ai-dial-chat: Skill for Claude Code

.claude/skills/celebration-scene-ideas/SKILL.md

celebration-scene-ideas is a skill for Claude Code, Codex from epam/ai-dial-chat. It costs 68 tokens per session (2,324 once invoked), scanned A, original, Apache-2.0.

A skill for designing story-driven celebration scenes in an AI chat interface, using page components as props, character movement, and SVG artwork. SVG is a format for drawing scalable two-dimensional graphics.

In plain words
What is it for?
Use it to propose storyboards, improve celebration animations, plan interactions with interface elements, or prepare a concept for implementation.
Why use it?
It helps turn a vague event-animation request into a clear concept while preserving the requested characters, mood, duration, and page elements. It does not implement the scene unless that work is requested.

Skill for Claude CodeCodex

Written for Claude Code and Codex: installed under .claude/, but also agents/openai.yaml present. Also seen: mentions AGENTS.md.

This is epam/ai-dial-chat's own configuration. It tells Claude Code and Codex how to work on ai-dial-chat itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything ai-dial-chat configures →

Reuse

Borrowing it

Nothing to install: this file belongs to epam/ai-dial-chat. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/epam/ai-dial-chat/development/.claude/skills/celebration-scene-ideas/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/epam/ai-dial-chat

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 celebration-scene-ideas

README.md
[![agentmods](https://agentmods.dev/badge/skills/epam/ai-dial-chat/celebration-scene-ideas/github.svg)](https://agentmods.dev/skills/epam/ai-dial-chat/celebration-scene-ideas)
Your own site
<a href="https://agentmods.dev/skills/epam/ai-dial-chat/celebration-scene-ideas"><img src="https://agentmods.dev/badge/skills/epam/ai-dial-chat/celebration-scene-ideas/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 celebration-scene-ideas

Your own site · 80×15
<a href="https://agentmods.dev/skills/epam/ai-dial-chat/celebration-scene-ideas"><img src="https://agentmods.dev/badge/skills/epam/ai-dial-chat/celebration-scene-ideas.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 68 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,324 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 $0.00068 $0.02324
Opus 5.5 $0.00027 $0.00930
Sonnet 5.5 $0.00014 $0.00465
Haiku 4.5 $0.00007 $0.00232

Measured 21d ago against content hash 3a4a8c4a2199, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

celebration-scene-ideas 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 21d 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.

.claude/skills/celebration-scene-ideas/SKILL.md · 105 lines

How it starts

The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Celebration Scene Ideas

Design scenes in which characters treat page components as props. Use this repository's Halloween scenes as a quality reference: a readable intention, action, interface reaction, unexpected resolution and restoration of the page. Respond in the user's language.

Establish the request

Use the event named in the request or already selected by the user. If missing, ask one short question while inspecting examples. Halloween is a quality reference, not the default event; the application's active event is not evidence of the user's choice.

Preserve requested characters, mood, number of ideas, duration, page elements and unwanted effects. Make reasonable choices for the rest. Ideas for an event without an existing module are valid; identify the module as additional work.

The default deliverable is an idea in the response. Do not create OpenSpec changes, scene files or images until the corresponding work is requested. If implementation is already authorized, use the concept as a brief foundation and continue without asking for the same permission again.

Implement scenes through openspec-propose (/opsx:propose, also called opsx-propose), then openspec-apply-change (/opsx:apply). Continue a suitable existing change instead of duplicating it. Include the plot, fallbacks, cleanup and numerical performance budgets in proposal/design/specs/tasks; verify them with tests and browser profiling during apply. Authorization for both proposal and implementation permits proceeding to apply without another confirmation. Archive only when requested.

Ground the idea in the repository

Paths below are relative to the AI DIAL Chat root. Follow AGENTS.md: use nx-workspace before workspace exploration and dial-docs before explaining documented behavior. If the repository is unavailable, distinguish assumptions from confirmed capabilities.

  1. Read libs/celebrations/README.md and the selected event's libs/celebrations/src/<event>/event.ts or event.tsx. Check existing scenes to avoid proposing a duplicate.
  2. Use the repository examples to choose one or two relevant techniques. Read their component, animation plan and target selection as needed; do not preload all of Halloween.
  3. Inspect libs/celebrations/src/models/celebration.ts and apps/chat/src/context/CelebrationHost.tsx for actual host anchors and triggers. An anchor does not guarantee a visible, eligible target in the current layout.

Read the full file on GitHub · 105 lines

Files

What ships with it

5 files 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. 21d ago Changed · +7 lines · +2 tokens per session 3a4a8c4a2199
  2. 24d ago First seen · 98 lines · 66 tokens per session scan A feafe3ba0a7d

Subscribe to this mod's changes

celebration-scene-ideas is a skill published in the GitHub repository epam/ai-dial-chat (502 stars, last pushed today), licensed Apache-2.0. It adds 68 tokens to every session and 2,324 once invoked, about $0.0003 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 2026-09-29.