agent-deck
Управление сессиями AI агентов через agent-deck CLI. Триггеры (RU): "запусти агента", "запусти саб-агента", "создай сессию",…
Publish static page artifacts from the publisher workspace to a GitHub Pages repository using a fine-grained token, with advisory image optimization and an original-image path. Use when a React/static page artifact is already prepared and needs to be copied into the Pages repo
$ npx -y skills add artwist-polyakov/polyakov-claude-skills --skill github-pages-publisher --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/github-pages-publisherContext preview
The summary Claude sees to decide when to auto-load this skill.
Publish static page artifacts from the publisher workspace to a GitHub Pages repository using a fine-grained token, with advisory image optimization and an original-image path. Use when a React/static page artifact is already prepared and needs to be copied into the Pages repo
name: github-pages-publisher description: Publish static page artifacts from the publisher workspace to a GitHub Pages repository using a fine-grained token, with advisory image optimization and an original-image path. Use when a React/static page artifact is already prepared and needs to be copied into the Pages repo under a strict year/year-month/page-slug directory layout, then committed and pushed, with a final public artifact URL returned.
Publish already-built static artifacts to a GitHub Pages repository.
This skill is the **deployment/output layer** for page artifacts created by other skills.
Every published artifact must go into this path shape inside the target repo:
`<year>/<year>-<month>/<page-slug>/`
Example:
Never publish flat at repo root. Never skip the year or year-month nesting.
Input should already exist as one of these:
This skill should not do major frontend design work. It should package and publish what already exists.
Always return the final public URL of the artifact.
Assume GitHub Pages serves from the repo's configured Pages base URL. The final URL should be:
`<pages-base-url>/<year>/<year>-<month>/<page-slug>/`
or, if needed explicitly:
`.../<page-slug>/index.html`
Prefer the clean directory URL when it resolves correctly.
1. Determine the publish date bucket:
2. Create or update target directory:
3. Copy artifact files into that directory 4. Optimize oversized raster images when practical, unless original-size sharing is intentional 5. Verify there is an entrypoint (`index.html` normally) 6. Run pre-publish validation (see section above) 7. Commit and push to the Pages repo using the configured fine-grained token workflow 8. Return the final public URL
python3 scripts/publish_static.py --source <dir-or-html> --slug <name> [--date YYYY-MM-DD] [--image-max-kb 500]
The script copies the artifact into `YYYY/YYYY-MM/slug/`, optimizes oversized `.jpg`, `.jpeg`, `.png`, and `.webp` images, commits, pushes, and prints the final public URL.
Image optimization is a recommendation, not a hard requirement. By default, the publishing script tries to keep each raster image under `500KB` by stripping metadata, recompressing, and resizing long edges when needed.
Use `--image-max-kb <kb>` for a different target. Use `--keep-large-images` or `--image-max-kb 0` when the user explicitly needs original-size images (for example, a full-resolution infographic, map, or downloadable media asset).
The original `--source` artifact is not changed. Optimization happens only after files are copied into the publish repo target directory. If Pillow/uv is unavailable or optimization fails, continue publishing originals and mention the warning.
Manual console run for a prepared artifact:
uv run --with pillow python3 scripts/optimize_images.py <artifact-dir> --max-kb 500
Before pushing, the agent must verify:
Read `config/README.md` for required environment variables and URL derivation.
Read if needed:
Управление сессиями AI агентов через agent-deck CLI. Триггеры (RU): "запусти агента", "запусти саб-агента", "создай сессию",…
Workflow кросс-агентного ревью с Codex. Triggers (RU): "кодекс ревью". Triggers (EN): "with codex review", "codex review…
SEO-краулер сайтов на базе Crawl4AI. Полный аудит страниц: title, meta, H1, canonical, breadcrumbs, навигация, внутренние ссылки.…
Fill Word document templates (contracts, forms) with structured data using docxtpl. Use when user uploads a .docx template with…
Generate/edit images via fal.ai. Supports Google Nano Banana Pro and OpenAI GPT Image 2 selected from config/.env. Supports…
Анализирует генетические данные пользователя из VCF файла. Используй когда пользователь спрашивает о своей генетике,…