wormclaude 1.0.119 → 1.0.121

package/skills/playground/templates/diff-review.md

@@ -1,179 +0,0 @@
-# Diff Review Template
-
-Reach for this template when the playground is about reviewing code diffs: git commits, pull requests, and code changes with interactive line-by-line commenting for feedback.
-
-## Layout
-
-```
-+-------------------+----------------------------------+
-|                   |                                  |
-|  Commit Header:   |  Diff Content                    |
-|  • Hash           |  (files with hunks)              |
-|  • Message        |  with line numbers               |
-|  • Author/Date    |  and +/- indicators              |
-|                   |                                  |
-+-------------------+----------------------------------+
-|  Prompt Output Panel (fixed bottom-right)            |
-|  [ Copy All ]                                        |
-|  Shows all comments formatted for prompt             |
-+------------------------------------------------------+
-```
-
-Diff review playgrounds lay out git diffs with syntax highlighting. Users click a line to attach a comment, and those comments feed into the generated prompt that drives the code review feedback.
-
-## Control types for diff review
-
-| Feature | Control | Behavior |
-|---|---|---|
-| Line commenting | Click any diff line | Opens textarea below the line |
-| Comment indicator | Badge on commented lines | Shows which lines have feedback |
-| Save/Cancel | Buttons in comment box | Persist or discard comment |
-| Copy prompt | Button in prompt panel | Copies all comments to clipboard |
-
-## Diff rendering
-
-Turn the diff data into a structured shape before rendering:
-
-```javascript
-const diffData = [
-  {
-    file: "path/to/file.py",
-    hunks: [
-      {
-        header: "@@ -41,13 +41,13 @@ function context",
-        lines: [
-          { type: "context", oldNum: 41, newNum: 41, content: "unchanged line" },
-          { type: "deletion", oldNum: 42, newNum: null, content: "removed line" },
-          { type: "addition", oldNum: null, newNum: 42, content: "added line" },
-        ]
-      }
-    ]
-  }
-];
-```
-
-## Line type styling
-
-| Type | Background | Text Color | Prefix |
-|---|---|---|---|
-| `context` | transparent | default | ` ` (space) |
-| `addition` | green tint (#dafbe1 light / rgba(46,160,67,0.15) dark) | green (#1a7f37 light / #7ee787 dark) | `+` |
-| `deletion` | red tint (#ffebe9 light / rgba(248,81,73,0.15) dark) | red (#cf222e light / #f85149 dark) | `-` |
-| `hunk-header` | blue tint (#ddf4ff light) | blue (#0969da light) | `@@` |
-
-## Comment system
-
-Give every diff line its own unique id so comments can be tracked:
-
-```javascript
-const comments = {}; // { lineId: commentText }
-
-function selectLine(lineId, lineEl) {
-  // Deselect previous
-  document.querySelectorAll('.diff-line.selected').forEach(el =>
-    el.classList.remove('selected'));
-  document.querySelectorAll('.comment-box.active').forEach(el =>
-    el.classList.remove('active'));
-
-  // Select new
-  lineEl.classList.add('selected');
-  document.getElementById(`comment-box-${lineId}`).classList.add('active');
-}
-
-function saveComment(lineId) {
-  const textarea = document.getElementById(`textarea-${lineId}`);
-  const comment = textarea.value.trim();
-
-  if (comment) {
-    comments[lineId] = comment;
-  } else {
-    delete comments[lineId];
-  }
-
-  renderDiff(); // Re-render to show comment indicator
-  updatePromptOutput();
-}
-```
-
-## Prompt output format
-
-Emit the comments in a structured code review layout:
-
-```javascript
-function updatePromptOutput() {
-  const commentKeys = Object.keys(comments);
-
-  if (commentKeys.length === 0) {
-    promptContent.innerHTML = '<span class="no-comments">Click on any line to add a comment...</span>';
-    return;
-  }
-
-  let output = 'Code Review Comments:\n\n';
-
-  commentKeys.forEach(lineId => {
-    const lineEl = document.querySelector(`[data-line-id="${lineId}"]`);
-    const file = lineEl.dataset.file;
-    const lineNum = lineEl.dataset.lineNum;
-    const content = lineEl.dataset.content;
-
-    output += `📍 ${file}:${lineNum}\n`;
-    output += `   Code: ${content.trim()}\n`;
-    output += `   Comment: ${comments[lineId]}\n\n`;
-  });
-
-  promptContent.textContent = output;
-}
-```
-
-## Data attributes for line elements
-
-Stash metadata on each line element so the prompt can be built from it:
-
-```html
-<div class="diff-line addition"
-     data-line-id="0-1-5"
-     data-file="src/utils/handler.py"
-     data-line-num="45"
-     data-content="subagent_id = tracker.register()">
-```
-
-## Pre-populating with real data
-
-To build a diff viewer around a specific commit:
-
-1. Run `git show <commit> --format="%H%n%s%n%an%n%ad" -p`
-2. Parse that output into the `diffData` structure
-3. Surface the commit metadata in the header section
-
-## Theme support
-
-Cover both light and dark modes:
-
-```css
-/* Light mode */
-body { background: #f6f8fa; color: #1f2328; }
-.file-card { background: #ffffff; border: 1px solid #d0d7de; }
-.diff-line.addition { background: #dafbe1; }
-.diff-line.deletion { background: #ffebe9; }
-
-/* Dark mode */
-body { background: #0d1117; color: #c9d1d9; }
-.file-card { background: #161b22; border: 1px solid #30363d; }
-.diff-line.addition { background: rgba(46, 160, 67, 0.15); }
-.diff-line.deletion { background: rgba(248, 81, 73, 0.15); }
-```
-
-## Interactive features
-
-- **Hover hint:** Pop a "Click to comment" tooltip when a line is hovered
-- **Comment indicator:** Mark lines that already hold a comment with a badge (💬)
-- **Toast notification:** Flash "Copied to clipboard!" after a copy
-- **Edit existing:** Let users go back and revise comments they've already saved
-
-## Example topics
-
-- Git commit review (single commit diff with line comments)
-- Pull request review (multiple commits, file-level and line-level comments)
-- Code diff comparison (before/after refactoring)
-- Merge conflict resolution (showing both versions with annotations)
-- Code audit (security review with findings per line)

