s4h-writing-dialogue

s4h-writing-dialogue is a skill for Claude Code from human-avatar/skills-for-humanity. It costs 91 tokens per session (1,665 once invoked), scanned A, original, MIT.

A guide to improving fictional or scripted dialogue by examining hidden meaning, distinct character voices, exposition, and scene momentum.

In plain words
What is it for?
Use it to review or rewrite dialogue so characters speak with different voices and their underlying tensions come through indirectly.
Why use it?
It helps fix conversations that sound unnatural, explain too much, or make every character sound alike.

Skill for Claude Code

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

Part of the skills-for-humanity plugin — 197 skills, 1 hook shipped together

Good fit Use it to review or rewrite dialogue so characters speak with different voices and their underlying tensions come through indirectly.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/human-avatar/skills-for-humanity/s4h-writing-dialogue
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 human-avatar/skills-for-humanity --skill s4h-writing-dialogue
Clone the repo
git clone --depth 1 https://github.com/human-avatar/skills-for-humanity

Made for: Claude Code.

Or install skills-for-humanity, the plugin that ships this one along with the rest of its 197 skills, 1 hook.

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 s4h-writing-dialogue

README.md
[![agentmods](https://agentmods.dev/badge/skills/human-avatar/skills-for-humanity/s4h-writing-dialogue/github.svg)](https://agentmods.dev/skills/human-avatar/skills-for-humanity/s4h-writing-dialogue)
Your own site
<a href="https://agentmods.dev/skills/human-avatar/skills-for-humanity/s4h-writing-dialogue"><img src="https://agentmods.dev/badge/skills/human-avatar/skills-for-humanity/s4h-writing-dialogue/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 s4h-writing-dialogue

Your own site · 80×15
<a href="https://agentmods.dev/skills/human-avatar/skills-for-humanity/s4h-writing-dialogue"><img src="https://agentmods.dev/badge/skills/human-avatar/skills-for-humanity/s4h-writing-dialogue.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 91 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,665 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
  • NVIDIA SkillSpector pass 7 Sept 2026
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 $0.00091 $0.01665
Opus 5 $0.00046 $0.00833
Sonnet 5 $0.00018 $0.00333
Haiku 4.5 $0.00009 $0.00167

Measured 9d ago against content hash 75af2f2625a7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

s4h-writing-dialogue 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 9d 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.

skills/s4h-writing-dialogue/SKILL.md · 125 lines

How it starts

The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Writing: Dialogue

Dialogue fails in two primary ways: it says exactly what it means (no subtext), or it explains things the characters already know (exposition dressed as conversation). Both failures produce the same effect on the reader — a sense of flatness, of the author's hand visible, of characters becoming mouthpieces rather than people.

Real conversation is oblique. People in conflict rarely say "I'm angry with you." They talk about something else. The anger is present in what they say about the dishes, the schedule, the way someone looks. The subtext is the scene — the surface conversation is the vehicle for it. When dialogue is on the nose, the subtext and the surface are the same thing, which means there is no scene — only information delivery.

Voice differentiation is the second major failure point. Every character has a distinct rhythm of thought, a vocabulary range shaped by their history, evasion patterns specific to their wound, and a relationship to silence. When characters sound interchangeable, the dialogue's only differentiator is the attribution ("he said / she said") — which means the characters, on the page, don't exist yet.


Your Process

Step 1: Speaker Goals — Surface vs. Subtext For each speaker in the exchange, identify:

Framing check: Confirm the specific dialogue before continuing. State what you've identified — the exchange being analysed, the speakers involved, and the apparent dramatic situation — in one sentence, then use AskUserQuestion:

  • Question: "I'm reading this as: [your one-sentence framing of the dialogue, its speakers, and the situation it takes place in]. Is that right?"
  • Header: "Framing"
  • Options:
    • Yes — proceed — framing is correct
    • Adjust — one element is off; user will correct it before you continue
    • Reframe — different situation than read; incorporate the correction before proceeding
  • Surface goal: What they appear to be talking about
  • Subtext goal: What they actually want from this exchange (what they won't say directly)

Read the full file on GitHub · 125 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. 9d ago First seen · 125 lines · 91 tokens per session scan A 75af2f2625a7

Subscribe to this mod's changes

s4h-writing-dialogue is a skill published in the GitHub repository human-avatar/skills-for-humanity (223 stars, last pushed 1mo ago), licensed MIT. It adds 91 tokens to every session and 1,665 once invoked, about $0.0005 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 2026-09-03.

Related

Other skills, from other repositories

decision-making-under-pressure

Provides practical habits for making better decisions faster -- reframing problems before solving them, knowing when to stop deliberating, balancing intuition with analysis, resisting 'just this once' compromises, and breaking overthinking cycles. Use when facing a high-stakes choice with incomplete data, sensing that…

fatihguner/foreman · 95 tokens

flow-state

Optimizes individual and team productivity using Csikszentmihalyi's flow state framework, covering the conditions for flow (clear goals, immediate feedback, challenge-skill balance), the four-stage flow cycle, and organizational flow design. Use when auditing personal or team focus time, diagnosing productivity loss…

fatihguner/foreman · 96 tokens

stoic-right-action

Applies Stoic ethics of right action to entrepreneurial decision-making, covering the four cardinal virtues (courage, justice, temperance, wisdom), ethical leadership under pressure, and the discipline of choosing the harder right over the easier wrong. Use when facing ethical dilemmas in business, building a…

fatihguner/foreman · 89 tokens

bakeoff

Turn one decision into a judged tournament of solutions, then pick the best. Given a problem, design choice, or a suggestion you want cross-verified, it generates diverse candidate solutions, auto-derives the evaluation dimensions for THAT problem (so you don't have to know what to score on), judges every candidate…

CoriChui/bakeoff · 330 tokens

balanced-scorecard

Translate strategy into metrics across Financial, Customer, Internal Process, and Learning & Growth perspectives.

tupe12334/instinct · 22 tokens

customer-journey-map

Visualize every touchpoint a customer has with a product or service — stages, actions, emotions, pain points, opportunities.

tupe12334/instinct · 31 tokens