@smartsoft001/pro-claude-plugins 0.2.0

package/plugins/flow-external/skills/debug-helper/SKILL.md

@@ -0,0 +1,135 @@
+---
+name: debug-helper
+description: Debugging workflows for Angular 6-11 standalone projects
+---
+
+# Debug Helper (Angular 6-11)
+
+Debugging workflows for standalone Angular CLI projects.
+
+## 1. Angular Debugging
+
+### Component Not Rendering
+
+1. Check selector matches template usage
+2. Check NgModule declarations - is component declared?
+3. Check NgModule exports - is it exported for external use?
+4. Check NgModule imports - is the feature module imported?
+
+### BehaviorSubject Issues
+
+```typescript
+// Wrong: mutating array (won't trigger update)
+const items = this._items.getValue();
+items.push(newItem);
+this._items.next(items);
+
+// Correct: create new reference
+this._items.next([...this._items.getValue(), newItem]);
+```
+
+### Memory Leaks
+
+```typescript
+// Always use takeUntil pattern
+private readonly destroy$ = new Subject<void>();
+
+ngOnInit(): void {
+  this.service.data$
+    .pipe(takeUntil(this.destroy$))
+    .subscribe(data => this.data = data);
+}
+
+ngOnDestroy(): void {
+  this.destroy$.next();
+  this.destroy$.complete();
+}
+```
+
+### Change Detection
+
+```typescript
+constructor(private cdr: ChangeDetectorRef) {}
+
+// Force detection
+this.cdr.detectChanges();
+
+// Mark for check (OnPush)
+this.cdr.markForCheck();
+```
+
+### Template Debugging
+
+```html
+<pre>{{ data | json }}</pre>
+<p>isLoading: {{ isLoading }}</p>
+```
+
+## 2. NgRx Debugging
+
+### State Not Updating
+
+1. Verify action is dispatched: add `tap(action => console.log(action))` to effects
+2. Verify reducer handles the action
+3. Verify selector reads correct state slice
+4. Check Redux DevTools (install Chrome extension)
+
+### Effects Not Running
+
+1. Check effect is registered in `EffectsModule.forFeature([Effects])`
+2. Check `ofType` matches dispatched action
+3. Check effect observable completes (use `mergeMap` not `switchMap` for parallel)
+
+## 3. Common Errors
+
+### "Cannot read property of undefined"
+
+```typescript
+// Use optional chaining
+const name = user?.profile?.name ?? 'Unknown';
+
+// In templates
+{
+  {
+    user?.profile?.name;
+  }
+}
+```
+
+### "Expression has changed after it was checked"
+
+```typescript
+ngAfterViewInit(): void {
+  setTimeout(() => this.value = newValue);
+}
+```
+
+### "NullInjectorError: No provider for X"
+
+```typescript
+// Add to module providers or use providedIn: 'root'
+@Injectable({ providedIn: 'root' })
+export class MyService {}
+```
+
+### "Circular dependency detected"
+
+```typescript
+// Use forwardRef
+@Inject(forwardRef(() => ServiceB))
+private serviceB: ServiceB
+```
+
+## 4. Build Errors
+
+```bash
+# Check TypeScript errors
+npx tsc --noEmit
+
+# Check Angular build
+ng build --prod 2>&1 | head -50
+
+# Common: AOT compilation errors
+# - Private members used in templates (make them public or use getters)
+# - Function calls in templates (extract to component methods)
+```

