hott-ugly-ads
Develop and review audience-relevant, feed-native paid social ad briefs using Barry Hott's public Ugly Ads method when creating concepts, revising creative, or diagnosing ads for scrolling feeds.
- License 许可
- Apache-2.0
- 所属仓库
- getedgehq/skills
- 最近更新
- 2026-11-12
- Stars
- ★ 5
- Forks
- 0
01 前言 Front Matter
- name
- hott-ugly-ads
- description
- Develop and review audience-relevant, feed-native paid social ad briefs using Barry Hott's public Ugly Ads method when creating concepts, revising creative, or diagnosing ads for scrolling feeds.
02 资源文件 7
- 参考文档checklists/review-checklist.md5.2 KB
- 参考文档DERIVATION.json2.7 KB
- 参考文档examples/worked-examples.md6.9 KB
- 许可证LICENSE10.5 KB
- 参考文档references/method.md13.7 KB
- 参考文档references/sources.md3.0 KB
- 参考文档templates/output-template.md6.0 KB
03 SKILL.md 正文
Barry Hott's Ugly Ads
Based on Barry Hott's public method. Not affiliated with or endorsed by Barry Hott.
When to use
Use this skill to develop, revise, brief, or diagnose paid social creative for scrolling feeds, especially Instagram, Facebook, and TikTok. It produces a production-ready creative brief with distinct concepts, opening alternatives, evidence notes, a review, and a proposed learning plan. The central question is whether the intended viewer will recognize something relevant to their own life before scrolling away. [S1][S4][S8]
Use it for premium products too. Choose production style from the audience and placement rather than price alone. For television, YouTube, and other contexts that suit polished production, adapt the style accordingly. A campaign's awareness objective does not change what viewers expect in their feed. [S1][S3]
Read the method before developing concepts. Open the examples for calibration, the template while drafting, and the checklist before delivery. The sources establish attribution; they are not a substitute for current audience research. If research or account data is unavailable, distinguish assumptions from observations and propose how to resolve the gaps. Do not invent customer experiences, feed evidence, or performance results.
Procedure
-
Frame the assignment. Use the brief fields to record the audience, situation, placement, offer, desired action, and practical constraints. Identify whether the task concerns new creative or an existing asset. Record missing facts that could change the concept rather than silently choosing an audience.
-
Adopt the cold viewer's perspective. Read the viewing-moment rules. Assume little brand knowledge and little available attention. Describe a frustration, desire, or recognizable result in one sentence. Explain why someone unfamiliar with the product would care. [S4][S8]
-
Study the actual feed. Follow the research procedure. Collect relevant organic examples and note their audience, context, camera, language, pace, and opening. Keep links and observation dates in the template. Identify whether each reference is observed or merely proposed. [S7]
-
Choose a human premise. Use the concept rules to turn a feature into an experienced problem or change. Separate the premise from its visual vessel. Compare the weak and improved drafts in the illustrations if the concept still depends on product familiarity. [S4]
-
Match the vessel to the audience. Apply the style and authenticity rules. Select a phone recording, founder account, note, demonstration, or other format because the research supports it. Preserve useful product-quality cues and remove decorative marketing signals that slow recognition. [S1][S2][S3]
-
Draft distinct concepts. Fill the concept card for each chosen premise: opening, human situation, product role, benefit, evidence, and action. Make the product's contribution understandable. Include production instructions sufficient for another person to execute the idea without guessing its point. [S1][S4]
-
Create a meaningful alternative. Use the iteration rules to write an alternate opening or angle and name the hypothesis it tests. A different human situation should change what appears or happens, not only replace a headline. Keep the underlying offer consistent where comparison requires it.
-
Verify credibility. Follow the authenticity cautions. Identify real speakers, substantiated claims, and any synthetic material. Separate scripted illustrations from customer evidence. Supply AI with research context before using it for variants. [S2][S7]
-
Review in context. Run the pass/fail checklist at phone size beside relevant feed examples. Ask a cold reviewer what is happening, who it concerns, and what changes. Record failures and revise the premise, delivery, or clarity before investing in extra polish.
