Knowledge systematization engine โ 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.
From cmnpx claudepluginhub tody-agent/codymaster --plugin cmThis skill uses the workspace's default tool permissions.
README.mdindex.htmlpackage-lock.jsonpackage.jsonprompts/analysis.mdprompts/api-reference.mdprompts/architecture.mdprompts/data-flow.mdprompts/database.mdprompts/deployment.mdprompts/flows.mdprompts/jtbd.mdprompts/personas.mdprompts/sop-modules.mdscripts/doc-gen.shscripts/dockit-dashboard.shscripts/dockit-runner.shscripts/dockit-task.shskills/analyze-codebase.mdskills/api-reference.mdProvides UI/UX resources: 50+ styles, color palettes, font pairings, guidelines, charts for web/mobile across React, Next.js, Vue, Svelte, Tailwind, React Native, Flutter. Aids planning, building, reviewing interfaces.
Fetches up-to-date documentation from Context7 for libraries and frameworks like React, Next.js, Prisma. Use for setup questions, API references, and code examples.
Implements distributed tracing with Jaeger/Tempo for microservices, including Kubernetes/Docker setup and OpenTelemetry instrumentation (Python/Flask). Use for debugging latency, dependencies, and request flows.
A professional knowledge systematization engine powered by codebase analysis and UX design principles. One source scan = one complete knowledge base โ 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.
/DocKit Master| Type | Skill File | Description |
|---|---|---|
| knowledge | skills/persona-builder.md + skills/jtbd-analyzer.md + skills/flow-mapper.md (files pending) | Personas, JTBD, Process Flows โ knowledge foundation |
| tech | skills/tech-docs.md | Architecture, database, deployment, data flow |
| sop | skills/sop-guide.md | Step-by-step user guides (enriched with knowledge) |
| api | skills/api-reference.md | API endpoint reference with examples |
| all | All above | Full knowledge base + documentation suite |
| Support Skill | File | Purpose |
|---|---|---|
| SEO Checklist | skills/seo-checklist.md | Per-page SEO audit (title, meta, headings, robots) |
| Content Writing | skills/content-writing.md | SEO copywriting, keywords, active voice, FAQ |
| LLM Optimization | skills/llm-optimization.md | AI-readable structure, NotebookLM-friendly |
| Format | Workflow | Description |
|---|---|---|
| markdown | workflows/export-markdown.md | Plain .md files in docs/ folder |
| vitepress | workflows/setup-vitepress.md | Premium VitePress static site (default) โ built-in Mermaid, search, dark mode |
CRITICAL: Ask ALL questions in ONE message. Do NOT ask one at a time. Present the following intake form to the user, using this ๐ DocKit Master โ Configuration
Please answer the following questions so I can automatically create an execution plan:
| # | Question | Options | Default |
|---|---|---|---|
| 1 | ๐ Document type? | knowledge ยท tech ยท sop ยท api ยท all | all |
| 2 | ๐จ Output format? | markdown (plain) ยท vitepress (premium site) | vitepress |
| 3 | ๐ Code scan scope? | full (entire project) ยท focused (specific folder/feature) | full |
| 4 | ๐ฏ Focus area? (only if focused) | Folder name, module, or specific feature | โ |
| 5 | ๐ Writing language? | Auto-detect from chat language (see below) | auto-detect |
| 6 | ๐ Add multi-language? | yes (add English + source language) ยท no | no |
| 7 | ๐น Record video demo? | yes (record browser walkthrough) ยท no | no |
| 8 | ๐ Project path? | (absolute path) | current workspace |
| 9 | ๐ SEO optimization? | yes (SEO frontmatter + checklist + sitemap) ยท no | yes |
| 10 | ๐ค Optimize for AI/LLM? | yes (AI-readable + NotebookLM sitemap) ยท no | yes |
You can answer briefly, e.g.: "all, vitepress, full, yes, no, yes, yes"
๐ Smart language rules:
vizhjaenyes): Automatically add English (en) as secondary language
vi + enzh + enAfter receiving answers, immediately create an execution plan (do NOT ask more questions).
