dreyer-funnel-diagnosis
Diagnose funnel bottlenecks through performance evidence and target-group psychology, then develop creative strategy and ad scripts, landing pages, or VSLs. Use for funnel audits, weak conversion, unclear value, or research-led copy revisions.
- 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
- dreyer-funnel-diagnosis
- description
- Diagnose funnel bottlenecks through performance evidence and target-group psychology, then develop creative strategy and ad scripts, landing pages, or VSLs. Use for funnel audits, weak conversion, unclear value, or research-led copy revisions.
02 资源文件 7
- 参考文档checklists/review-checklist.md5.3 KB
- 参考文档DERIVATION.json2.6 KB
- 参考文档examples/worked-examples.md7.9 KB
- 许可证LICENSE10.5 KB
- 参考文档references/method.md13.1 KB
- 参考文档references/sources.md3.7 KB
- 参考文档templates/output-template.md7.0 KB
03 SKILL.md 正文
Dreyer Funnel Diagnosis
Based on Erik Dreyer's public method. Not affiliated with or endorsed by Erik Dreyer.
When to use
Use this skill when a business needs to understand why a funnel underperforms before commissioning new copy, or when developing a coherent creative strategy across an ad, landing page, and video sales letter (VSL). It also supports a focused revision when audience language, motivation, or perceived value appears to obstruct the next action. The deliverable combines an evidence-based diagnosis, a psychological audience brief, a creative hypothesis, usable copy, and a measurement plan.
The public foundation concerns relevance, audience understanding, language, value, and differentiation. The funnel measurement procedures are this package's operational extensions. Read the attribution boundary in references/method.md before claiming anything is Dreyer's documented process. The supplied 600+ experience figure is unverified here; never turn it into a validated dataset, performance guarantee, or credential for the agent. German terms are descriptive vocabulary, not invented proprietary method names.
Procedure
-
Frame the assignment. Read templates/output-template.md, fields 1 and 2. Record the offer, buyer, channel, requested assets, business objective, and practical constraints. Translate a vague request such as better conversion into a defined action and denominator. Identify whether the task is an audit, a new funnel, or a limited copy revision.
-
Establish evidence boundaries. Read references/sources.md and the provenance section in references/method.md. Separate Dreyer's public principles, client facts, and your own hypotheses. Do not fill research gaps with fictional customer insights or claim access to private scripts.
-
Map the customer path. Use the funnel map in references/method.md. Identify the promise, decision, and observable transition at each stage, including follow-up or sales where relevant. Capture existing copy alongside performance evidence so diagnosis considers the entire path.
-
Check the measurements. Follow the evidence rules in references/method.md. Record counts, date range, source, segment, attribution window, and tracking limitations. Check whether audiences and periods are comparable. Missing or unreliable measurements produce a provisional diagnosis and a concrete collection request.
-
Build the psychological brief. Use the audience fields in templates/output-template.md. Gather purchase triggers, desired progress, feared consequences, prior attempts, objections, and language from customer evidence. Preserve differences between segments rather than blending incompatible motivations into one persona.
-
Locate the probable bottleneck. Apply the decision table in references/method.md. Connect an observed loss to a plausible buyer hesitation, then consider competing explanations such as poor traffic, technical friction, offer mismatch, or sales handling. State confidence and the observation that could disprove your diagnosis.
-
Choose a creative strategy. Follow the angle rules in references/method.md. Select one audience, one relevant motivation, one supported outcome, and one reason to believe. Specify the belief that must change before the next action. Meaningful differentiation must survive comparison with actual alternatives.
-
Design the message sequence. Use the asset guidance in references/method.md. Carry the same promise from ad to page to VSL, while giving each asset a distinct job. Place the necessary explanation, evidence, objection response, and next action where the diagnosed hesitation occurs.
-
Draft and revise. Consult examples/worked-examples.md for two invented illustrations. Write concrete, audience-appropriate copy, then compare it with the weak draft. Explain which diagnosed problem each change addresses. Use placeholders for unavailable proof rather than fabricating numbers or testimonials.
-
Make the hypothesis testable. Complete the test fields in templates/output-template.md. Define the control, meaningful change, primary business measure, quality guardrail, allocation, owner, and decision conditions before results arrive. Do not treat improved clicks alone as evidence of improved economics.
-
Review the complete deliverable. Run checklists/review-checklist.md. Resolve failed checks or visibly label the remaining uncertainty. Confirm that every factual promise has support and that the proposed intervention fits the user's actual scope.
-
Deliver the next decision. Finish templates/output-template.md with the diagnosis, selected strategy, requested assets, and test or research action. Distinguish proposed copy from measured results. If evidence is inconclusive, recommend the next observation that would change the decision.
Files in this skill
- SLUG.txt: Package identifier in kebab-case.
- SKILL.md: Activation guidance and the twelve-step workflow.
- references/method.md: Public principles, attribution boundaries, and operational decision rules.
- references/sources.md: Six curl-fetched public sources and research limitations.
- examples/worked-examples.md: Invented examples with weak drafts, revisions, and rule explanations.
- templates/output-template.md: Deliverable fields with completion guidance.
- checklists/review-checklist.md: Pass/fail criteria and remedies for common failures.
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.