-
Plan a fair comparison. Complete the testing fields using the testing guidance. Name the existing benchmark, comparable conditions, budget limits, evidence needs, and acquisition outcomes. Include shares as a diagnostic signal without treating them as proof of profitability. [S5][S6]
-
Deliver and close the learning loop. Return the completed brief, review status, and next decision. Label untested predictions as hypotheses. If results exist, explain what they support and which meaningful change should come next. A proposed test does not itself authorize spending or publishing.
Files in this skill
- references/method.md: Full principles, decision rules, research, testing, edge cases, and explicit cautions.
- references/sources.md: Eight fetched public sources with citation identifiers and contribution notes.
- examples/worked-examples.md: Two invented illustrations showing weak drafts, improved concepts, and the rules behind the changes.
- templates/output-template.md: Fill-in creative brief, concept cards, review record, and proposed test plan with field guidance.
- checklists/review-checklist.md: Pass/fail review, evidence status, common failure modes, and concrete fixes.
04 同仓库更多 Skills
zero-downtime-cloud-move
Runbook for moving a live app from one cloud to another (Google Cloud to AWS, AWS to Google Cloud, a PaaS to your own account, or one storage provider to another) without downtime. The agent inventories what is really running, builds the new stack next to the old one, keeps a one-line rollback for every phase, proves the new stack with real workloads before any traffic moves, cuts over with a checklist, watches a fixed window after the switch, copies data with an idempotent job whose second pass must report 0 left, and deletes the old cloud last. Use when someone asks to migrate, move or replatform a production app, switch cloud providers, move a backend, database files or object storage, plan a DNS cutover, or decommission an old cloud account.
zayats-ceo-branding
Build an evidence-based CEO positioning paper, Personal Branding Roadmap, and editorial workflow using Marina Zayats's public method. Use for executive branding, LinkedIn ghostwriting briefs, profile strategy, and recurring CEO-approved content planning.
yc-app-roast
YC App Roast: roast a YC or a16z Speedrun application. Use when a founder wants their YC or Speedrun answers scored, asks "what would a YC partner think", wants the weak answers found or rewritten, or wants their draft checked before they submit. Scores every answer 0-10 against public advice from YC and Speedrun partners, names the top issue with the exact words that cost points, and writes a rewrite from the founder's own facts. Works for YC and a16z Speedrun. Not affiliated with Y Combinator or a16z.
yc-app-review
YC App Review: get a YC or a16z Speedrun application reviewed by people you trust. Use when a founder wants friends, mentors or alumni to review their YC or Speedrun application, or asks to share their draft for feedback. Builds a shareable review page (one HTML file, application-portal look) where reviewers leave notes per question and press "Send my notes" to send them back as text, then parses the notes into proposed rewrites. Optional tracked private links per reviewer. Works for YC and a16z Speedrun. Not affiliated with Y Combinator or a16z.
x-growth-playbook
X Growth Playbook. Analyse a person's own X (Twitter) posts and tell them what to post next, with the numbers behind every claim. Compares quote posts vs originals, links vs no links, short vs long, time of day in their timezone, media vs text and the topics they name, reports medians with n, then writes a 10-step plan and the next 7 posts in their voice. Use when the user says "analyse my X posts", "what works on my Twitter", "how do I grow on X", "what should I post next on X", "audit my X account", or shares an X data archive, X API export or a list of their posts. Runs on the user's computer.
workplan
Create, update, or close work plans for multi-step tasks. Use when starting refactors, bug lists, feature work, migrations, or any task with 2+ steps. Also use after auto-compaction to re-orient. Triggers: "workplan", "work plan", "create a plan", "what's the plan", "where was I", or when Claude detects a multi-step task that needs tracking.