Map the answers to this execution config:
DOC_TYPE = [knowledge | tech | sop | api | all]
FORMAT = [markdown | vitepress]
SCOPE = [full | focused]
FOCUS_TARGET = [directory/module name if focused, else null]
LANGUAGE = [vi | en | vi+en]
I18N = [yes | no] (only relevant for vitepress)
RECORD = [yes | no]
PROJECT_PATH = [absolute path]
SEO = [yes | no] (default: yes)
LLM_OPTIMIZE = [yes | no] (default: yes)
Then present the plan to user as a checklist artifact, like:
## ๐ Execution Plan
- [ ] Scan code: [full/focused โ target]
- [ ] Generate documents: [type] in [language]
- [ ] Export format: [markdown/vitepress]
- [ ] [If vitepress + i18n] Configure multi-language
- [ ] [If record] Record video walkthrough
- [ ] [If seo] Run SEO checklist + generate sitemap
- [ ] [If llm_optimize] Apply LLM optimization rules
- [ ] Review and deliver
After presenting the plan โ proceed to Step 2 immediately (auto-execute). Do NOT wait for approval unless the plan has ambiguity.
Read and follow skills/analyze-codebase.md in this directory.
Output: structured analysis saved to docs/analysis.md (NOT _analysis.md) including:
MANDATORY โ Read skills/content-guidelines.md before generating any content.
Key rules to enforce:
.md file must have title, description, keywords, robots<details> for advanced content:::tip, :::info, :::warning, :::danger for callouts:::code-group for multi-platform examplesIf SEO = yes: Read skills/content-writing.md for:
If LLM_OPTIMIZE = yes: Read skills/llm-optimization.md for:
Based on the chosen type, read and follow the corresponding skill file:
knowledge โ Run 3 skills sequentially:
skills/persona-builder.md โ docs/personas/ (Buyer & User Personas)skills/jtbd-analyzer.md โ docs/jtbd/ (JTBD Canvases)skills/flow-mapper.md โ docs/flows/ (Workflow, Sequence, Lifecycle, Journey)tech โ Read skills/tech-docs.md, generate:
docs/architecture.md โ System architecture + ADRdocs/database.md โ Database schema & data modeldocs/deployment.md โ Deployment & infrastructuredocs/data-flow.md โ Data flow diagramssop โ Auto-run knowledge first if not yet generated, then:
skills/sop-guide.md, generate:docs/sop/ โ One .md per feature/moduleapi โ Read skills/api-reference.md, generate:
docs/api/ โ Organized by resourceall โ Run knowledge โ tech โ sop โ api sequentially
Based on the chosen format, read and follow the corresponding workflow:
markdown โ Read workflows/export-markdown.md
docs/README.md as indexvitepress โ Read workflows/setup-vitepress.md
Read and follow workflows/generate-sitemap.md:
sitemap config option. Generate robots.txt, extract sitemap-urls.txtdocs/sitemap.md (link index) + docs/sitemap-urls.txtRead skills/seo-checklist.md and audit every generated page:
Present to user:
If generated docs > 30 files, also suggest:
๐ก **Pro Tip: Deep Search**
The documentation set just created has [X] files. You can index them using
[qmd](https://github.com/tobi/qmd) for semantic search by AI
across all future sessions:
\`\`\`bash
npm install -g @tobilu/qmd
qmd collection add ./docs --name project-docs
qmd context add qmd://project-docs "Project documentation for [project-name]"
qmd embed
\`\`\`
See also: `cm-deep-search` skill.
For a fast interactive experience, users can run the doc generation script from the skill root:
# Run from the cm-dockit skill directory
bash scripts/doc-gen.sh
Note: The
scripts/directory anddoc-gen.shscript need to be created. For now, trigger this skill by invokingcm-dockitdirectly via the AI assistant.
| UX Law | Application |
|---|---|
| Hick's Law | โค7 TOC items, progressive disclosure for advanced content |
| Miller's Law | Information chunked into groups of 5-9 |
| Doherty Threshold | Tables for structured data, scannable summaries |
| Jakob's Law | Standard doc layout (sidebar + content + TOC) |
| Fitts's Law | Touch-friendly navbar links (โฅ44px) |
| WCAG 2.1 AA | Focus-visible rings, high contrast, reduced motion |
(file_path:line_number)<details> for troubleshooting (progressive disclosure)title, descriptionnpx vitepress build without errorsrobots: "index, follow" unless page is internal/draftsitemap-urls.txt generated for NotebookLM importIf you are an AI agent asked to modify or upgrade this skill (CM DocKit):
cm-dockit skill directory by executing $ npm run test:gate or $ vitest. Do NOT claim "task completed" unless tests pass.templates/vitepress-premium, ensure the frontend test suite (tests/frontend.test.ts) still works.[project_root]/docs/ content into docs-site/. Always rely on srcDir: '../docs' in config.mts.