voice-builder

voice-builder is a skill for Claude Code from charlie947/social-media-skills. It costs 184 tokens per session (2,670 once invoked), scanned A, original, MIT.

A writing assistant that builds a personal style guide from an interview and three to five examples of your writing. It can cover formats such as LinkedIn posts, emails, essays, and newsletters.

In plain words
What is it for?
Use it at the start of a Cowork project when you want content written in your voice. It supports work on social posts, blog articles, emails, essays, and other published writing.
Why use it?
It helps an agent write in your usual voice instead of producing generic-sounding text. The interview and examples give it information about your style and preferences.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: names the AskUserQuestion tool.

Part of the social-media-skills plugin — 17 skills shipped together

Good fit Use it at the start of a Cowork project when you want content written in your voice. It supports work on social posts, blog articles, emails, essays, and other published writing.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/charlie947/social-media-skills/voice-builder
About the project

charlie947/social-media-skills is a collection of markdown instructions that gives AI agents specialized workflows for creating and managing social-media content. It supports a content system spanning LinkedIn, Instagram, Substack, X, and YouTube, with shared voice and context files guiding the individual skills.

charlie947/social-media-skills · 3,385 stars · on GitHub

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 charlie947/social-media-skills --skill voice-builder
Clone the repo
git clone --depth 1 https://github.com/charlie947/social-media-skills

Made for: Claude Code.

Or install social-media-skills, the plugin that ships this one along with the rest of its 17 skills.

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 voice-builder

README.md
[![agentmods](https://agentmods.dev/badge/skills/charlie947/social-media-skills/voice-builder/github.svg)](https://agentmods.dev/skills/charlie947/social-media-skills/voice-builder)
Your own site
<a href="https://agentmods.dev/skills/charlie947/social-media-skills/voice-builder"><img src="https://agentmods.dev/badge/skills/charlie947/social-media-skills/voice-builder/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 voice-builder

Your own site · 80×15
<a href="https://agentmods.dev/skills/charlie947/social-media-skills/voice-builder"><img src="https://agentmods.dev/badge/skills/charlie947/social-media-skills/voice-builder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 184 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,670 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. Third-party audits
  • Socket pass 28 Apr 2026
  • Snyk fail 28 Apr 2026
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Memory Poisoning · line 134
    Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.
    Fix: Protect agent memory and state from modification by untrusted content. Use read-only memory for critical instructions and validate all state changes.
How audits are shown
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 $0.00184 $0.02670
Opus 5 $0.00092 $0.01335
Sonnet 5 $0.00037 $0.00534
Haiku 4.5 $0.00018 $0.00267

Measured 13d ago against content hash 7f47bd4b5c13, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

voice-builder 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 13d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

skills/voice-builder/SKILL.md · 259 lines

How it starts

The opening of the file, as written. The whole thing — 259 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Voice Builder

CRITICAL: Auto-start on load

The moment this skill is loaded, installed, uploaded, or triggered, you MUST immediately run Step 1 below. This means your very next message to the user is the interview questions. Nothing else.

Do NOT:

  • Summarise this skill
  • Describe what files it creates
  • Explain how it works
  • Say "here's what this skill contains"
  • Ask if the user wants to run it
  • Confirm installation
  • Offer options like "want me to run this now?"

Do THIS:

  • Go straight to Step 1
  • Send the interview questions as your first and only response

This applies whether the user uploaded a .skill file, said "build my voice", pasted samples, or triggered the skill in any other way. No preamble. No summary. Interview first.

Step 1. Run the About Me interview

You MUST call the AskUserQuestion tool to ask these questions. Do not type the questions as chat text. Use the tool. The tool renders as an interactive form the user fills in, which is a better experience than typing answers into chat.

AskUserQuestion supports a maximum of 4 questions per call, so send two calls: Batch 1 first, wait for answers, then Batch 2.

Batch 1 (your very first action, no text before it)

Call AskUserQuestion with this exact JSON structure for the questions parameter:

[
  {
    "question": "What is your name and what do you do?",
    "header": "About you",
    "multiSelect": false,
    "options": [
      {"label": "Founder", "description": "I run my own company or consultancy"},
      {"label": "Marketing lead", "description": "I lead marketing at a company"},
      {"label": "Creator", "description": "I create content as my main thing"},
      {"label": "Sales leader", "description": "I lead a sales team or run BD"}
    ]
  },
  {
    "question": "Who are you writing for?",
    "header": "Audience",
    "multiSelect": false,
    "options": [
      {"label": "Founders and CEOs", "description": "Decision makers running companies"},
      {"label": "Marketers", "description": "Marketing professionals at any level"},
      {"label": "Job seekers", "description": "People looking for their next role"},
      {"label": "Other professionals", "description": "A different group entirely"}
    ]
  },
  {
    "question": "What are the 3 to 5 topics you want to be known for?",
    "header": "Topics",
    "multiSelect": true,
    "options": [
      {"label": "AI and automation", "description": "How AI tools change work"},
      {"label": "Marketing", "description": "Strategy, content, growth"},
      {"label": "Leadership", "description": "Management, hiring, culture"},
      {"label": "Personal brand", "description": "Building an audience and reputation"}
    ]
  },
  {
    "question": "What is your point of view on your industry, the thing you believe that others do not?",
    "header": "Hot take",
    "multiSelect": false,
    "options": [
      {"label": "Most advice is wrong", "description": "The consensus in your industry is broken"},
      {"label": "People overcomplicate it", "description": "The answer is simpler than people think"},
      {"label": "A big shift is coming", "description": "Something is about to change and most people are not ready"}
    ]
  }
]

Read the full file on GitHub · 259 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 13d ago First seen · 259 lines · 184 tokens per session scan A 7f47bd4b5c13

Subscribe to this mod's changes

voice-builder is a skill published in the GitHub repository charlie947/social-media-skills (3,385 stars, last pushed 13d ago), licensed MIT. It adds 184 tokens to every session and 2,670 once invoked, about $0.0009 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 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens