GAIK Solution Configuration Wizard. Guides the user from a natural-language use-case description to a validated executable blueprint (JSON), a Mermaid workflow diagram, a standards-based BPMN 2.0 visual blueprint, a runnable PoC, and a use-case documentation suite. Collects the complete requirement set (with a completeness gate), reasons about each component's behaviour-changing options, selects GAIK components, generates and validates the blueprint, and saves all outputs to a user-chosen directory.
GAIK toolkit overview and reference. Use when needing context on GAIK components (extractors, parsers, transcribers, RAG, TTS, classifiers, pipelines), the repository structure, configuration pattern, environment variables, building-block API tables, the documentation update map, or the demo app and docs website setup. For CREATING a new component package use build-software-component; for ADDING EXAMPLES and running the canonical publish flow (docs → demo app → PyPI tag) use gaik-add-examples. Covers: structured data extraction, document parsing, audio transcription (Whisper/local), transcript enhancement, text-to-speech, RAG pipelines (pgvector/Chroma), document classification, end-to-end pipelines.
Audits the GAIK Solution Wizard's component registry, reference cards, and SKILL.md guidance against the installed gaik package, then proposes and applies the updates needed to keep them in sync. Use after changing gaik components (new component, renamed constructor/method, changed options, removed component, new install extra, new module) or after bumping the gaik version. Runs a deterministic introspection scan, classifies each finding, and edits only after you approve a change table.
Creates evaluation documentation for a GAIK component in both locations: evaluation_layer/eval_methods/{component}_eval/ (README + optional script stubs) and guidance_layer/website/content/docs/evaluation-layer/{component}-eval.mdx (full user-facing page). Also updates index.mdx and meta.json to register the new page.
Creates a use-case description page under guidance_layer/website/content/docs/use-cases/ following the established GAIK format (business layer → strategy → no-code → code-based → components → evaluation → resources). Accepts user-provided context and marks any missing sections as Coming Soon. Updates meta.json to register the new page.
Adds or updates working code examples for GAIK toolkit components and pipelines in implementation_layer/examples/. Use when adding a new example, demonstrating a feature, creating a usage sample, or showing how a building block or pipeline works. After the example is in place, offers optional follow-ups: update API docs (guidance_layer/docs/), update the Fumadocs website (guidance_layer/website/content/docs/), expose the feature in the demo app (toolkit_demo_app/api/routers + UI), and push a PyPI release tag. Covers software_components (extractor, parsers, transcriber, RAG, classifier, TTS, enhance_transcript, validators (LLMJudge / panel / pairwise / calibration), evaluators (ExtractionEvaluator, RAGEvaluator, BatchEvaluationRunner), form_understander, observability) and software_modules (AudioToStructuredData, DocumentsToStructuredData, RAGWorkflow, MultiSourceReportGenerator). Not for creating a brand-new component package — use build-software-component for that.
GAIK Solution Configuration Wizard. Guides the user from a natural-language use-case description to a validated executable blueprint (JSON), a Mermaid workflow diagram, a standards-based BPMN 2.0 visual blueprint, a runnable PoC, and a use-case documentation suite. Collects the complete requirement set with a completeness gate, reasons about each component's behaviour-changing options, selects GAIK components, and validates everything.
Creates a new GAIK software component as an installable Python package. Accepts context from URLs, external codebases, or plain descriptions. Produces an implementation plan for user review, then executes the plan: creates component files, updates pyproject.toml, installs the package, and verifies with import smoke tests. For the full release-ready flow (more examples, docs, demo app integration, PyPI release tag) delegates to the gaik-add-examples skill instead of duplicating that workflow. Use when the user asks to create, build, or add a new GAIK software component, wrap a library, or turn a codebase or API into a reusable installable package.