Agent skill

Table Tone

by jwynia in jwynia/agent-skills

Diagnose and calibrate tonal delivery for tabletop RPG sessions.

MITAuto-check passedMedia & Creative

Install Table Tone

skills CLI
$ npx skills add jwynia/agent-skills --skill table-tone -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install jwynia/agent-skills table-tone --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/jwynia/agent-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/creative/fiction/application/table-tone .claude/skills/table-tone && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
table-tone
GitHub stars
169
Token cost
~3.7k tokens
SKILL.md length
1,908 words
Files
1
Skills in repo
111
Repo updated
First seen
Licence
MIT

At a glance

Diagnose and calibrate tonal delivery for tabletop RPG sessions.

  • Works in 8 steps: The Tonal Anchor → The Humor Policy → The Consequence Dial → …
  • Narration feels flat
  • SKILL.md covers Core Principle, The Tonal States, Establishing Baseline Tone and Reading the Room, plus 4 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Table Tone is an agent skill from jwynia/agent-skills. Diagnose and calibrate tonal delivery for tabletop RPG sessions. Use when narration feels flat, tone shifts jarringly, descriptions overwhelm play, or energy stays monotonous throughout sessions.

Its SKILL.md is about 3.7k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Media & Creative, covering Text to speech and voice. The licence is MIT.

When your agent uses it

  • Narration feels flat
  • Tone shifts jarringly
  • Descriptions overwhelm play
  • Energy stays monotonous throughout sessions

Example prompts

  • “/table-tone”

Workflow steps

8 steps, taken from the step headings in SKILL.md.

  1. The Tonal Anchor
  2. The Humor Policy
  3. The Consequence Dial
  4. The Wonder/Horror Ratio
  5. Identify the Problem Type
  6. Check Baseline
  7. Look for Pattern
  8. Recommend Interventions

What it can do on your machine

Read from SKILL.md and the folder at commit e02ec7e. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Table Tone loads about 3.7k tokens when it runs. Until then it costs about 52 tokens; SKILL.md has 1,908 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~52
When it runs · the whole SKILL.md, loaded when a task matches
~3.7k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from jwynia/agent-skills at commit e02ec7e, republished under its MIT licence (© jwynia). 1,908 words, ~3,724 tokens.

Download SKILL.mdSave it as .claude/skills/table-tone/SKILL.md (or your agent's skills folder).
name
table-tone
description
Diagnose and calibrate tonal delivery for tabletop RPG sessions. Use when narration feels flat, tone shifts jarringly, descriptions overwhelm play, or energy stays monotonous throughout sessions.
license
MIT
metadata.author
jwynia
metadata.version
1.0
metadata.type
diagnostic
metadata.mode
diagnostic+assistive
metadata.domain
fiction

Table Tone: Diagnostic Skill

You diagnose tonal delivery problems at the RPG table. Your role is to help GMs establish, maintain, and intentionally vary the atmospheric feel of their games.

Core Principle

Tone is the contract between GM and players about what kind of experience they're having.

Tone tells players how to interpret events. The same scene—a tavern brawl—plays completely differently in:

  • Swashbuckling adventure: exciting, consequence-light, maybe comedic
  • Gritty noir: dangerous, morally ambiguous, someone might die
  • Cosmic horror: the violence reveals something wrong with reality itself

When tone is unclear or inconsistent, players don't know how to engage. They make jokes during horror moments or take silly situations too seriously.


The Tonal States

State T1: Flat Table

Symptoms: Descriptions are information dumps. "You enter a room. There's a table. Two goblins are here." Everything delivered at the same neutral energy. Players feel like they're hearing a wiki article, not experiencing a world.

Key Questions:

  • Are descriptions engaging multiple senses?
  • Is there emotional color in the narration?
  • Does the delivery have any energy variation?
  • Are NPCs just information dispensers?

Diagnostic Checklist:

  • Descriptions use sensory details beyond visual
  • Narration includes emotional/atmospheric language
  • Voice modulation (even text-based pacing) varies
  • NPCs have distinct mannerisms and energy

Interventions:

  • Add one non-visual sense to each location description
  • Give each NPC a signature verbal tic or physical behavior
  • Vary sentence length and pacing in descriptions
  • Practice "show the feeling" not just "state the facts"

Example Fix:

  • Flat: "The throne room is large. The king sits on a throne. He looks angry."
  • Tonal: "Silence. The throne room swallows your footsteps. King Aldric doesn't rise—doesn't need to. His knuckles whiten on the armrest as you approach."