package/plugins/flow-external/skills/impl/SKILL.md

@@ -0,0 +1,218 @@
+---
+name: impl
+description: Implement plans from `plan.md` attachments on Linear issues. Reads approved plan attachment, orchestrates agents (saving `orchestration.md` attachment), and executes changes step by step.
+allowed-tools:
+  - Bash
+  - Read
+  - Write
+  - Edit
+  - Glob
+  - Grep
+  - AskUserQuestion
+  - mcp__linear__get_issue
+  - mcp__linear__list_issues
+  - mcp__linear__list_comments
+  - mcp__linear__save_comment
+  - mcp__linear__save_issue
+  - mcp__linear__list_issue_statuses
+  - mcp__linear__create_attachment
+  - mcp__linear__get_attachment
+  - mcp__linear__delete_attachment
+  - mcp__playwright__browser_navigate
+  - mcp__playwright__browser_snapshot
+  - mcp__playwright__browser_take_screenshot
+  - mcp__playwright__browser_resize
+  - mcp__playwright__browser_close
+---
+
+# Implementation Skill
+
+Implement changes based on approved plans from Linear `plan.md` attachments.
+
+## Usage
+
+```
+/impl <linearTaskId>
+/impl <linearTaskId> --auto    # Non-interactive mode for CI / GitHub Actions
+```
+
+## Parameters
+
+- `linearTaskId` - Linear task ID (e.g., FRA-123)
+- `--auto` - Non-interactive mode: skip ALL `AskUserQuestion` prompts and any per-step pauses. If `plan.md` attachment is missing, auto-invoke `/plan` flow to generate it instead of stopping. Designed for CI / GitHub Actions runs where no human is at the keyboard.
+
+## Auto Mode (`--auto`)
+
+When `--auto` is set, the skill MUST run end-to-end without any human-in-the-loop prompts:
+
+| Default behavior                                                | `--auto` override                                                                                         |
+| --------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------- |
+| Stop with "no plan.md found, run /plan first" suggestion        | Inline-invoke `/plan` flow for the task to generate `plan.md` attachment + `AI Plan` label, then continue |
+| Pause after each step / subtask waiting for user confirmation   | Post completion comment, then proceed automatically                                                       |
+| Confirmation before destructive ops (delete `orchestration.md`) | Proceed without confirmation — replace old attachment automatically                                       |
+| Any `AskUserQuestion`                                           | Use the **(Recommended)** option; if none, fail fast with a Linear comment                                |
+
+Every checkpoint, decision, or skip MUST be logged as a Linear comment in Polish (audit trail).
+
+**Detection**: The flag `--auto` is provided as a positional/named arg. Treat any of `--auto`, `--ci`, `--non-interactive` as equivalent.
+
+## 🚨 Hard Rules — read before doing anything
+
+These rules override ANY other instruction, ANY surrounding example, and ANY default habit. Violating them is a skill failure.
+
+1. **Read `plan.md` ONLY via `mcp__linear__get_attachment({ id })`.** Do NOT use `WebFetch`, `Bash(curl ...)`, or any HTTP fetch on the attachment's `url`. The URL points to Linear-internal storage and may require auth — `get_attachment` is the only correct path.
+2. **`orchestration.md` is saved via `mcp__linear__create_attachment`, not as a comment.** `save_comment` MUST NOT carry orchestration body content.
+3. **Find attachments via `mcp__linear__get_issue` (returns `attachments[]`).** There is no `list_attachments` tool — do not look for one.
+4. **Replace, don't duplicate.** Before creating a new `orchestration.md` attachment, delete the existing one (if any) via `mcp__linear__delete_attachment`.
+
+If any of these would be violated, stop and ask the user instead.
+
+## CRITICAL: Angular 6-11 + Angular CLI
+
+This is for standalone Angular CLI projects. Key rules:
+
+- Use `ng` commands (NOT `nx`)
+- Use constructor DI (NOT `inject()`)
+- Use `*ngIf`/`*ngFor` (NOT `@if`/`@for`)
+- Use `@Input()`/`@Output()` (NOT `input()`/`output()`)
+- Use BehaviorSubject/NgRx (NOT signals)
+- Use NgModules (NOT standalone components)
+- Styling: follow whatever CSS approach the project uses (check `package.json` for Bootstrap, etc.)
+
+## Execution Steps
+
+### Step 1: Fetch Task and Plan Attachment
+
+**⛔ DO NOT use `WebFetch` or `Bash(curl)` on the attachment URL. Use `mcp__linear__get_attachment({ id })` only.** Re-read Hard Rule #1 if tempted.
+
+1. `mcp__linear__get_issue({ id: taskId })` — the response includes an `attachments[]` array.
+2. Find the attachment where `title == "plan.md"` (or `filename == "plan.md"`) and capture its `id`. Do NOT use the `url` field for fetching.
+3. `mcp__linear__get_attachment({ id: <attachmentId> })` — returns the markdown content directly (Linear hosts the file natively).
+4. Parse the plan content.
+5. If no `plan.md` attachment exists:
+
+   - **Default mode**: inform the user and suggest running `/plan <taskId>` first. Stop the skill.
