{
  "markdown": "# ZIO Skills — Teach Your Agent to Build ZIO Applications\n\nTeaching coding agents (Claude Code, Cursor, Codex, Gemini, OpenCode) how to build and document ZIO applications.\n\nThis marketplace currently ships two plugins:\n\n- **`zio-skills`** — Build ZIO and ZIO HTTP applications (server scaffolding, OpenAPI code generation, endpoint API, …).\n- **`documentation`** — Write high-quality documentation for ZIO libraries (reference pages, how-to guides, tutorials, mdoc conventions, writing-style enforcement).\n\n## Installation\n\n### Claude Code\n\nFirst, add the marketplace, then install one or both plugins:\n\n```bash\nclaude plugin marketplace add zio/zio-skills\n\n# build apps with ZIO / ZIO HTTP\nclaude plugin install zio-skills@ziogenetics\n\n# write documentation for ZIO libraries\nclaude plugin install documentation@ziogenetics\n```\n\nThen invoke a skill in Claude Code:\n```\n/zio-http-scaffold\n/zio-http-openapi-to-endpoint\n/zio-http-endpoint-to-openapi\n/zio-http-imperative-to-declarative\n/docs-data-type-ref\n/docs-how-to-guide\n/docs-tutorial\n/docs-writing-style-judgment\n/docs-writing-style-mechanical\n```\n\n### Cursor\n\n```bash\n/add-plugin zio-skills\n```\n\n### Gemini CLI\n\n```bash\ngemini extensions install https://github.com/zio/zio-skills\n```\n\nTo update:\n\n```bash\ngemini extensions update zio-skills\n```\n\n### Codex\n\nClone the repo and symlink:\n\n```bash\ngit clone https://github.com/zio/zio-skills.git ~/.agents/skills/zio-skills\n```\n\nor user Skill Installer inside codex cli:\n\n```bash\n$skill-installer zio/zio-skills\n```\n\n### OpenCode\n\nAdd to `opencode.json`:\n```json\n{\n  \"plugin\": [\"zio-skills@git://github.com/zio/zio-skills.git\"]\n}\n```\n\n## Tools\n\n### Crossref Agent\n\n**Crossref Agent** is a Flue-based TypeScript tool that automatically discovers and creates cross-references between pages in Markdown documentation. It helps improve documentation quality, SEO, and user navigation by intelligently identifying related pages and generating link suggestions with confidence-based filtering.\n\n#### Key Features\n\n- **Automated Link Discovery** — Scans documentation to find pages that should be cross-referenced\n- **Intelligent Suggestions** — Uses Claude LLM to generate contextually relevant link suggestions with confidence scoring\n- **Security Hardening** — Built-in validation for path safety, symlink handling, and LLM output verification\n- **Flexible Execution** — Four modes: dry-run analysis, suggestions, application, and full pipeline with reporting\n- **State Management** — Persistent tracking of index state and applied suggestions for incremental updates\n\n#### Quick Start\n\n```bash\n# Install dependencies\nnpm install\n\n# Run in dry-run mode (analyze without making changes)\nnpm run crossref -- --mode=dry-run\n\n# Generate suggestions for new cross-references\nnpm run crossref -- --mode=suggest\n\n# Apply all suggestions to documentation\nnpm run crossref -- --mode=apply\n\n# Run complete pipeline with analytics report\nnpm run crossref -- --mode=full\n```\n\n#### Technologies\n\n- **Framework**: Flue (agent orchestration)\n- **Language**: TypeScript with Valibot schema validation\n- **AI Model**: Claude Haiku 4.5 for suggestions and enrichment\n- **Testing**: Vitest with 43+ test cases\n- **State Storage**: JSON-based index and suggestion tracking\n\nThat module was `writer-assistant/`, removed in this repository once its capabilities had been ported into `flowrite/`. What was ported, what was dropped and why is recorded in [flowrite/WRITER-ASSISTANT-MIGRATION.md](flowrite/WRITER-ASSISTANT-MIGRATION.md), which also carries the commands to recover any file from git history.