State T2: Tonal Whiplash

Symptoms: Jarring shifts between comedy and drama, or horror and slapstick. Players don't know what register to operate in. Emotional beats don't land because the previous scene was tonally incompatible.

Key Questions:

  • Do tonal shifts have transitions?
  • Is there a baseline tone to return to?
  • Are shifts intentional or accidental?
  • Do players seem confused about how to engage?

Diagnostic Checklist:

  • Clear baseline tone established for campaign
  • Transitions buffer major tonal shifts
  • Comedy doesn't undercut dramatic moments
  • Horror/drama don't interrupt fun when players are joking

Signs of Whiplash:

  • Dramatic villain speech immediately followed by goofy shopkeeper
  • Horror reveal that players laugh at because previous scene was comedic
  • Players unsure if they should take a threat seriously
  • "Wait, is this supposed to be funny?" confusion

Interventions:

  • Establish and communicate baseline tone
  • Use transition scenes to shift between registers
  • Let dramatic moments breathe before shifting
  • Match NPC energy to scene requirements
  • Signal intentional shifts: "the mood changes..."

Transition Techniques:

  • Time skip: "Three days later, the mood has lifted..."
  • Scene buffer: neutral travel/rest scene between extremes
  • Environmental cue: weather, lighting, music shift
  • Character reflection: moment of quiet processing

State T3: Purple GM

Symptoms: Overwrought descriptions that slow play. Every room gets a paragraph. Every NPC gets a dramatic introduction. Players zone out during narration. Combat takes forever because each attack needs flowery description.

Key Questions:

  • Are descriptions proportional to importance?
  • Can players engage, or must they wait?
  • Is style overwhelming substance?
  • Does narration speed match action speed?

Diagnostic Checklist:

  • Important scenes get more description than mundane ones
  • Players have space to interject and act
  • Combat descriptions are punchy, not paragraphs
  • Purple only for key moments, not everything

When Rich Description Works:

  • First introduction of major location
  • Dramatic reveals and turning points
  • Horror/wonder moments meant to linger
  • Player victories and epic moments

When to Cut Back:

  • Routine travel and shopping
  • Combat (action needs speed)
  • Repeated locations
  • When players are eager to act

Interventions:

  • Limit descriptions to 2-3 sentences default
  • Reserve paragraphs for key moments
  • Match description length to scene importance
  • Check: are players waiting or engaged?
  • Use player imagination—hint, don't exhaustively describe

Example Calibration:

  • Too much: "The ancient oaken door, its iron bands corroded by centuries of salt air, creaks on hinges that haven't known oil since the Third Age, revealing beyond it a chamber of such profound darkness that your torchlight seems to recoil..."
  • Right-sized: "The old door groans open. Beyond, darkness swallows your torchlight. Something in there is breathing."

State T4: Monotone Energy

Symptoms: Everything delivered at the same intensity. Combat doesn't feel more urgent than shopping. The climactic battle has the same energy as a random encounter. Players never feel tension rising or falling.

Key Questions:

  • Does pacing vary between scenes?
  • Do high-stakes moments feel different?
  • Is there a sense of rising/falling tension?
  • Does the climax feel climactic?

Diagnostic Checklist:

  • High-stakes scenes have urgency
  • Quiet moments actually feel quiet
  • Pacing accelerates toward climaxes
  • Resolution scenes decompress

Energy Calibration by Scene Type:

Scene TypeEnergy LevelPacing
ExplorationMediumMeasured, atmospheric
Social/RPVariableResponsive to players
CombatHighFast, punchy
InvestigationLow-MediumDeliberate, building
ClimaxMaximumIntense, accelerating
DenouementLowSlow, reflective

Interventions:

  • Consciously shift energy between scene types
  • Use pacing as a tool: slow for tension, fast for action
  • Build to climaxes through escalating energy
  • Allow decompression after intense moments
  • Practice "reading the room" for when to push or pull back

State T5: Genre Mismatch

Symptoms: Tone doesn't match the game's genre expectations. Running a horror game like an action movie. Playing D&D like Call of Cthulhu. The mechanics and tone are fighting each other.

Key Questions:

  • What genre is this game supposed to be?
  • Does the tone match genre conventions?
  • Are mechanics and tone aligned?
  • Do players expect this genre's tropes?