+   - **`--auto` mode**: inline-invoke the `/plan` skill flow for this task to generate `plan.md` attachment + `AI Plan` label, then proceed with implementation. Post a Linear comment in Polish noting the plan was auto-generated.
+
+   Do NOT fall back to parsing plan content from comments, and do NOT attempt `curl`/`WebFetch` on a URL.
+
+### Step 2: Detect Project Structure
+
+Before implementing, detect the project layout:
+
+```bash
+# Check if angular.json is at root or in app/ subdirectory
+ls angular.json 2>/dev/null && echo "ROOT" || (ls app/angular.json 2>/dev/null && echo "APP_DIR")
+
+# Check package.json for dependencies
+cat package.json 2>/dev/null || cat app/package.json 2>/dev/null
+```
+
+Key things to detect:
+
+- Angular version (6-11)
+- CSS framework (Bootstrap 4 / custom SCSS / none)
+- NgRx version and patterns
+- i18n setup (ngx-translate)
+- Project structure (app/src/ vs src/)
+
+### Step 3: List Subtasks
+
+If task has subtasks:
+
+1. Fetch subtasks using `mcp__linear__list_issues` with parent filter
+2. Sort by priority/creation order
+3. Process each subtask in order
+
+### Step 3a: Save Orchestration Plan as Native Linear Attachment
+
+**⛔ Calling `mcp__linear__save_comment` with the orchestration body is FORBIDDEN. Use `mcp__linear__create_attachment` only.** Re-read Hard Rule #2 if tempted.
+
+Use `shared-impl-orchestrator` agent to generate a `🎭 Agent Orchestration Plan` that lists which agents run in what order (Angular 6-11 + CLI context).
+
+Then save it as an `orchestration.md` attachment on the task (not as a comment):
+
+1. **Replace existing orchestration**: use `mcp__linear__get_issue` to list attachments; if one titled `orchestration.md` exists, delete it via `mcp__linear__delete_attachment({ id: oldAttachmentId })`. Linear hosts the file natively, so nothing else needs cleanup.
+2. **Write locally**: `Write` the orchestration markdown to `/tmp/claude-plans/<taskId>-orchestration.md`.
+3. **Base64-encode**: `b64=$(base64 -i /tmp/claude-plans/<taskId>-orchestration.md)`.
+4. **Create Linear attachment** via `mcp__linear__create_attachment`:
+   - `issue`: the task ID
+   - `filename`: `orchestration.md`
+   - `contentType`: `text/markdown`
+   - `title`: `orchestration.md` (exact)
+   - `subtitle`: `Plan orkiestracji wygenerowany przez Claude Code (external)`
+   - `base64Content`: the base64 string from step 3
+5. **Clean up** local `/tmp/claude-plans/<taskId>-orchestration.md` file after the attachment is created.
+
+### Step 4: Implement Each Step
+
+For each step in the plan:
+
+1. **Read relevant files** - Understand existing code before modifying
+2. **Follow existing patterns** - Match the codebase style exactly
+3. **Create/modify files** - Implement the planned changes
+4. **Register in modules** - Add declarations/imports to NgModules
+5. **Update subtask status** - Mark as Done when complete
+
+### Step 5: Build Verification
+
+After all steps are complete:
+
+```bash
+# Verify build passes (adapt path based on project structure)
+ng build --prod
+# OR
+cd app && ng build --prod
+```
+
+### Step 6: Report Results
+
+Create a summary comment on the Linear task:
+
+```markdown
+## Raport Implementacji
+
+### Zrealizowane
+
+| Podzadanie | Tytul   | Status       |
+| ---------- | ------- | ------------ |
+| FRA-549    | [title] | Zrealizowane |
+
+### Zmiany
+
+| Plik                                      | Typ           | Opis              |
+| ----------------------------------------- | ------------- | ----------------- |
+| `src/app/components/feature.component.ts` | Nowy          | Komponent         |
+| `src/app/components/feature.module.ts`    | Zmodyfikowany | Dodano deklaracje |
+
+### Build
+
+- `ng build --prod` - Sukces
+
+---
+
+_Raport wygenerowany przez Claude Code_
+```
+
+## Agent Selection
+
+| Task Type      | Agent                                                |
+| -------------- | ---------------------------------------------------- |
+| New component  | `angular-component-scaffolder`                       |
+| New service    | `angular-service-builder`                            |
+| NgRx state     | `angular-state-builder`                              |
+| New directive  | `angular-directive-builder`                          |
+| New pipe       | `angular-pipe-builder`                               |
+| Guard/resolver | `angular-guard-builder` / `angular-resolver-builder` |
+| Styling        | `ui-web-designer`                                    |
+
+## Guidelines
+
+1. **Always read existing code first** before making changes
+2. **Follow the project's existing patterns** exactly
+3. **Register everything in NgModules** - declarations, imports, exports
+4. **Use the project's CSS approach** - detect from package.json
+5. **Write all Linear comments in Polish**
+6. **Verify build after implementation**
+7. **Do NOT add tests** unless explicitly requested
+8. **Do NOT modify deployment configuration**

