devskill 2.0.6 → 2.0.8

package/skills/powerbi-modeling/references/RLS.md

@@ -0,0 +1,226 @@
+# Row-Level Security (RLS) in Power BI
+
+## Overview
+
+Row-Level Security restricts data access at the row level based on user identity. Users see only the data they're authorized to view.
+
+## Design Principles
+
+### 1. Filter on Dimension Tables
+Apply RLS to dimensions, not fact tables:
+- More efficient (smaller tables)
+- Filters propagate through relationships
+- Easier to maintain
+
+```dax
+// On Customer dimension - filters propagate to Sales
+[Region] = "West"
+```
+
+### 2. Create Minimal Roles
+Avoid many role combinations:
+- Each role = separate cache
+- Roles are additive (union, not intersection)
+- Consolidate where possible
+
+### 3. Use Dynamic RLS When Possible
+Data-driven rules scale better:
+- User mapping in a table
+- USERPRINCIPALNAME() for identity
+- No role changes when users change
+
+## Static vs Dynamic RLS
+
+### Static RLS
+Fixed rules per role:
+```dax
+// Role: West Region
+[Region] = "West"
+
+// Role: East Region  
+[Region] = "East"
+```
+
+**Pros:** Simple, clear
+**Cons:** Doesn't scale, requires role per group
+
+### Dynamic RLS
+User identity drives filtering:
+```dax
+// Single role filters based on logged-in user
+[ManagerEmail] = USERPRINCIPALNAME()
+```
+
+**Pros:** Scales, self-maintaining
+**Cons:** Requires user mapping data
+
+## Implementation Patterns
+
+### Pattern 1: Direct User Mapping
+User email in dimension table:
+```dax
+// On Customer table
+[CustomerEmail] = USERPRINCIPALNAME()
+```
+
+### Pattern 2: Security Table
+Separate table mapping users to data:
+```
+SecurityMapping table:
+| UserEmail | Region |
+|-----------|--------|
+| joe@co.com | West  |
+| sue@co.com | East  |
+```
+
+```dax
+// On Region dimension
+[Region] IN 
+    SELECTCOLUMNS(
+        FILTER(SecurityMapping, [UserEmail] = USERPRINCIPALNAME()),
+        "Region", [Region]
+    )
+```
+
+### Pattern 3: Manager Hierarchy
+Users see their data plus subordinates:
+```dax
+// Using PATH functions for hierarchy
+PATHCONTAINS(Employee[ManagerPath], 
+    LOOKUPVALUE(Employee[EmployeeID], Employee[Email], USERPRINCIPALNAME()))
+```
+
+### Pattern 4: Multiple Rules
+Combine conditions:
+```dax
+// Users see their region OR if they're a global viewer
+[Region] = LOOKUPVALUE(Users[Region], Users[Email], USERPRINCIPALNAME())
+|| LOOKUPVALUE(Users[IsGlobal], Users[Email], USERPRINCIPALNAME()) = TRUE()
+```
+
+## Creating Roles via MCP
+
+### List Existing Roles
+```
+security_role_operations(operation: "List")
+```
+
+### Create Role with Permission
+```
+security_role_operations(
+  operation: "Create",
+  definitions: [{
+    name: "Regional Sales",
+    modelPermission: "Read",
+    description: "Restricts sales data by region"
+  }]
+)
+```
+
+### Add Table Permission (Filter)
+```
+security_role_operations(
+  operation: "CreatePermissions",
+  permissionDefinitions: [{
+    roleName: "Regional Sales",
+    tableName: "Customer",
+    filterExpression: "[Region] = USERPRINCIPALNAME()"
+  }]
+)
+```
+
+### Get Effective Permissions
+```
+security_role_operations(
+  operation: "GetEffectivePermissions",
+  references: [{ name: "Regional Sales" }]
+)
+```
+
+## Testing RLS
+
+### In Power BI Desktop
+1. Modeling tab > View As
+2. Select role(s) to test
+3. Optionally specify user identity
+4. Verify data filtering
+
+### Test Unexpected Values
+For dynamic RLS, test:
+- Valid users
+- Unknown users (should see nothing or error gracefully)
+- NULL/blank values
+
+```dax
+// Defensive pattern - returns no data for unknown users
+IF(
+    USERPRINCIPALNAME() IN VALUES(SecurityMapping[UserEmail]),
+    [Region] IN SELECTCOLUMNS(...),
+    FALSE()
+)
+```
+
+## Common Mistakes
+
+### 1. RLS on Fact Tables Only
+**Problem:** Large table scans, poor performance
+**Solution:** Apply to dimension tables, let relationships propagate
+
+### 2. Using LOOKUPVALUE Instead of Relationships
+**Problem:** Expensive, doesn't scale
+**Solution:** Create proper relationships, let filters flow
+
+### 3. Expecting Intersection Behavior
+**Problem:** Multiple roles = UNION (additive), not intersection
+**Solution:** Design roles with union behavior in mind
+
+### 4. Forgetting About DirectQuery
+**Problem:** RLS filters become WHERE clauses
+**Solution:** Ensure source database can handle the query patterns
+
+### 5. Not Testing Edge Cases
+**Problem:** Users see unexpected data
+**Solution:** Test with: valid users, invalid users, multiple roles
+
+## Bidirectional RLS
+
+For bidirectional relationships with RLS:
+```
+Enable "Apply security filter in both directions"
+```
+
+Only use when:
+- RLS requires filtering through many-to-many
+- Dimension-to-dimension security needed
+
+**Caution:** Only one bidirectional relationship per path allowed.
+
+## Performance Considerations
+
+- RLS adds WHERE clauses to every query
+- Complex DAX in filters hurts performance
+- Test with realistic user counts
+- Consider aggregations for large models
+
+## Object-Level Security (OLS)
+
+Restrict access to entire tables or columns:
+```
+// Via XMLA/TMSL - not available in Desktop UI
+```
+
+Use for:
+- Hiding sensitive columns (salary, SSN)
+- Restricting entire tables
+- Combined with RLS for comprehensive security
+
+## Validation Checklist
+
+- [ ] RLS applied to dimension tables (not fact tables)
+- [ ] Filters propagate correctly through relationships
+- [ ] Dynamic RLS uses USERPRINCIPALNAME()
+- [ ] Tested with valid and invalid users
+- [ ] Edge cases handled (NULL, unknown users)
+- [ ] Performance tested under load
+- [ ] Role mappings documented
+- [ ] Workspace roles understood (Admins bypass RLS)