Genre-Tone Mapping:

GenreTonal BaselineKey Elements
Heroic FantasyHopeful, adventurousGood vs. evil, triumph, wonder
GrimdarkCynical, harshMoral ambiguity, costly victories
Cosmic HorrorDread, insignificanceUnknown, madness, no true victory
Pulp AdventureExciting, lightTwo-fisted action, daring escapes
NoirCynical, atmosphericMoral compromise, femme fatales
SwashbucklingDashing, romanticWit, style over substance
Survival HorrorTense, resource-scarceVulnerability, hard choices

Interventions:

  • Identify target genre explicitly
  • Study genre conventions (films, books, other games)
  • Align NPC behavior with genre expectations
  • Match consequence weight to genre (pulp: light, grimdark: heavy)
  • Use genre-appropriate language and imagery

Establishing Baseline Tone

Before play begins, establish:

1. The Tonal Anchor

One sentence describing how this campaign should FEEL:

  • "Desperate heroes against impossible odds"
  • "Competent professionals doing morally gray work"
  • "Wide-eyed adventurers discovering wonder"
  • "Survivors barely holding on in a broken world"
2. The Humor Policy

Where does comedy fit?

  • Integrated: Comedy woven throughout naturally
  • Bracketed: Comedy in downtime, serious in action
  • Rare: Comedy as relief valve only
  • None: Straight-faced throughout
3. The Consequence Dial

How heavy are outcomes?

  • Light: Death rare, setbacks temporary
  • Medium: Real stakes, recoverable failure
  • Heavy: Consequences stick, death possible
  • Brutal: The world is not fair
4. The Wonder/Horror Ratio

What emotional notes dominate?

  • More wonder → sense of discovery, magic is amazing
  • More horror → sense of dread, the unknown is threatening
  • Balanced → both present, shifting by context

Reading the Room

Tone isn't just GM output—it's a conversation with players.

Show full SKILL.md (771 more words)Show less
Signs Players Want Different Tone:
Player BehaviorMay Indicate
Joking during serious scenesNeed lighter tone or transition
Quiet/withdrawnScene too intense or wrong register
Checking phonesEnergy too low, pacing too slow
Interrupting descriptionsReady to act, cut the narration
Leaning in, engagedTone is working, maintain
Adjusting in Real Time:
  • If jokes derail drama → either lean into comedy or clearly signal "let's refocus"
  • If players seem lost → clarify what register you're in
  • If energy flags → accelerate pacing or shift scene
  • If tension overwhelms → provide relief valve moment

Anti-Patterns

The Shakespeare GM

Pattern: Every NPC speaks in elevated language regardless of station. Problem: Kills verisimilitude, exhausts players, blurs NPC distinction. Fix: Match NPC language to character and context. The peasant doesn't talk like the wizard.

The Edgelord

Pattern: Grimdark everything. Constant horror. No hope. Problem: Numbness. Horror needs contrast to work. Fix: Light makes shadow. Include moments of warmth, humor, hope to make the dark matter.

The Theme Park GM

Pattern: Every zone has different tone. Forest = whimsy, dungeon = horror, city = comedy. Problem: World feels like a theme park, not a place. Fix: Establish world-level baseline. Individual locations can shade it, not contradict it.

The Emotional Ambush

Pattern: Heavy emotional content without warning or consent. Problem: Players feel blindsided, not immersed. Fix: Establish content agreements. Approach heavy content with player buy-in.

The One-Note Band

Pattern: Same tone, always. Action movie pace for everything. Problem: No contrast, no breathing room, eventual exhaustion. Fix: Vary deliberately. Quiet after loud. Slow after fast.


Diagnostic Process

When a GM reports tone problems:

1. Identify the Problem Type
  • Does narration feel boring? → T1 (Flat Table)
  • Are tonal shifts jarring? → T2 (Tonal Whiplash)
  • Are descriptions overwhelming? → T3 (Purple GM)
  • Does everything feel the same? → T4 (Monotone Energy)
  • Does tone not fit the game? → T5 (Genre Mismatch)
2. Check Baseline
  • Is there an established baseline tone?
  • Is it communicated to players?
  • Is it appropriate for the game/genre?
3. Look for Pattern
  • Is the problem consistent or situational?
  • When does it break down? (combat, drama, NPCs?)
  • What's the GM's natural tendency? (too sparse, too rich?)
4. Recommend Interventions

Based on identified state, provide specific fixes.


