Publish static page artifacts to SourceCraft Sites (Yandex infrastructure, works in Russia), with advisory image optimization and an original-image path. Use when a static page/React artifact needs to be deployed to SourceCraft under YYYY/YYYY-MM/page-slug directory layout.
npx skills add https://github.com/artwist-polyakov/polyakov-claude-skills --skill sourcecraft-publisher
Publish already-built static artifacts to a SourceCraft Sites repository. Works from Russia (Yandex infrastructure).
This skill is the deployment/output layer for page artifacts created by other skills (e.g. telegram-channel-parser digest).
Every published artifact must go into this path shape inside the target repo:
<year>/<year>-<month>/<page-slug>/
Example:
2026/2026-03/ai-digest-week/Never publish flat at repo root. Never skip the year or year-month nesting.
Input should already exist as one of these:
This skill does not do frontend design work. It packages and publishes what already exists.
Read config/README.md for required environment variables and token setup.
cp config/.env.example config/.env
Required: SOURCECRAFT_TOKEN, SOURCECRAFT_REPO, SOURCECRAFT_SITE_URL.
YYYYYYYY-MM<year>/<year-month>/<page-slug>/index.html normally).sourcecraft/sites.yaml exists in repo rootpython3 scripts/publish_static.py --source <dir-or-html> --slug <name> [--date YYYY-MM-DD] [--image-max-kb 500]
The script:
.sourcecraft/sites.yaml config existsYYYY/YYYY-MM/slug/.jpg, .jpeg, .png, and .webp images before commitImage 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
Always return the final public URL:
<SOURCECRAFT_SITE_URL>/<year>/<year>-<month>/<page-slug>/
Before pushing, verify:
index.html entrypointRead if needed:
references/publish-checklist.md — operational checklist before pushingAnalyze Stockbee-style Day 1 Episodic Pivot candidates from earnings, guidance raises, M&A, FDA/regulatory approvals, analyst actions, major contracts, product launches, short-squeeze catalysts, or theme/story events. Scores catalyst quality together with gap/range expansion, volume shock, neglect/revaluation context, liquidity, and risk to the EP-day low. Use when the user asks for EP candidates, episodic pivots, Day 1 catalyst trades, game-changing news reactions, delayed EP watchlists, or handoffs into PEAD monitoring.
Maps architectural components in a codebase and measures their size to identify what should be extracted first. Use when asking "how big is each module?", "what components do I have?", "which service is too large?", "analyze codebase structure", "size my monolith", or planning where to start decomposing. Do NOT use for runtime performance sizing or infrastructure capacity planning.
Understand and adhere to the project's technology stack including Laravel, PHP, React, PostgreSQL, Pest, Tailwind CSS, and all configured tools and services. Use this skill when making architectural decisions, when choosing libraries or packages, when configuring development tools, when setting up testing frameworks, when implementing authentication, when integrating third-party services, when configuring CI/CD pipelines, when setting up local development environments, or when ensuring consistency with the established tech stack across all parts of the application.
Use when the user requests diagrams, flowcharts, architecture diagrams, ER diagrams, UML / sequence / class diagrams, SysML / MBSE diagrams (block definition, internal block, requirement, parametric), BPMN business process diagrams, swimlane / cross-functional flowcharts, network topology, cloud architecture from Terraform or Kubernetes manifests, ML/DL model figures (Transformer/CNN/LSTM), mind maps, or any visualization. Also use proactively when explaining systems with 3+ components, complex data flows, or relationships that benefit from visual representation. Best suited when the diagram needs custom styling, rich shape vocabulary, swimlanes, or exportable images (PNG/SVG/PDF/JPG). Generates .drawio XML and exports locally via the native draw.io desktop CLI.
When the user wants to plan product distribution via marketplaces, app stores, or third-party platforms. Also use when the user mentions "distribution channels," "marketplace listing," "app store listing," "Figma plugin," "Chrome extension marketplace," "AWS Marketplace," "Shopify app," "GPTs store," "app distribution," or "third-party marketplace." For channel mix, use integrated-marketing.
网页设计与部署。生成精美的单页 HTML 网页(报告、落地页、数据可视化等),支持一键部署到 Cloudflare Pages。使用 Tailwind CSS + Chart.js + Font Awesome 技术栈。当用户要求制作网页、生成报告页面、创建落地页、数据可视化展示、部署网页到线上时使用。
Use when the user asks for a Databricks lakehouse architecture diagram — medallion architecture (Bronze/Silver/Gold), Delta Lake, Unity Catalog, workspace deployment, data-plane/control-plane, or any diagram built with Databricks icons. Builds with the declarative layout engine using ground-truth stencils, validates (stencils/colors/nesting/geometry), runs a render-based vision self-check. Default output is .drawio; PNG/SVG only on request.
Generate ActivityKit Live Activity infrastructure with Dynamic Island layouts, Lock Screen presentation, and push-to-update support. Use when adding Live Activities to an iOS app.
Take artwist-polyakov/sourcecraft-publisher from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.