package/skills/powerbi-modeling/references/STAR-SCHEMA.md

@@ -0,0 +1,103 @@
+# Star Schema Design for Power BI
+
+## Overview
+
+Star schema is the optimal design pattern for Power BI semantic models. It organizes data into:
+- **Dimension tables**: Enable filtering and grouping (the "one" side)
+- **Fact tables**: Enable summarization (the "many" side)
+
+## Table Classification
+
+### Dimension Tables
+- Contain descriptive attributes for filtering/slicing
+- Have unique key columns (one row per entity)
+- Examples: Customer, Product, Date, Geography, Employee
+- Naming convention: Singular noun (`Customer`, `Product`)
+
+### Fact Tables  
+- Contain measurable, quantitative data
+- Have foreign keys to dimensions
+- Store data at consistent grain (one row per transaction/event)
+- Examples: Sales, Orders, Inventory, WebVisits
+- Naming convention: Business process noun (`Sales`, `Orders`)
+
+## Design Principles
+
+### 1. Separate Dimensions from Facts
+```
+BAD:  Single denormalized "Sales" table with customer details
+GOOD: "Sales" fact table + "Customer" dimension table
+```
+
+### 2. Consistent Grain
+Every row in a fact table represents the same thing:
+- Order line level (most common)
+- Daily aggregation
+- Monthly summary
+
+Never mix grains in one table.
+
+### 3. Surrogate Keys
+Add surrogate keys when source lacks unique identifiers:
+```m
+// Power Query: Add index column
+= Table.AddIndexColumn(Source, "CustomerKey", 1, 1)
+```
+
+### 4. Date Dimension
+Always create a dedicated date table:
+- Mark as date table in Power BI
+- Include fiscal periods if needed
+- Add relative date columns (IsCurrentMonth, IsPreviousYear)
+
+```dax
+Date = 
+ADDCOLUMNS(
+    CALENDAR(DATE(2020,1,1), DATE(2030,12,31)),
+    "Year", YEAR([Date]),
+    "Month", FORMAT([Date], "MMMM"),
+    "MonthNum", MONTH([Date]),
+    "Quarter", "Q" & FORMAT([Date], "Q"),
+    "WeekDay", FORMAT([Date], "dddd")
+)
+```
+
+## Special Dimension Types
+
+### Role-Playing Dimensions
+Same dimension used multiple times (e.g., Date for OrderDate, ShipDate):
+- Option 1: Duplicate the table (OrderDate, ShipDate tables)
+- Option 2: Use inactive relationships with USERELATIONSHIP in DAX
+
+### Slowly Changing Dimensions (Type 2)
+Track historical changes with version columns:
+- StartDate, EndDate columns
+- IsCurrent flag
+- Requires pre-processing in data warehouse
+
+### Junk Dimensions
+Combine low-cardinality flags into one table:
+```
+OrderFlags dimension: IsRush, IsGift, IsOnline
+```
+
+### Degenerate Dimensions
+Keep transaction identifiers (OrderNumber, InvoiceID) in fact table.
+
+## Anti-Patterns to Avoid
+
+| Anti-Pattern | Problem | Solution |
+|--------------|---------|----------|
+| Wide denormalized tables | Poor performance, hard to maintain | Split into star schema |
+| Snowflake (normalized dims) | Extra joins hurt performance | Flatten dimensions |
+| Many-to-many without bridge | Ambiguous results | Add bridge/junction table |
+| Mixed grain facts | Incorrect aggregations | Separate tables per grain |
+
+## Validation Checklist
+
+- [ ] Each table is clearly dimension or fact
+- [ ] Fact tables have foreign keys to all related dimensions
+- [ ] Dimensions have unique key columns
+- [ ] Date table exists and is marked
+- [ ] No circular relationship paths
+- [ ] Consistent naming conventions

