prep-workshop-slides

prep-workshop-slides is a command for Claude Code from danielpaulai/Purely-Personal-Run-a-business-by-itself. It costs 60 tokens per session (1,855 once invoked), scanned A, original, MIT.

A workshop slideshow generator that turns attendees' LinkedIn profiles into personalised opening slides. Each slide can show a person's name, writing style, favourite word, AI-generated-content score, and an observation based on their posts.

In plain words
What is it for?
Use it with an attendee CSV or a list of LinkedIn URLs to scrape profiles, analyse posts, and create a slideshow for the start of a workshop.
Why use it?
It helps a facilitator prepare a relevant opening for each attendee instead of presenting the same generic introduction to everyone.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Part of the purely-personal plugin — 4 skills, 9 commands, 1 plugin shipped together

Good fit Use it with an attendee CSV or a list of LinkedIn URLs to scrape profiles, analyse posts, and create a slideshow for the start of a workshop.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/danielpaulai/purely-personal-run-a-business-by-itself/prep-workshop-slides
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo
git clone --depth 1 https://github.com/danielpaulai/Purely-Personal-Run-a-business-by-itself

Made for: Claude Code.

Or install purely-personal, the plugin that ships this one along with the rest of its 4 skills, 9 commands, 1 plugin.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for prep-workshop-slides

README.md
[![agentmods](https://agentmods.dev/badge/commands/danielpaulai/purely-personal-run-a-business-by-itself/prep-workshop-slides/github.svg)](https://agentmods.dev/commands/danielpaulai/purely-personal-run-a-business-by-itself/prep-workshop-slides)
Your own site
<a href="https://agentmods.dev/commands/danielpaulai/purely-personal-run-a-business-by-itself/prep-workshop-slides"><img src="https://agentmods.dev/badge/commands/danielpaulai/purely-personal-run-a-business-by-itself/prep-workshop-slides/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for prep-workshop-slides

Your own site · 80×15
<a href="https://agentmods.dev/commands/danielpaulai/purely-personal-run-a-business-by-itself/prep-workshop-slides"><img src="https://agentmods.dev/badge/commands/danielpaulai/purely-personal-run-a-business-by-itself/prep-workshop-slides.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 60 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,855 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00060 $0.01855
Opus 5 $0.00030 $0.00928
Sonnet 5 $0.00012 $0.00371
Haiku 4.5 $0.00006 $0.00186

Measured 11d ago against content hash 0f455f0dd889, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

prep-workshop-slides scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

commands/prep-workshop-slides.md · 185 lines

How it starts

The opening of the file, as written. The whole thing — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/prep-workshop-slides

You are the Workshop Producer. Your job: turn a list of LinkedIn URLs into a personalized opening slideshow that makes every attendee feel seen in the first 10 seconds of Day 1.

This is the single highest-impact workshop asset. Do not skip it. Do not fabricate data. If a scrape fails, flag it so the facilitator knows before Day 1.


Input

One of:

  1. CSV path: ./workshop/attendees.csv with columns: name, linkedin_url, email
  2. Inline paste: user pastes LinkedIn URLs one per line, ≥2 and ≤50

If no input: ask user to paste URLs.


Step 1 — Scrape + Analyze Each Attendee

For each LinkedIn URL, run in parallel:

  1. apify-linkedin → pull profile headline, headshot URL, last 30 posts
  2. voice-extractor on the posts → tone, hook pattern, banned phrases, example openings

From the raw output, derive these 5 data points per attendee:

Attendee data schema

Field Source Example
name profile → name "Daniel Paul"
initials first letter + last letter of name "DP"
headshot_url profile → photo URL ...
verdict_bold 3 adjectives describing their tone "Direct. Conversational. Allergic to corporate."
verdict_rest 1 complementary sentence "You write like you talk. The AI already knows."
data.posts.value count of posts analyzed 30
data.hook.value their signature hook pattern "PersonalProof"
data.hook.sub their most-used hook opener ""I built X. It cost me zero dollars.""
data.word.value most frequent non-stopword, with count ""system""
data.word.sub "Used N times · non-stopword" "Used 27 times · non-stopword"
data.slop.value AI-slop score 1–10 7
data.slop.sub explanation "Em-dashes in 19 of 30 posts"
data.slop.warn true if score ≥ 6 true
observation.bold the mind-blown stat "34% of your sentences"
observation.text the insight that makes it personal "start with 'And' or 'But.' That's not an accident. That's your voice."

Read the full file on GitHub · 185 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 11d ago First seen · 185 lines · 60 tokens per session scan A 0f455f0dd889

Subscribe to this mod's changes

prep-workshop-slides is a command published in the GitHub repository danielpaulai/Purely-Personal-Run-a-business-by-itself (2 stars, last pushed 28d ago), licensed MIT. It adds 60 tokens to every session and 1,855 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.