ai-qakit 1.0.0

package/templates/.claude/commands/devkit/docs/update.md

@@ -0,0 +1,207 @@
+---
+description: Update project documentation based on codebase changes
+argument-hint: [focus-area]
+allowed-tools: Read, Write, MultiEdit, Bash, LS, Glob, Grep, WebSearch, WebFetch, Task, AskUserQuestion, Skill
+---
+
+# Docs: Update
+
+Analyze codebase and update documentation to reflect current state, strictly following `.claude/doc-templates/` structure.
+
+## Usage
+
+`@docs/update [focus-area]`
+
+## Templates Reference
+
+All updates MUST maintain the template structure from `.claude/doc-templates/`:
+
+| Template | Doc File | Sections to Update |
+|----------|----------|-------------------|
+| `project-overview-pdr.md` | `docs/project-overview-pdr.md` | Features, Requirements, Roadmap |
+| `codebase-summary.md` | `docs/codebase-summary.md` | Stats, Components, Dependencies |
+| `code-standards.md` | `docs/code-standards.md` | Conventions, Patterns |
+| `system-architecture.md` | `docs/system-architecture.md` | Components, Data Flow, APIs |
+| `technical-documents.md` | `docs/technical-documents.md` | C4 Diagrams, Deployment, Setup |
+| `development-rules.md` | `docs/development-rules.md` | Rules, Checklists |
+
+## Focus Areas
+
+| Area | Updates | Files |
+|------|---------|-------|
+| `api` | Endpoints, schemas, auth | `codebase-summary.md`, `technical-documents.md` |
+| `architecture` | Components, data flow, diagrams | `system-architecture.md`, `technical-documents.md` |
+| `setup` | Prerequisites, scripts, env vars | `technical-documents.md`, `codebase-summary.md` |
+| `standards` | Conventions, patterns, rules | `code-standards.md`, `development-rules.md` |
+| `all` | Everything | All documentation files |
+
+## Additional Requests
+
+<additional_requests>
+$ARGUMENTS
+</additional_requests>
+
+---
+
+## Process
+
+### Step 1: Read Current Documentation
+
+Load existing docs from `docs/` directory:
+- Check which template sections exist
+- Identify filled vs `{{PLACEHOLDER}}` or `// TODO:` sections
+- Note any custom additions outside template
+
+### Step 2: Analyze Codebase Changes
+
+Detect changes since last update:
+- **New Files**: Components, services, utilities
+- **Modified Files**: API changes, new functions
+- **Dependencies**: Added/removed packages
+- **Configuration**: Env vars, build settings
+- **Tests**: Coverage changes
+
+### Step 3: Compare Against Templates
+
+For each template section:
+
+1. **Check completeness** - Are all required fields filled?
+2. **Verify accuracy** - Does content match current code?
+3. **Identify gaps** - What's missing or outdated?
+
+### Step 4: Update Documentation
+
+Apply changes while preserving template structure:
+
+```markdown
+# Template Structure MUST Be Preserved
+
+## Section from Template
+| Field | Previous Value | Updated Value |
+|-------|----------------|---------------|
+| {{TECH_STACK}} | React 17 | React 18 |
+| {{DATABASE}} | PostgreSQL 13 | PostgreSQL 15 |
+```
+
+### Step 5: Update Metadata
+
+Update revision information in each file:
+
+```markdown
+## Revision History
+
+| Version | Date | Author | Changes |
+|---------|------|--------|---------|
+| 1.1.0 | 2025-01-15 | AI | Added new API endpoints |
+| 1.0.0 | 2025-01-01 | AI | Initial documentation |
+```
+
+---
+
+## Update Rules
+
+### MUST Preserve
+
+- Template section structure
+- Section ordering from template
+- Table formats and headers
+- Cross-reference links
+
+### MUST Update
+
+- Version numbers and dates
+- Statistics (file counts, line counts)
+- Dependency versions
+- API endpoint lists
+- Component descriptions
+
+### MUST Fill
+
+- All remaining `{{PLACEHOLDER}}` values with actual content
+- All remaining `// TODO:` markers with project-specific information
+
+### MUST NOT
+
+- Remove template sections (mark as N/A if not applicable)
+- Change section headings
+- Add unstructured content outside template sections
+- Leave `{{PLACEHOLDER}}` unfilled when info is available
+- Leave `// TODO:` unfilled when info can be detected
+
+### TODO Handling
+
+For sections that need manual input:
+
+```markdown
+## C4 Diagrams
+
+// TODO: Update System Context diagram with new external service
+// TODO: Add new component to Container diagram
+
+### Current Diagrams
+[existing content]
+```
+
+---
+
+## Delegation
+
+Use `docs-manager` agent to analyze the codebase and execute the update process.
+
+**Report Protocol**: Follow ./.claude/CLAUDE.md "Sub-Agent Report Generation" protocol before spawning subagents.
+
+---
+
+## Output
+
+```
+📝 DOCS UPDATED (TEMPLATE-COMPLIANT)
+════════════════════════════════════════
+
+CHANGES DETECTED:
+• 5 new API endpoints
+• 2 dependency updates
+• 1 new component
+• 3 config changes
+
+UPDATED FILES:
+✅ codebase-summary.md
+   ├── Quick Stats: Updated file counts
+   ├── Tech Stack: React 17 → 18
+   └── Core Components: Added PaymentService
+
+✅ technical-documents.md
+   ├── System Containers: Added Redis cache
+   └── Development Setup: New env variables
+
+✅ code-standards.md
+   └── Conventions: Added new patterns
+
+⏭️ system-architecture.md (no changes needed)
+⏭️ project-overview-pdr.md (no changes needed)
+
+NEW TODO MARKERS: 2
+• C4 diagram update required
+• New external system documentation
+
+TEMPLATE COMPLIANCE: ✅ 100%
+════════════════════════════════════════
+```
+
+---
+
+## Validation Checklist
+
+After update:
+
+- [ ] All sections maintain template structure
+- [ ] No orphaned `{{PLACEHOLDER}}` values
+- [ ] No orphaned `// TODO:` values (when info available)
+- [ ] Version/date updated in Revision History
+- [ ] Statistics reflect current codebase
+- [ ] Links between docs are valid
+- [ ] TODO markers added for manual tasks
+- [ ] No content outside template sections
+- [ ] C4 diagrams creation done base on project context.
+
+**IMPORTANT**: Do not start implementing until planning is complete.