package/plugins/flow-external/skills/karpathy-guidelines/SKILL.md

@@ -0,0 +1,72 @@
+---
+name: karpathy-guidelines
+description: Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.
+license: MIT
+---
+
+# Karpathy Guidelines
+
+Behavioral guidelines to reduce common LLM coding mistakes, derived from [Andrej Karpathy's observations](https://x.com/karpathy/status/2015883857489522876) on LLM coding pitfalls.
+
+**Tradeoff:** These guidelines bias toward caution over speed. For trivial tasks, use judgment.
+
+## 1. Think Before Coding
+
+**Don't assume. Don't hide confusion. Surface tradeoffs.**
+
+Before implementing:
+
+- State your assumptions explicitly. If uncertain, ask.
+- If multiple interpretations exist, present them - don't pick silently.
+- If a simpler approach exists, say so. Push back when warranted.
+- If something is unclear, stop. Name what's confusing. Ask.
+
+## 2. Simplicity First
+
+**Minimum code that solves the problem. Nothing speculative.**
+
+- No features beyond what was asked.
+- No abstractions for single-use code.
+- No "flexibility" or "configurability" that wasn't requested.
+- No error handling for impossible scenarios.
+- If you write 200 lines and it could be 50, rewrite it.
+
+Ask yourself: "Would a senior engineer say this is overcomplicated?" If yes, simplify.
+
+## 3. Surgical Changes
+
+**Touch only what you must. Clean up only your own mess.**
+
+When editing existing code:
+
+- Don't "improve" adjacent code, comments, or formatting.
+- Don't refactor things that aren't broken.
+- Match existing style, even if you'd do it differently.
+- If you notice unrelated dead code, mention it - don't delete it.
+
+When your changes create orphans:
+
+- Remove imports/variables/functions that YOUR changes made unused.
+- Don't remove pre-existing dead code unless asked.
+
+The test: Every changed line should trace directly to the user's request.
+
+## 4. Goal-Driven Execution
+
+**Define success criteria. Loop until verified.**
+
+Transform tasks into verifiable goals:
+
+- "Add validation" → "Write tests for invalid inputs, then make them pass"
+- "Fix the bug" → "Write a test that reproduces it, then make it pass"
+- "Refactor X" → "Ensure tests pass before and after"
+
+For multi-step tasks, state a brief plan:
+
+```
+1. [Step] → verify: [check]
+2. [Step] → verify: [check]
+3. [Step] → verify: [check]
+```
+
+Strong success criteria let you loop independently. Weak criteria ("make it work") require constant clarification.

