persona-generation-public

persona-generation-public is a skill for Claude Code, Codex from syangchester-lab/build-your-persona. It costs 146 tokens per session (990 once invoked), scanned A, original, MIT.

A generator for creating a model of a public figure's stated views, arguments, and speaking patterns from public material such as papers, interviews, talks, social posts, and transcripts. It produces an installable SKILL.md file for use as a discussion partner or panelist.

In plain words
What is it for?
Use it to build a reusable debate partner, test a position against a public figure's likely arguments, or add that perspective to a discussion panel.
Why use it?
It helps represent what a person has publicly argued without claiming to reproduce their private thoughts.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to build a reusable debate partner, test a position against a public figure's likely arguments, or add that perspective to a discussion panel.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/syangchester-lab/build-your-persona/persona-generation-public
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.

Any agent
npx skills add syangchester-lab/build-your-persona --skill persona-generation-public
Clone the repo
git clone --depth 1 https://github.com/syangchester-lab/build-your-persona

Made for: Claude Code, Codex.

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 persona-generation-public

README.md
[![agentmods](https://agentmods.dev/badge/skills/syangchester-lab/build-your-persona/persona-generation-public/github.svg)](https://agentmods.dev/skills/syangchester-lab/build-your-persona/persona-generation-public)
Your own site
<a href="https://agentmods.dev/skills/syangchester-lab/build-your-persona/persona-generation-public"><img src="https://agentmods.dev/badge/skills/syangchester-lab/build-your-persona/persona-generation-public/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 persona-generation-public

Your own site · 80×15
<a href="https://agentmods.dev/skills/syangchester-lab/build-your-persona/persona-generation-public"><img src="https://agentmods.dev/badge/skills/syangchester-lab/build-your-persona/persona-generation-public.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 146 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 990 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 $0.00146 $0.00990
Opus 5.5 $0.00058 $0.00396
Sonnet 5.5 $0.00029 $0.00198
Haiku 4.5 $0.00015 $0.00099

Measured 2mo ago against content hash e652a58f4ee8, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

persona-generation-public 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 2mo 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.

generate/persona-generation-public/SKILL.md · 122 lines

How it starts

The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Persona Generator — Public Stance Model

You've loaded the public stance generator. I'll help you build an AI that argues the way a specific public figure would — based entirely on what they've said publicly.

The result: a SKILL.md file you can load as a sparring partner or Symposium panelist.


Before we start: the honest disclaimer

A stance model ≠ a cognitive twin.

We only have access to what someone chose to say publicly. We can model their argumentative patterns, their rhetorical moves, their known positions. We cannot model their private reasoning.

This matters for how you use the output: it can tell you "this person would likely push back by [X move]" — not "this is exactly how they think."


Step 1: Tell me who and why

Answer these:

Who are you building a stance model of? (name + why this person is relevant to your work)

What do you need from them? Stress-testing a specific position? A sparring partner for a domain they know well? A panelist in a multi-perspective session?

What's your time horizon? Quick-and-dirty for a one-off session, or a reusable skill you'll deploy repeatedly?


Step 2: Share your source pack

I'll build from whatever you provide. Quality beats quantity.

Best sources (shows how they argue, not just what they think):

  • Long-form interviews where they face pushback
  • Academic papers or detailed written work
  • Keynote talks with Q&A
  • Social media threads where they're making an argument (not just reacting)

Thin sources (use sparingly):

  • News quotes (context stripped)
  • Secondhand summaries
  • Headlines

Aim for: at least 5 substantial artifacts, at least 3 years of coverage. Paste them, link them, or describe them and I'll tell you what I can work with.


Step 3: Archetype check

The methodology works best for Scholar-Commentators — people who write extensively, argue publicly, and have a long enough track record to show how their positions have evolved.

Archetype Confidence What to watch for
Scholar-Commentator High Optimized track
Executive Medium Private strategy rarely surfaces publicly
Political figure Medium-Low Performance vs. actual stance hard to separate
Creative / Performer Low Work ≠ argument patterns

Read the full file on GitHub · 122 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. 2mo ago First seen · 122 lines · 146 tokens per session scan A e652a58f4ee8

Subscribe to this mod's changes

persona-generation-public is a skill published in the GitHub repository syangchester-lab/build-your-persona (2 stars, last pushed 5mo ago), licensed MIT. It adds 146 tokens to every session and 990 once invoked, about $0.0006 per session on Opus 5.5. 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.

Related

persona-generation-public compared with skills from other repositories

persona-generation-public next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
persona-generation-publicsyangchester-lab/build-your-personaSkill25mo agoMITA146Claude Code, Codex
imagegenopenai/codexSkill134ktodayApache-2.0A113Codex
local-ai-agentsmicrosoft/ai-agents-for-beginnersSkill79ktodayMITA200Claude Code, Codex
playwright-climicrosoft/playwrightSkill99ktodayApache-2.0A19Claude Code
systematic-debuggingobra/superpowersSkill314k3d agoMITA21Claude Code
next-cache-components-adoptionvercel/next.jsSkill143ktodayMITA95Claude Code
chat-pet-sprite-creationmicrosoft/vscodeSkill195ktodayMITA53Claude Code, Codex