package/templates/.claude/commands/devkit/fix/fast.md

@@ -0,0 +1,22 @@
+---
+description: Analyze and fix small issues [FAST]
+argument-hint: [issues]
+allowed-tools: Read, Write, MultiEdit, Bash, LS, Glob, Grep, WebSearch, WebFetch, Task, AskUserQuestion
+---
+
+**Report Protocol**: Follow ./.claude/CLAUDE.md "Sub-Agent Report Generation" protocol before spawning subagents.
+
+Analyze the skills catalog and activate the skills that are needed for the task during the process.
+
+## Mission
+**Think hard** to analyze and fix these issues:
+<issues>$ARGUMENTS</issues>
+
+## Workflow
+1. If the user provides a screenshots or videos, use `ai-multimodal` skill to describe as detailed as possible the issue, make sure developers can predict the root causes easily based on the description.
+2. Use `debugger` subagent to find the root cause of the issues and report back to main agent.
+3. Use `problem-solving` skills to tackle the issues.
+4. Start implementing the fix based the reports and solutions.
+5. Use `tester` agent to test the fix and make sure it works, then report back to main agent.
+6. If there are issues or failed tests, repeat from step 2.
+7. After finishing, respond back to user with a summary of the changes and explain everything briefly, guide user to get started and suggest the next steps.