Integration with Other Skills

Related SkillWhen to Hand Off
scene-sequencingWhen pacing issues are structural, not tonal
dialogueWhen NPC voice specifically needs work
genre-conventionsWhen genre knowledge gap is the issue
game-facilitatorWhen the issue is player management, not delivery
Prerequisites

Do NOT use table-tone when:

  • Players aren't engaged because the STORY is broken (use story-sense)
  • The issue is mechanical, not tonal
  • Player conflict is the real problem

Quick Reference: Tone Calibration

Before Session:

  • What's the baseline tone for today?
  • Any major tonal shifts planned?
  • What energy level are we starting at?

During Session:

  • Am I matching scene importance with description weight?
  • Are my transitions smooth or jarring?
  • What's the room energy? Match or shift it?

After Session:

  • Did the tone land?
  • Were there jarring moments?
  • What worked? What didn't?

Output Persistence

This skill writes primary output to files so work persists across sessions.

Output Discovery

Before doing any other work:

  1. Check for context/output-config.md in the project
  2. If found, look for this skill's entry
  3. If not found or no entry for this skill, ask the user first:
    • "Where should I save output from this table-tone session?"
    • Suggest: explorations/table-tone/ or a sensible location for this project
  4. Store the user's preference:
    • In context/output-config.md if context network exists
    • In .table-tone-output.md at project root otherwise
Primary Output

For this skill, persist:

  • Tone diagnosis - current state and issues identified
  • Intended tone definition - what the GM is aiming for
  • Toolkit selections - techniques and elements that reinforce tone
  • Session notes - what worked and what didn't
Conversation vs. File
Goes to FileStays in Conversation
Tone definitionDiscussion of preferences
Toolkit checklistClarifying questions
Session retrospectivesReal-time feedback
Technique recommendationsPlayer dynamic discussion
File Naming

Pattern: {campaign}-tone-{date}.md Example: dnd-campaign-tone-2025-01-15.md

What You Do NOT Do

  • You do not dictate what tone a campaign "should" be
  • You do not diagnose when the problem is player conflict
  • You do not impose your preferences over the table's
  • You do not assume one tone is better than another

Your role is diagnostic: identify tonal problems, explain why they're problems, and guide toward solutions. The GM establishes their own tone.


Key Insight

Tone is a promise. When you establish a tone, players calibrate their engagement, emotional investment, and expectations to match. Break that promise carelessly and you break immersion. Honor it and players will follow you anywhere—into comedy, tragedy, horror, or wonder.

The goal isn't "correct" tone. The goal is intentional tone—knowing what feeling you're creating and creating it on purpose.

© jwynia, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/creative/fiction/application/table-tone of jwynia/agent-skills.

Open the folder on GitHubat commit e02ec7e

Compare with similar skills

Table Tone next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Table Tone compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Table Tone this skilljwynia/agent-skills169—~3.7kAutomated safety check: PassMIT
MoneyPrinterTurbo Video Generatorharry0703/MoneyPrinterTurbo129k—~2.1kAutomated safety check: WarnMIT
HyperFrames Media Useheygen-com/hyperframes59k—~2.4kAutomated safety check: PassApache-2.0
Openspec OnboardSAP/e-mobility-charging-stations-simulator22725 repos~3.5kAutomated safety check: PassMIT
Blog AudioAgriciDaniel/claude-blog2.3k1 repos~2.2kAutomated safety check: NotesMIT
Musictadaspetra/loop2962 repos~827Automated safety check: PassMIT

Similar skills

  • MoneyPrinterTurbo Video Generator

    harry0703/MoneyPrinterTurbo

    Installs and runs MoneyPrinterTurbo to turn a topic or script into a finished short video with voice-over, subtitles, stock footage and music.

    129k GitHub stars~2.1k tokensUpdated today
    Media & CreativeAuto-check: warnings
  • HyperFrames Media Use

    heygen-com/hyperframes

    Finds, generates and edits media for HyperFrames video projects: music, sound effects, images, icons, logos, voiceovers, captions and color grades.

    59k GitHub stars~2.4k tokensUpdated today
    Media & CreativeAuto-check passed
  • Openspec Onboard

    SAP/e-mobility-charging-stations-simulator

    Official

    Guided onboarding for OpenSpec - walk through a complete workflow cycle with narration and real codebase work.

    227 GitHub starsUsed in 25 repos~3.5k tokens
    Media & CreativeAuto-check passed
  • Blog Audio

    AgriciDaniel/claude-blog

    Generate audio narration of blog posts using Google Gemini TTS.

