dokhak

Continue writing multiple sections. Uses researcher->writer->reviewer pipeline for each section. Supports domain-adaptive content generation (technology, history, science, arts, general).

Diagnose project structure health and interactively fix issues. Checks required files, cross-file consistency, and completion status sync.

Initialize a new learning resource project through interactive interview. Creates plan.md, task.md, persona.md, project-context.md, interview-data.md, and CLAUDE.md. Supports multiple domains: technology, history, science, arts, and general.

Show project progress and statistics. Displays completion percentage, Part/Chapter breakdown, and next pending tasks.

Write the next document section using researcher->writer->reviewer pipeline. Identifies next incomplete task, gathers research, writes document, and reviews quality. Supports domain-adaptive content generation (technology, history, science, arts, general).

Conducts conversational interviews to create learner profiles. Use PROACTIVELY when /init is invoked. Outputs persona.md, interview-data.md and returns project metadata.

Collects and structures web research results for learning resource projects. Use proactively when: gathering official documentation URLs, finding learning paths/roadmaps, collecting core concepts for a topic, or starting a new self-learning project. Adapts search strategy based on domain (technology, history, science, arts, general). Returns structured XML+Markdown summary to minimize context usage.

Gathers and synthesizes information for learning document writing. Use PROACTIVELY when /write or /continue identifies next section to write. Adapts search strategy based on domain (technology, history, science, arts, general). Returns confirmation message only.

Reviews written document for quality and consistency. Use PROACTIVELY when writer completes a document section. Checks page count, writer identity alignment, adjacent section coherence, code policy, and terminology. Returns structured XML feedback with domain-adaptive criteria.

Designs learning resource structure (Part/Chapter/Section hierarchy) and creates plan.md/task.md files. Use when: creating plan.md structure, allocating pages per section, designing curriculum flow, or setting up session-based task distribution. Automatically loads project-scaffolder skill for templates.

Writes learning documents based on research results and project context. Use PROACTIVELY when research has been gathered and document needs to be written. Adapts writing style based on domain. Writes files directly, returns only completion summary.

Domain-specific configuration profiles for learning resource creation. Defines search strategies, special fields, terminology policies, and content structures for different academic domains: technology, history, science, arts, and general. Use when researcher or writer agents need domain-adapted behavior.

Resources for conversational interviews to create learner profiles. Used by project-interviewer agent during /init.

Creates plan.md, task.md, persona.md, project-context.md, and CLAUDE.md for new self-learning resource projects. Use when: (1) /init command is invoked, (2) setting up a new tutorial/guide/documentation project, (3) structure-designer agent needs templates for learning resource structure design. Provides hierarchical Part/Chapter/Section templates with page allocation.

Research file storage conventions and templates for dokhak agents. Use when: (1) saving research results from research-collector or researcher agents, (2) reading cached research files, (3) checking if research exists for a section. Provides directory structure, file format templates, and naming conventions.