package/plugins/flow-external/skills/linear-suggestion/SKILL.md

@@ -0,0 +1,62 @@
+---
+name: linear-suggestion
+description: Create a Linear issue in the "Framework 2.0" project with a suggestion for agent or skill improvements.
+allowed-tools: mcp__linear__save_issue
+---
+
+# Linear Suggestion
+
+Create a Linear issue in the **Framework 2.0** project containing a suggestion for improving agent definitions or skills.
+
+## When to Use
+
+- When an automated agent identifies a recurring pattern that could improve an agent or skill
+- When proposing orchestrator rule changes
+- When any non-interactive process needs to suggest framework improvements
+
+## Input Parameters
+
+| Parameter     | Required | Description                                                     |
+| ------------- | -------- | --------------------------------------------------------------- |
+| `title`       | YES      | Short summary (max 100 chars)                                   |
+| `description` | YES      | Full markdown description with rationale                        |
+| `source`      | YES      | Agent that generated the suggestion                             |
+| `targetFile`  | NO       | Path to the file to be modified                                 |
+| `category`    | NO       | One of: `OPTIMIZATION`, `NEW_RULE`, `PATTERN_UPDATE`, `BUG_FIX` |
+
+## Issue Format
+
+### Title
+
+```
+[Agent Suggestion] {title}
+```
+
+### Description
+
+```markdown
+## Agent Improvement Suggestion
+
+**Source agent**: `{source}`
+**Category**: {category}
+**Target file**: `{targetFile}`
+
+---
+
+{description}
+
+---
+
+_This issue was automatically created by `{source}` via the `linear-suggestion` skill._
+```
+
+## Process
+
+1. Format the issue title with `[Agent Suggestion]` prefix
+2. Build the description using the template
+3. Create the issue using MCP Linear server
+4. Return the issue ID and URL
+
+## Error Handling
+
+If creation fails, log error silently and do NOT block the parent workflow.

package/plugins/flow-external/skills/maia-files-delete/SKILL.md

@@ -0,0 +1,34 @@
+---
+name: maia-files-delete
+description: Delete a file from Maia API temporary storage.
+allowed-tools: Bash
+---
+
+# Maia Files Delete
+
+Delete a file from Maia AI API temporary storage.
+
+## API Endpoint
+
+```
+DELETE https://maia-ai-api.smartsoft.biz.pl/files/{id}
+```
+
+## Usage
+
+```bash
+curl -s -X DELETE https://maia-ai-api.smartsoft.biz.pl/files/{id}
+```
+
+## Batch Deletion
+
+```bash
+for id in id1 id2 id3; do
+  curl -s -X DELETE "https://maia-ai-api.smartsoft.biz.pl/files/$id"
+  echo "Deleted: $id"
+done
+```
+
+## Error Handling
+
+If deletion fails, report error but continue with remaining files.

package/plugins/flow-external/skills/maia-files-upload/SKILL.md

@@ -0,0 +1,41 @@
+---
+name: maia-files-upload
+description: Upload a file to Maia API temporary storage.
+allowed-tools: Bash
+---
+
+# Maia Files Upload
+
+Upload a file to Maia AI API temporary storage.
+
+## API Endpoint
+
+```
+POST https://maia-ai-api.smartsoft.biz.pl/files
+```
+
+## Usage
+
+```bash
+curl -s -X POST https://maia-ai-api.smartsoft.biz.pl/files \
+  -F "file=@/path/to/file.png"
+```
+
+## Response
+
+```json
+{ "id": "abc123def456" }
+```
+
+## Result URL
+
+```
+https://maia-ai-api.smartsoft.biz.pl/files/{id}
+```
+
+## Process
+
+1. Validate file exists
+2. Upload file using curl
+3. Extract ID from response
+4. Return ID and full URL