AGENT SKILL

leeuwis-persona-demand-gen

Build persona-based LinkedIn demand generation plans and agency briefs for B2B SaaS, separating demand creation from capture and prioritizing ICP fit, SQL quality and pipeline. Use when planning paid media, repairing lead quality or reviewing agency performance.

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
leeuwis-persona-demand-gen
description
Build persona-based LinkedIn demand generation plans and agency briefs for B2B SaaS, separating demand creation from capture and prioritizing ICP fit, SQL quality and pipeline. Use when planning paid media, repairing lead quality or reviewing agency performance.

02 资源文件 7

03 SKILL.md 正文

Persona-based LinkedIn demand generation

Based on Julian Leeuwis's public method. Not affiliated with or endorsed by Julian Leeuwis.

When to use

Use this skill to turn a B2B SaaS paid media request into an actionable campaign plan and agency brief. It is particularly useful when inexpensive leads fail Sales qualification, LinkedIn is compared with search using identical conversion expectations, or agency reviews focus on activity while pipeline stalls. The deliverable connects the buying committee's problems to messages, separates future demand development from existing intent capture, and makes downstream outcomes visible to the people executing campaigns.

Work from the supplied business evidence. Ask for missing information that changes the plan, including the product, market, budget, buying cycle, CRM stages and Sales qualification criteria. Continue drafting with explicit assumptions where possible. Do not invent customer findings, conversion rates or proof. This skill produces a reviewable brief; it does not itself authorize campaign launches, spend changes or messages to an agency.

Read the evidence boundary in references/method.md before applying the method. Four complete posts were fetched with curl. Additional profile excerpts were retrieved through public search indexing because direct profile access was blocked. The persona worksheet, forecasting formulas and review thresholds are package implementation guidance, rather than a verified proprietary Leeuwis framework.

Procedure

  1. Establish the assignment and evidence boundary. Record the decision, planning period, audience, budget and constraints. Consult references/sources.md for provenance and retrieval limitations. Separate published principles, business evidence and your proposed implementation so the reader can assess each claim.

  2. Inspect the inherited system. Follow the baseline guidance in references/method.md. Review available historical spend, conversions, qualification and opportunities before proposing a rebuild. Record missing data and the likely bottleneck. Preserve a comparison period wherever practical.

  3. Align Product, Marketing and Sales. Use references/method.md to define the customer problem, product contribution and consistent sales story. Name the client strategy owner and one person accountable across the funnel. Identify disagreements that would make advertising scale an unresolved problem.

  4. Make the ICP executable. Complete the account criteria in templates/output-template.md. Specify inclusions, exclusions, buying circumstances and evidence from accepted and rejected leads. Translate vague market labels into characteristics the agency can recognize or communicate through problem-specific creative.

  5. Map the buying committee into useful personas. Apply references/method.md. Describe each role's job, problem, trigger, objection and required proof. Prioritize a reachable audience with a distinct message hypothesis. Treat these personas as testable business assumptions, and avoid multiplying campaigns without enough budget to learn.

  6. Agree SQL quality and pipeline accounting. Use references/method.md. Define Sales acceptance, rejection reasons, opportunity entry and pipeline value. Reconcile the target with conversion assumptions and sales capacity. Keep immature cohorts and missing qualification separate from confirmed failures.

  7. Separate creation and capture. Build the two program rows in templates/output-template.md. Give LinkedIn education a future demand job and high-intent capture a conversion job. Assign messages, destinations, measures and evaluation windows by buyer readiness. Explain the budget allocation and uncertainty without claiming a universal split.

  8. Repair the measurement path. Follow references/method.md. Specify campaign identifiers entering the CRM, stage timestamps, deduplication and qualified conversion feedback. Name who verifies the path. If it is unreliable, make repair a launch dependency for decisions requiring that data.

  9. Test the message before extensive production. Use references/method.md. State one hypothesis, audience, variants, budget limit, review date and evidence needed to decide. Include rejection feedback. Use examples/worked-examples.md to see how broad lead requests become concrete briefs.

  10. Write the agency brief and learning loop. Fill templates/output-template.md with targets, ownership, campaign roles, reporting and next decisions. Explain how Sales findings change targeting, messaging or bidding. Distinguish immediate diagnostic signals from later pipeline outcomes.

  11. Review and return the deliverable. Run checklists/review-checklist.md. Repair failures or disclose unresolved dependencies with owners. Return the completed brief, assumptions, measurement gaps and next experiment. Preserve the evidence limitations and label any illustrative numbers.

Files in this skill

04 同仓库更多 Skills

getedgehq
getedgehq/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.

★ 5
getedgehq
getedgehq/skills

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.

★ 5
getedgehq
getedgehq/skills

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.

★ 5
getedgehq
getedgehq/skills

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.

★ 5
getedgehq
getedgehq/skills

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.

★ 5
getedgehq
getedgehq/skills

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.

★ 5