async-learning-teacher
Transform saved links, papers, articles, posts, videos, and reference collections into approachable AI teaching artifacts for later study. Use when a user…
Create truthful, human-centered marketing campaigns for an app or product, including positioning, channel copy, original artwork, editable layouts, README banners, and selective website integration. Use when asked to make launch materials, promotional artwork, social assets,
$ npx -y skills add tamdogood/builder-essential-skills --skill create-marketing-kit --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/create-marketing-kitContext preview
The summary Claude sees to decide when to auto-load this skill.
Create truthful, human-centered marketing campaigns for an app or product, including positioning, channel copy, original artwork, editable layouts, README banners, and selective website integration. Use when asked to make launch materials, promotional artwork, social assets,
name: create-marketing-kit description: Create truthful, human-centered marketing campaigns for an app or product, including positioning, channel copy, original artwork, editable layouts, README banners, and selective website integration. Use when asked to make launch materials, promotional artwork, social assets, campaign kits, ads, or marketing content from an existing product; to adapt a visual reference without copying it; or to add approved campaign art to product surfaces. Do not invent claims, fake UI, publish, deploy, or replace product proof without explicit evidence and authorization.
Turn verified product truth into a cohesive, reusable campaign kit. Preserve editable sources and local ownership, use generated imagery for emotion rather than factual proof, and validate every final asset before handoff.
Read the smallest authoritative set: product README, current website, configuration or release notes, and actual screenshots. Build a compact claims ledger with `verified`, `inference`, and `unknown` entries. Stop or narrow the campaign when a central claim is unsupported.
Read [references/campaign-strategy.md](references/campaign-strategy.md) before writing positioning or copy.
Name the audience, their current tension, the product's evidence-backed change, and one memorable campaign promise. Derive a message hierarchy:
1. campaign promise; 2. supporting value proposition; 3. two or three proof points; 4. honest qualifier or release boundary; 5. one call to action.
Prefer one strong idea repeated consistently over unrelated slogans.
Select only the surfaces the user needs. Typical exports are:
Create `marketing/<campaign-slug>/campaign-manifest.json` before export. Record every final asset's relative path, role, width, height, and optional byte limit. Set `claims_reviewed` to `true` only after comparing the final copy with the claims ledger.
Read [references/art-direction.md](references/art-direction.md) whenever artwork is requested or a visual reference is supplied.
Save exact prompts and reference notes in `prompts.md`. Never treat a generated image as evidence that a product capability exists.
Place text, logo, dividers, and actual product captures with deterministic tools. Prefer editable SVG for campaign masters and HTML/CSS or native components for website integrations. Derive all aspect ratios from the same thesis and art direction, but recompose each format rather than mechanically cropping it.
Keep readable contrast, safe margins, and mobile legibility. Use real interface captures only when they remain readable and current.
Create concise variants appropriate to each channel. Include a guardrail section listing prohibited claims, required qualifiers, preferred terms, and release-stage language. Avoid generic hype, manufactured urgency, and unsupported superlatives.
When integration is requested:
A repository for skills that are essential to my daily work
Repo: tamdogood/builder-essential-skills
Transform saved links, papers, articles, posts, videos, and reference collections into approachable AI teaching artifacts for later study. Use when a user…
Inspect an unfamiliar repository, turn a focused Markdown behavior scenario into a deterministic test in the repository's native test stack, run it, and…
Apply a disciplined engineering workflow to any code change. Use whenever implementing a feature, fixing a bug, or refactoring — before writing code, not…
Create or update a complete repository skill from a user's idea, including the workflow instructions, references, scripts or assets, agent metadata, skill-card…
Provider-neutral deep-research orchestration for brainstorming, technology choices, comparisons, and state-of-the-art surveys. The Research Lead makes scope…
Use when the user asks to run or continue an autonomous build: turn a goal into an approved plan, dispatch implementation and review agents, and finish with…