package/skills/pptx/LICENSE.txt

@@ -0,0 +1,30 @@
+© 2025 Anthropic, PBC. All rights reserved.
+
+LICENSE: Use of these materials (including all code, prompts, assets, files,
+and other components of this Skill) is governed by your agreement with
+Anthropic regarding use of Anthropic's services. If no separate agreement
+exists, use is governed by Anthropic's Consumer Terms of Service or
+Commercial Terms of Service, as applicable:
+https://www.anthropic.com/legal/consumer-terms
+https://www.anthropic.com/legal/commercial-terms
+Your applicable agreement is referred to as the "Agreement." "Services" are
+as defined in the Agreement.
+
+ADDITIONAL RESTRICTIONS: Notwithstanding anything in the Agreement to the
+contrary, users may not:
+
+- Extract these materials from the Services or retain copies of these
+  materials outside the Services
+- Reproduce or copy these materials, except for temporary copies created
+  automatically during authorized use of the Services
+- Create derivative works based on these materials
+- Distribute, sublicense, or transfer these materials to any third party
+- Make, offer to sell, sell, or import any inventions embodied in these
+  materials
+- Reverse engineer, decompile, or disassemble these materials
+
+The receipt, viewing, or possession of these materials does not convey or
+imply any license or right beyond those expressly granted above.
+
+Anthropic retains all right, title, and interest in these materials,
+including all copyrights, patents, and other intellectual property rights.

