$npx -y skills add tody-agent/codymaster --skill cm-dockitKnowledge systematization engine — analyze codebases, generate Personas, JTBD, Process Flows, technical docs, SOP user guides, API references. Output as Markdown or VitePress Premium. SEO-optimized, AI/LLM-readable. One scan = complete knowledge base.
| 1 | # CM DocKit: Knowledge Systematization Engine |
| 2 | |
| 3 | A professional knowledge systematization engine powered by codebase analysis and UX design principles. **One source scan = one complete knowledge base** — Personas, JTBD, Process Flows, Technical Docs, SOPs, API Reference. Supports plain Markdown output or a premium VitePress site. Includes SEO optimization, sitemap generation, and AI/LLM-readable content. |
| 4 | |
| 5 | ## When to Activate |
| 6 | |
| 7 | - User asks to "create documentation", "generate docs" |
| 8 | - User mentions "SOP", "user guide", "manual" |
| 9 | - User wants technical docs from a codebase |
| 10 | - User runs `/DocKit Master` |
| 11 | |
| 12 | ## Document Types |
| 13 | |
| 14 | | Type | Skill File | Description | |
| 15 | |------|-----------|-------------| |
| 16 | | **knowledge** | `skills/persona-builder.md` + `skills/jtbd-analyzer.md` + `skills/flow-mapper.md` *(files pending)* | Personas, JTBD, Process Flows — knowledge foundation | |
| 17 | | **tech** | `skills/tech-docs.md` | Architecture, database, deployment, data flow | |
| 18 | | **sop** | `skills/sop-guide.md` | Step-by-step user guides (enriched with knowledge) | |
| 19 | | **api** | `skills/api-reference.md` | API endpoint reference with examples | |
| 20 | | **all** | All above | Full knowledge base + documentation suite | |
| 21 | |
| 22 | | Support Skill | File | Purpose | |
| 23 | |--------------|------|---------| |
| 24 | | **SEO Checklist** | `skills/seo-checklist.md` | Per-page SEO audit (title, meta, headings, robots) | |
| 25 | | **Content Writing** | `skills/content-writing.md` | SEO copywriting, keywords, active voice, FAQ | |
| 26 | | **LLM Optimization** | `skills/llm-optimization.md` | AI-readable structure, NotebookLM-friendly | |
| 27 | |
| 28 | ## Output Formats |
| 29 | |
| 30 | | Format | Workflow | Description | |
| 31 | |--------|---------|-------------| |
| 32 | | **markdown** | `workflows/export-markdown.md` | Plain `.md` files in `docs/` folder | |
| 33 | | **vitepress** | `workflows/setup-vitepress.md` | Premium VitePress static site (**default**) — built-in Mermaid, search, dark mode | |
| 34 | |
| 35 | ## Procedure |
| 36 | |
| 37 | ### Step 1: Gather Input (Single Consolidated Prompt) |
| 38 | |
| 39 | **CRITICAL:** Ask ALL questions in ONE message. Do NOT ask one at a time. |
| 40 | Present the following intake form to the user, using this **📚 DocKit Master — Configuration** |
| 41 | |
| 42 | Please answer the following questions so I can automatically create an execution plan: |
| 43 | |
| 44 | | # | Question | Options | Default | |
| 45 | |---|---------|---------|--------| |
| 46 | | 1 | **📑 Document type?** | `knowledge` · `tech` · `sop` · `api` · `all` | `all` | |
| 47 | | 2 | **🎨 Output format?** | `markdown` (plain) · `vitepress` (premium site) | `vitepress` | |
| 48 | | 3 | **📂 Code scan scope?** | `full` (entire project) · `focused` (specific folder/feature) | `full` | |
| 49 | | 4 | **🎯 Focus area?** *(only if `focused`)* | Folder name, module, or specific feature | — | |
| 50 | | 5 | **🌏 Writing language?** | Auto-detect from chat language *(see below)* | auto-detect | |
| 51 | | 6 | **🌐 Add multi-language?** | `yes` (add English + source language) · `no` | `no` | |
| 52 | | 7 | **📹 Record video demo?** | `yes` (record browser walkthrough) · `no` | `no` | |
| 53 | | 8 | **📁 Project path?** | *(absolute path)* | current workspace | |
| 54 | | 9 | **🔍 SEO optimization?** | `yes` (SEO frontmatter + checklist + sitemap) · `no` | `yes` | |
| 55 | | 10 | **🤖 Optimize for AI/LLM?** | `yes` (AI-readable + NotebookLM sitemap) · `no` | `yes` | |
| 56 | |
| 57 | *You can answer briefly, e.g.: "all, vitepress, full, yes, no, yes, yes"* |
| 58 | |
| 59 | **🌏 Smart language rules:** |
| 60 | |
| 61 | 1. **Auto-detect**: Determine default language from the user's chat language |
| 62 | - User chats in Vietnamese → default `vi` |
| 63 | - User chats in Chinese → default `zh` |
| 64 | - User chats in Japanese → default `ja` |
| 65 | - User chats in English → default `en` |
| 66 | - *(Applies similarly for any other language)* |
| 67 | 2. **Multi-language (`yes`)**: Automatically add English (`en`) as secondary language |
| 68 | - Example: Vietnamese user + multi-language → `vi` + `en` |
| 69 | - Example: Chinese user + multi-language → `zh` + `en` |
| 70 | - If user already chats in English + multi-language → ask which secondary language |
| 71 | 3. **Override**: User can override by specifying explicitly, e.g.: \"write in Japanese\" |
| 72 | |
| 73 | --- |
| 74 | |
| 75 | ### Step 1b: Auto-Generate Execution Plan |
| 76 | |
| 77 | After receiving answers, **immediately create an execution plan** (do NOT ask more questions). |
| 78 | |
| 79 | Map the answers to this execution config: |
| 80 | |
| 81 | ``` |
| 82 | DOC_TYPE = [knowledge | tech | sop | api | all] |
| 83 | FORMAT = [markdown | vitepress] |
| 84 | SCOPE = [full | focused] |
| 85 | FOCUS_TARGET = [directory/module name if focused, else null] |
| 86 | LANGUAGE = [vi | en | vi+en] |
| 87 | I18N = [yes | no] (only relevant for vitepress) |
| 88 | RECORD = [yes | no] |
| 89 | PROJECT_PATH = [absolute path] |
| 90 | SEO = [yes | no] (default: yes) |
| 91 | LLM_OPTIMIZE = [yes | no] (default: yes) |
| 92 | ``` |
| 93 | |
| 94 | Then present the plan to user as a checklist artifact, like: |
| 95 | |
| 96 | ```markdown |
| 97 | ## 🚀 Execution Plan |
| 98 | |
| 99 | - [ ] Scan code: [full/focused → |