\n\n## Skills\n\n### ZIO HTTP (`zio-skills` plugin)\n\n- **`zio-http-scaffold`** — Scaffold a minimal ZIO HTTP server and client\n- **`zio-http-openapi-to-endpoint`** — Generate Endpoint declarations from an OpenAPI spec\n- **`zio-http-endpoint-to-openapi`** — Generate OpenAPI documentation from Endpoint declarations + serve Swagger UI\n- **`zio-http-imperative-to-declarative`** — Convert imperative routes to typed Endpoint API\n\n### Documentation (`documentation` plugin)\n\nAuthoring skills:\n- **`docs-data-type-ref`** — Write a reference page for a single data type\n- **`docs-module-ref`** — Write a reference page for a module (multiple related types)\n- **`docs-how-to-guide`** — Write a goal-oriented how-to guide\n- **`docs-tutorial`** — Write a learning-oriented tutorial for newcomers\n- **`docs-document-pr`** — Generate documentation from a GitHub PR\n- **`docs-add-missing-section`** — Add a missing section to an existing reference page\n- **`docs-enrich-section`** — Add motivation and use-cases to a thin section\n\nAuthoring helpers:\n- **`docs-examples`** — Shared procedure for creating runnable companion examples\n- **`docs-research`** — Shared research procedure (find source, tests, examples, history)\n- **`docs-integrate`** — Wire a new doc page into Docusaurus navigation\n- **`docs-organize-types`** — Group types into logical sidebar categories\n\nQuality checks:\n- **`docs-writing-style-judgment`** — Judgment-based prose rules requiring language understanding (Rules J-1 to J-9)\n- **`docs-writing-style-mechanical`** — Mechanical prose rules checkable via regex (Rules M-1 to M-17) with `check-docs-style.sh` script\n- **`docs-mdoc-conventions`** — mdoc code-block modifiers and Docusaurus admonitions\n- **`docs-check-compliance`** — Audit a doc file against a rule skill\n- **`docs-verify-compliance`** — Fix compliance issues in a doc file\n- **`docs-critique`** — Review and fix an existing documentation file using a maker-critic loop\n- **`docs-find-documentation-gaps`** — Scan project for undocumented types/modules\n- **`docs-report-method-coverage`** — Check that all public members are documented\n- **`docs-data-type-list-members`** — Extract public members from a Scala type\n- **`docs-skill-retrospection`** — Improve a docs-* skill from execution feedback\n\n### Writing Style Rules Split\n\nThe `docs-writing-style` skill has been split into two focused skills to separate concerns and reduce token overhead:\n\n**Judgment-Based Rules (docs-writing-style-judgment)**\n- J-1: Person pronouns (\"we\" vs \"you\")\n- J-2: No manual line breaks in prose\n- J-3: Qualified method names (semantic cases)\n- J-4: Type name alone rule\n- J-5: No bare subheaders (quality check)\n- J-6: When to use ####\n- J-7: One concept per code block\n- J-8: Method signatures within containing type\n- J-9: Contextualized descriptions for code blocks\n\n**Mechanical Rules (docs-writing-style-mechanical)**\n- M-1 to M-17: Rules checkable via regex/bash (present tense, filler phrases, bullet capitalization, link formats, heading hierarchy, code block structure, table alignment, Scala syntax, implicit trace convention, etc.)\n\nUsage:\n- **LLM checker agent** imports only judgment skill (smaller, focused)\n- **Writer agent** imports both judgment and mechanical skills\n- **Mechanical checker script** runs independently via `check-docs-style.sh`\n- Violations reported as `[J-Rule N]` (judgment) and `[M-Rule N]` (mechanical) to avoid ambiguity\n\n## Planned Skills\n\n- Typed path & query parameters\n- Custom middleware with context injection\n- Type-safe HTTP client with EndpointExecutor\n- Server-Sent Events (SSE) streaming\n- WebSocket handlers\n- Datastar reactive UI integration\n- HTML templates with template2 DSL\n- Multipart form uploads\n- Testing with zio-http-testkit\n- Metrics & Prometheus integration\n- ZIO Streams patterns\n- ZIO Config patterns\n- And more…\n\n## Contributing\n\nSkills are curated learning resources. See [CLAUDE.md](CLAUDE.md) for contribution guidelines.\n\n## License\n\n[License](LICENSE)\n",
  "bytes": 7564,
  "sha": "4f7caf91c1c14a35abaa9dd8015fcbf24539536757be2c9bd3879d36c1518459",
  "repo_slug": "zio/zio-skills",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/plg_zio_zio_skills_ebcb2b10/readme"
}