package/skills/pptx/SKILL.md

@@ -0,0 +1,232 @@
+---
+name: pptx
+description: "Use this skill any time a .pptx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx file (even if the extracted content will be used elsewhere, like in an email or summary); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates, layouts, speaker notes, or comments. Trigger whenever the user mentions \"deck,\" \"slides,\" \"presentation,\" or references a .pptx filename, regardless of what they plan to do with the content afterward. If a .pptx file needs to be opened, created, or touched, use this skill."
+license: Proprietary. LICENSE.txt has complete terms
+---
+
+# PPTX Skill
+
+## Quick Reference
+
+| Task | Guide |
+|------|-------|
+| Read/analyze content | `python -m markitdown presentation.pptx` |
+| Edit or create from template | Read [editing.md](editing.md) |
+| Create from scratch | Read [pptxgenjs.md](pptxgenjs.md) |
+
+---
+
+## Reading Content
+
+```bash
+# Text extraction
+python -m markitdown presentation.pptx
+
+# Visual overview
+python scripts/thumbnail.py presentation.pptx
+
+# Raw XML
+python scripts/office/unpack.py presentation.pptx unpacked/
+```
+
+---
+
+## Editing Workflow
+
+**Read [editing.md](editing.md) for full details.**
+
+1. Analyze template with `thumbnail.py`
+2. Unpack → manipulate slides → edit content → clean → pack
+
+---
+
+## Creating from Scratch
+
+**Read [pptxgenjs.md](pptxgenjs.md) for full details.**
+
+Use when no template or reference presentation is available.
+
+---
+
+## Design Ideas
+
+**Don't create boring slides.** Plain bullets on a white background won't impress anyone. Consider ideas from this list for each slide.
+
+### Before Starting
+
+- **Pick a bold, content-informed color palette**: The palette should feel designed for THIS topic. If swapping your colors into a completely different presentation would still "work," you haven't made specific enough choices.
+- **Dominance over equality**: One color should dominate (60-70% visual weight), with 1-2 supporting tones and one sharp accent. Never give all colors equal weight.
+- **Dark/light contrast**: Dark backgrounds for title + conclusion slides, light for content ("sandwich" structure). Or commit to dark throughout for a premium feel.
+- **Commit to a visual motif**: Pick ONE distinctive element and repeat it — rounded image frames, icons in colored circles, thick single-side borders. Carry it across every slide.
+
+### Color Palettes
+
+Choose colors that match your topic — don't default to generic blue. Use these palettes as inspiration:
+
+| Theme | Primary | Secondary | Accent |
+|-------|---------|-----------|--------|
+| **Midnight Executive** | `1E2761` (navy) | `CADCFC` (ice blue) | `FFFFFF` (white) |
+| **Forest & Moss** | `2C5F2D` (forest) | `97BC62` (moss) | `F5F5F5` (cream) |
+| **Coral Energy** | `F96167` (coral) | `F9E795` (gold) | `2F3C7E` (navy) |
+| **Warm Terracotta** | `B85042` (terracotta) | `E7E8D1` (sand) | `A7BEAE` (sage) |
+| **Ocean Gradient** | `065A82` (deep blue) | `1C7293` (teal) | `21295C` (midnight) |
+| **Charcoal Minimal** | `36454F` (charcoal) | `F2F2F2` (off-white) | `212121` (black) |
+| **Teal Trust** | `028090` (teal) | `00A896` (seafoam) | `02C39A` (mint) |
+| **Berry & Cream** | `6D2E46` (berry) | `A26769` (dusty rose) | `ECE2D0` (cream) |
+| **Sage Calm** | `84B59F` (sage) | `69A297` (eucalyptus) | `50808E` (slate) |
+| **Cherry Bold** | `990011` (cherry) | `FCF6F5` (off-white) | `2F3C7E` (navy) |
+
+### For Each Slide
+
+**Every slide needs a visual element** — image, chart, icon, or shape. Text-only slides are forgettable.
+
+**Layout options:**
+- Two-column (text left, illustration on right)
+- Icon + text rows (icon in colored circle, bold header, description below)
+- 2x2 or 2x3 grid (image on one side, grid of content blocks on other)
+- Half-bleed image (full left or right side) with content overlay
+
+**Data display:**
+- Large stat callouts (big numbers 60-72pt with small labels below)
+- Comparison columns (before/after, pros/cons, side-by-side options)
+- Timeline or process flow (numbered steps, arrows)
+
+**Visual polish:**
+- Icons in small colored circles next to section headers
+- Italic accent text for key stats or taglines
+
+### Typography
+
+**Choose an interesting font pairing** — don't default to Arial. Pick a header font with personality and pair it with a clean body font.
+
+| Header Font | Body Font |
+|-------------|-----------|
+| Georgia | Calibri |
+| Arial Black | Arial |
+| Calibri | Calibri Light |
+| Cambria | Calibri |
+| Trebuchet MS | Calibri |
+| Impact | Arial |
+| Palatino | Garamond |
+| Consolas | Calibri |
+
+| Element | Size |
+|---------|------|