package/templates/.claude/commands/devkit/fix/hard.md

@@ -0,0 +1,44 @@
+---
+description: Use subagents to plan and fix hard issues
+argument-hint: [issues]
+allowed-tools: Read, Write, MultiEdit, Bash, LS, Glob, Grep, WebSearch, WebFetch, Task, AskUserQuestion
+---
+
+**Report Protocol**: Follow ./.claude/CLAUDE.md "Sub-Agent Report Generation" protocol before spawning subagents.
+
+**Ultrathink** to plan & start fixing these issues follow the Orchestration Protocol, Core Responsibilities, Subagents Team and Development Rules: 
+<issues>$ARGUMENTS</issues>
+
+## Workflow:
+
+If the user provides a screenshots or videos, use `ai-multimodal` skill to describe as detailed as possible the issue, make sure developers can predict the root causes easily based on the description.
+
+Use `sequential-thinking` skill to break complex problems into sequential thought steps.
+Use `problem-solving` skills to tackle the issues.
+Analyze the skills catalog and activate other skills that are needed for the task during the process.
+
+1. Use `debugger` subagent to find the root cause of the issues and report back to main agent.
+2. Use `researcher` subagent to research quickly about the root causes on the internet (if needed) and report back to main agent.
+3. Use `planner` subagent to create an implementation plan based on the reports, then report back to main agent.
+4. Then use general agent (main agent) to implement the plan step by step.
+5. Use `tester` subagent to write test cases and run the tests, make sure it works, then report back to main agent.
+6. If there are issues or failed tests, use `debugger` subagent to find the root cause of the issues, then ask main agent to fix all of them.
+7. Repeat the process until all tests pass or no more issues are reported.
+8. After finishing, delegate to `code-reviewer` subagent to review code. 
+   If there are critical issues, ask main agent to improve the code and test everything again.
+   Report back to user with a summary of the changes and explain everything briefly, use `AskUserQuestion` tool to ask user to review the changes and approve them.
+9. Project Management & Documentation:
+  **If user approves the changes:** Use `project-manager` subagents in parallel to update the project progress and documentation:
+    * Use `project-manager` subagent to update the project progress and task status in the given plan file.
+    * Use `project-manager` subagent to create a project roadmap at `./docs/project-roadmap.md` file.
+    * **IMPORTANT:** Sacrifice grammar for the sake of concision when writing outputs.
+  **If user rejects the changes:** Use `AskUserQuestion` tool to ask user to explain the issues and ask main agent to fix all of them and repeat the process.
+1.  Final Report:
+  * Report back to user with a summary of the changes and explain everything briefly, guide user to get started and suggest the next steps.
+  - **IMPORTANT:** Sacrifice grammar for the sake of concision when writing reports.
+  - **IMPORTANT:** In reports, list any unresolved questions at the end, if any.
+
+**REMEMBER**:
+- You can always generate images with `ai-multimodal` skills on the fly for visual assets.
+- You always read and analyze the generated assets with `ai-multimodal` skills to verify they meet requirements.
+- For image editing (removing background, adjusting, cropping), use `ImageMagick` skill or similar tools as needed.

package/templates/.claude/commands/devkit/fix.md

@@ -0,0 +1,16 @@
+---
+description: Analyze and fix small issues
+argument-hint: [issues]
+allowed-tools: Read, Write, MultiEdit, Bash, LS, Glob, Grep, WebSearch, WebFetch, Task, AskUserQuestion, Skill
+---
+
+**Report Protocol**: Follow ./.claude/CLAUDE.md "Sub-Agent Report Generation" protocol before spawning subagents.
+
+Else: 
+- Analyze the issues and ask for more details if needed.
+- Decide to use `/fix:fast` or `/fix:hard` SlashCommands based on the complexity.
+- Execute SlashCommand: `/fix:fast <detailed-instructions-prompt>` or `/fix:hard <detailed-instructions-prompt>`
+
+## Notes
+- `detailed-description` = enhanced prompt describing issue in detail
+- If unclear, use `AskUserQuestion` tool to ask user for clarification before routing