, onboarding, time-to-value, and the early experience that determines whether someone becomes a user or a lapsed account. Use this to design or fix signup and onboarding, diagnose why signups do not convert to active use, reduce time-to-value, or decide what a new user must accomplish first.
The English summary is being prepared. Showing the original description.
Designs orchestrator-and-subagent hierarchies for a repository — splitting agents by exclusive write surface, pairing every producer with an independent auditor, and enforcing the split with a script that runs in CI. Use this whenever the user wants to set up, expand, audit, or fix a multi-agent or subagent structure for a codebase; asks how to divide work between agents; wants agent charters, roles, or a surface map written; or is hitting agents that collide on the same files, review their own work, or drift from their remit. Also use when sizing a roster or deciding whether a new agent is justified.
The English summary is being prepared. Showing the original description.
Governs models and AI systems in production — intended use, evaluation, monitoring, human oversight, documentation, and the decision to deploy or retire. Use this before deploying a model or AI feature, when defining evaluation criteria, when a model's behavior has drifted, when assessing AI risk or regulatory exposure, or when deciding whether an AI system is fit for a consequential decision.
The English summary is being prepared. Showing the original description.
Produces executive-level research — market sizing, competitor mapping, trend analysis, and strategic intelligence — grounded in cited sources with the confidence in each claim made explicit. Use this to analyze a market or industry, map competitors, evaluate a market-entry or build-versus-buy decision, produce a research brief, or assemble evidence for a decision. Also use when comparing options that need a structured, evidence-based verdict rather than an opinion.
The English summary is being prepared. Showing the original description.