+| Slide title | 36-44pt bold |
+| Section header | 20-24pt bold |
+| Body text | 14-16pt |
+| Captions | 10-12pt muted |
+
+### Spacing
+
+- 0.5" minimum margins
+- 0.3-0.5" between content blocks
+- Leave breathing room—don't fill every inch
+
+### Avoid (Common Mistakes)
+
+- **Don't repeat the same layout** — vary columns, cards, and callouts across slides
+- **Don't center body text** — left-align paragraphs and lists; center only titles
+- **Don't skimp on size contrast** — titles need 36pt+ to stand out from 14-16pt body
+- **Don't default to blue** — pick colors that reflect the specific topic
+- **Don't mix spacing randomly** — choose 0.3" or 0.5" gaps and use consistently
+- **Don't style one slide and leave the rest plain** — commit fully or keep it simple throughout
+- **Don't create text-only slides** — add images, icons, charts, or visual elements; avoid plain title + bullets
+- **Don't forget text box padding** — when aligning lines or shapes with text edges, set `margin: 0` on the text box or offset the shape to account for padding
+- **Don't use low-contrast elements** — icons AND text need strong contrast against the background; avoid light text on light backgrounds or dark text on dark backgrounds
+- **NEVER use accent lines under titles** — these are a hallmark of AI-generated slides; use whitespace or background color instead
+
+---
+
+## QA (Required)
+
+**Assume there are problems. Your job is to find them.**
+
+Your first render is almost never correct. Approach QA as a bug hunt, not a confirmation step. If you found zero issues on first inspection, you weren't looking hard enough.
+
+### Content QA
+
+```bash
+python -m markitdown output.pptx
+```
+
+Check for missing content, typos, wrong order.
+
+**When using templates, check for leftover placeholder text:**
+
+```bash
+python -m markitdown output.pptx | grep -iE "xxxx|lorem|ipsum|this.*(page|slide).*layout"
+```
+
+If grep returns results, fix them before declaring success.
+
+### Visual QA
+
+**⚠️ USE SUBAGENTS** — even for 2-3 slides. You've been staring at the code and will see what you expect, not what's there. Subagents have fresh eyes.
+
+Convert slides to images (see [Converting to Images](#converting-to-images)), then use this prompt:
+
+```
+Visually inspect these slides. Assume there are issues — find them.
+
+Look for:
+- Overlapping elements (text through shapes, lines through words, stacked elements)
+- Text overflow or cut off at edges/box boundaries
+- Decorative lines positioned for single-line text but title wrapped to two lines
+- Source citations or footers colliding with content above
+- Elements too close (< 0.3" gaps) or cards/sections nearly touching
+- Uneven gaps (large empty area in one place, cramped in another)
+- Insufficient margin from slide edges (< 0.5")
+- Columns or similar elements not aligned consistently
+- Low-contrast text (e.g., light gray text on cream-colored background)
+- Low-contrast icons (e.g., dark icons on dark backgrounds without a contrasting circle)
+- Text boxes too narrow causing excessive wrapping
+- Leftover placeholder content
+
+For each slide, list issues or areas of concern, even if minor.
+
+Read and analyze these images:
+1. /path/to/slide-01.jpg (Expected: [brief description])
+2. /path/to/slide-02.jpg (Expected: [brief description])
+
+Report ALL issues found, including minor ones.
+```
+
+### Verification Loop
+
+1. Generate slides → Convert to images → Inspect
+2. **List issues found** (if none found, look again more critically)
+3. Fix issues
+4. **Re-verify affected slides** — one fix often creates another problem
+5. Repeat until a full pass reveals no new issues
+
+**Do not declare success until you've completed at least one fix-and-verify cycle.**
+
+---
+
+## Converting to Images
+
+Convert presentations to individual slide images for visual inspection:
+
+```bash
+python scripts/office/soffice.py --headless --convert-to pdf output.pptx
+pdftoppm -jpeg -r 150 output.pdf slide
+```
+
+This creates `slide-01.jpg`, `slide-02.jpg`, etc.
+
+To re-render specific slides after fixes:
+
+```bash
+pdftoppm -jpeg -r 150 -f N -l N output.pdf slide-fixed
+```
+
+---
+
+## Dependencies
+
+- `pip install "markitdown[pptx]"` - text extraction
+- `pip install Pillow` - thumbnail grids
+- `npm install -g pptxgenjs` - creating from scratch
+- LibreOffice (`soffice`) - PDF conversion (auto-configured for sandboxed environments via `scripts/office/soffice.py`)
+- Poppler (`pdftoppm`) - PDF to images

package/skills/pptx/SYNC.md

@@ -0,0 +1,5 @@
+# Sync Info
+
+- **Source:** `vendor/anthropics/skills/pptx`
+- **Git SHA:** `887114fd09f8f24a7e6c907f9ee505348498ab6a`
+- **Synced:** 2026-03-24