    2.3k GitHub starsUsed in 1 repo~2.2k tokens
    Media & CreativeAuto-check: notes
  • Music

    tadaspetra/loop

    Generate music using ElevenLabs Music API. An agent skill from tadaspetra/loop.

    296 GitHub starsUsed in 2 repos~827 tokens
    Media & CreativeAuto-check passed
  • Edu Math Video

    wy51ai/edulab

    A skill your agent uses when asked to make an explainer / walkthrough video (讲解视频、解题视频、例题精讲、微课) for a math problem (数学题, geometry, algebra, functions, motion/行程 problems), from a problem screenshot…

    1.4k GitHub stars~2.5k tokensUpdated 11 days ago
    Media & CreativeAuto-check: notes

More from jwynia/agent-skills

All 111 skills in this repo
  • Devcontainer

    jwynia/agent-skills

    Diagnose devcontainer configuration problems and guide development environment setup.

    169 GitHub stars~1.2k tokensUpdated 7 mo ago
    Auto-check: notes
  • Frontend Design

    jwynia/agent-skills

    Create distinctive, production-grade frontend interfaces with high design quality.

    169 GitHub stars~3.2k tokensUpdated 7 mo ago
    Auto-check passed
  • Gitea Workflow

    jwynia/agent-skills

    Orchestrate agile development workflows for Gitea repositories using the tea CLI.

    169 GitHub stars~3.8k tokensUpdated 7 mo ago
    Auto-check passed
  • Godot Asset Generator

    jwynia/agent-skills

    Generate game assets using AI image generation APIs (DALL-E, Replicate, fal.ai) and prepare them for Godot.

    169 GitHub stars~3.8k tokensUpdated 7 mo ago
    Auto-check passed
  • Mastra Hono

    jwynia/agent-skills

    Develop AI agents, tools, and workflows with Mastra v1 Beta and Hono servers.

    169 GitHub stars~2.9k tokensUpdated 7 mo ago
    Auto-check passed
  • PPTX Generator

    jwynia/agent-skills

    Create and manipulate PowerPoint PPTX files programmatically.

    169 GitHub stars~3.1k tokensUpdated 7 mo ago
    Auto-check passed

Questions about Table Tone

What does Table Tone do?

Diagnose and calibrate tonal delivery for tabletop RPG sessions. Table Tone is an agent skill from jwynia/agent-skills. Diagnose and calibrate tonal delivery for tabletop RPG sessions.

When should I use Table Tone?

Table Tone fits situations like: narration feels flat; tone shifts jarringly; descriptions overwhelm play; energy stays monotonous throughout sessions.

How do I install Table Tone in Claude Code?

Run `npx skills add jwynia/agent-skills --skill table-tone -a claude-code`. Or copy the skill folder (skills/creative/fiction/application/table-tone in jwynia/agent-skills) into .claude/skills/table-tone in your project. Claude Code loads it when a task matches its description.

How do I install Table Tone in Codex?

Run `npx skills add jwynia/agent-skills --skill table-tone -a codex`. Or copy the skill folder (skills/creative/fiction/application/table-tone in jwynia/agent-skills) into .agents/skills/table-tone in your project. Codex loads it when a task matches its description.

Can I use Table Tone in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add jwynia/agent-skills --skill table-tone -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/table-tone, .gemini/skills/table-tone, .github/skills/table-tone and .opencode/skills/table-tone in your project.

What does Table Tone need to run?

SKILL.md names no scripts, command-line tools or credentials: Table Tone is instructions for the agent only.

Does Table Tone access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Table Tone safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Table Tone use?

Table Tone is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Table Tone use?

About 3.7k tokens (SKILL.md is roughly 15k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Table Tone?

Skills that share tags, products or a category with Table Tone: MoneyPrinterTurbo Video Generator (harry0703/MoneyPrinterTurbo, 129k stars), HyperFrames Media Use (heygen-com/hyperframes, 59k stars), Openspec Onboard (SAP/e-mobility-charging-stations-simulator, 227 stars) and Blog Audio (AgriciDaniel/claude-blog, 2.3k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Table Tone?

jwynia (a GitHub user) maintains it in jwynia/agent-skills, which has 169 GitHub stars. The repository holds 111 skills in this directory. The repository was last updated on February 24, 2026.

Source: jwynia/agent-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.