gigachat-image

gigachat-image is a skill for Claude Code from theYahia/WWmcp. It costs 20 tokens per session (577 once invoked), scanned A, original, MIT.

An image-generation workflow for GigaChat, an AI service that creates pictures from text descriptions. It also supports checking the remaining usage allowance and adding an uploaded reference image.

In plain words
What is it for?
Use it to create an image from a prompt, provide a reference file, check the allowance before generation, and adjust the subject, style, or colours between attempts.
Why use it?
It gives a defined way to check availability, describe the desired picture, receive the generated file identifier, and refine the result. It avoids assuming that a direct image link will be returned.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Good fit Use it to create an image from a prompt, provide a reference file, check the allowance before generation, and adjust the subject, style, or colours between attempts.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/theyahia/wwmcp/gigachat-image
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 theYahia/WWmcp --skill gigachat-image
Clone the repo
git clone --depth 1 https://github.com/theYahia/WWmcp

Made for: Claude Code.

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 gigachat-image

README.md
[![agentmods](https://agentmods.dev/badge/skills/theyahia/wwmcp/gigachat-image/github.svg)](https://agentmods.dev/skills/theyahia/wwmcp/gigachat-image)
Your own site
<a href="https://agentmods.dev/skills/theyahia/wwmcp/gigachat-image"><img src="https://agentmods.dev/badge/skills/theyahia/wwmcp/gigachat-image/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 gigachat-image

Your own site · 80×15
<a href="https://agentmods.dev/skills/theyahia/wwmcp/gigachat-image"><img src="https://agentmods.dev/badge/skills/theyahia/wwmcp/gigachat-image.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 20 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 577 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 $0.00020 $0.00577
Opus 5 $0.00010 $0.00289
Sonnet 5 $0.00004 $0.00115
Haiku 4.5 $0.00002 $0.00058

Measured 5d ago against content hash ee3328fbd1f6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

gigachat-image 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 5d 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.

servers/gigachat/.claude/skills/gigachat-image/SKILL.md · 52 lines

What it actually says

/gigachat-image — Картинка из текста

Алгоритм

  1. Вызови get_balance — проверь остаток токенов и квоты. Генерация изображений съедает заметно больше, чем текст; узнать об исчерпании до вызова дешевле, чем после.
  2. Собери промпт. GigaChat генерирует изображение из обычного сообщения диалога, поэтому опиши картинку прямо в тексте: сюжет, стиль, композиция, палитра.
  3. Вызови generate_image с model (GigaChat или GigaChat-Pro) и messages — массивом объектов вида роль user плюс content с описанием.
  4. Ответ содержит идентификатор файла изображения. Отдай его пользователю и скажи, как картинку забрать — прямой ссылки в ответе нет.
  5. Если результат не устроил, уточняй промпт по одному параметру за итерацию (сначала сюжет, потом стиль, потом палитра) — так видно, что именно повлияло.
  6. Если нужно приложить референс, вызови file_upload с file_content (base64), file_name и purpose, и упомяни файл в сообщении.

Формат ответа

## Изображение GigaChat

**Модель**: GigaChat-Pro
**Промпт**: «Осенний парк в тумане, акварель, приглушённая палитра»
**Файл**: img_8f2a91c0
**Квота**: осталось 128 400 токенов

Уточнить: добавьте в промпт время суток и ракурс.

Важно

  • В отличие от текстовой генерации, у generate_image нет параметров temperature и max_tokens — вся настройка идёт через формулировку промпта.
  • Ответ отдаёт идентификатор файла, а не картинку в ответе. Не утверждай, что показал изображение.
  • GigaChat отклоняет промпты, нарушающие его политику контента. Ошибку показывай как есть, не обходи её переформулировками без запроса пользователя.

Примеры

/gigachat-image осенний парк в тумане, акварель
/gigachat-image логотип кофейни, минимализм, две краски GigaChat-Pro
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. 5d ago First seen · 52 lines · 20 tokens per session scan A ee3328fbd1f6

Subscribe to this mod's changes

gigachat-image is a skill published in the GitHub repository theYahia/WWmcp (29 stars, last pushed 4d ago), licensed MIT. It adds 20 tokens to every session and 577 once invoked, about $0.0001 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 2026-09-06.

Related

Other skills, from other repositories

audio-dispatch

Transcribe a meeting audio file with Voxtral diarization, classify each speaker's turns by intent, and produce a per-speaker action plan. Use when the user provides a meeting or call recording with multiple speakers.

Swih/mistral-mcp · 43 tokens

ableton-extension

Build, modify, and debug Ableton Live extensions written with the @ableton-extensions/sdk — TypeScript/Node.js code that runs in Live's Extension Host. Use this whenever the user is working on an Ableton Live extension: scaffolding a new one, adding context-menu actions or commands, navigating or mutating the Live Set…

aker-dev/ableton-extension-skill · 202 tokens

javascript-typescript

Professional JavaScript and TypeScript development skill covering modern ES6+, TypeScript, Node.js, Express, React, testing frameworks, and best practices. Use this skill when developing JavaScript/TypeScript applications, building React/Node.js projects, implementing RESTful APIs, or need guidance on modern JS/TS…

ProjAnvil/MindForge · 69 tokens

visualize

Render a polished visual inline in the chat as part of your answer — a diagram, a chart, an interactive explainer, or a UI mockup. Load it proactively whenever an explanation would land better as a picture than as prose. Do not wait to be asked.

vellum-ai/vellum-assistant · 57 tokens

okx-cex-trade

Use when the user asks to 'buy BTC', 'sell ETH', 'place a limit order', 'place a market order', 'cancel my order', 'amend my order', 'long BTC perp', 'short ETH swap', 'open a position', 'close a position', 'set take profit', 'limit take profit', 'immediate TP', 'set stop loss', 'self-trade prevention', 'stpMode'…

okx/agent-trade-kit · 278 tokens

memstack-content-youtube-script

Use this skill when the user says 'YouTube script', 'video script', 'write script for YouTube', 'YouTube video outline', or is creating scripted content for a YouTube video with hooks, chapters, and CTAs. Do NOT use for TikTok/Reels short-form scripts or webinar presentations.

cwinvestments/memstack · 70 tokens