package/skills/playground/templates/document-critique.md

@@ -1,171 +0,0 @@
-# Document Critique Template
-
-Reach for this template when the playground exists to review and critique documents: SKILL.md files, READMEs, specs, proposals, or any text that calls for structured feedback through an approve/reject/comment workflow.
-
-## Layout
-
-```
-+---------------------------+--------------------+
-|                           |                    |
-|  Document content         |  Suggestions panel |
-|  with line numbers        |  (filterable list) |
-|  and suggestion           |  • Approve         |
-|  highlighting             |  • Reject          |
-|                           |  • Comment         |
-|                           |                    |
-+---------------------------+--------------------+
-|  Prompt output (approved + commented items)    |
-|  [ Copy Prompt ]                               |
-+------------------------------------------------+
-```
-
-## Key components
-
-### Document panel (left)
-- Show the whole document alongside line numbers
-- Flag lines that carry suggestions with a colored left border
-- Color-code by status: pending (amber), approved (green), rejected (red, dimmed)
-- Clicking a suggestion card scrolls to the line it points at
-
-### Suggestions panel (right)
-- Filter tabs: All / Pending / Approved / Rejected
-- A header tally showing how many sit in each status
-- Every suggestion card carries:
-  - Its line reference (for example "Line 3" or "Lines 17-24")
-  - The suggestion text itself
-  - Action buttons: Approve / Reject / Comment (or Reset once a decision is made)
-  - An optional textarea for the user's own comments
-
-### Prompt output (bottom)
-- Builds a prompt strictly from approved suggestions plus user comments
-- Splits into: Approved Improvements, Additional Feedback, Rejected (kept for context)
-- Copy button with "Copied!" feedback
-
-## State structure
-
-```javascript
-const suggestions = [
-  {
-    id: 1,
-    lineRef: "Line 3",
-    targetText: "description: Creates interactive...",
-    suggestion: "The description is too long. Consider shortening.",
-    category: "clarity",  // clarity, completeness, performance, accessibility, ux
-    status: "pending",    // pending, approved, rejected
-    userComment: ""
-  },
-  // ... more suggestions
-];
-
-let state = {
-  suggestions: [...],
-  activeFilter: "all",
-  activeSuggestionId: null
-};
-```
-
-## Suggestion matching to lines
-
-Tie suggestions back to document lines by parsing the lineRef:
-
-```javascript
-const suggestion = state.suggestions.find(s => {
-  const match = s.lineRef.match(/Line[s]?\s*(\d+)/);
-  if (match) {
-    const targetLine = parseInt(match[1]);
-    return Math.abs(targetLine - lineNum) <= 2; // fuzzy match nearby lines
-  }
-  return false;
-});
-```
-
-## Document rendering
-
-Deal with markdown-style formatting inline:
-
-```javascript
-// Skip ``` lines, wrap content in code-block-wrapper
-if (line.startsWith('```')) {
-  inCodeBlock = !inCodeBlock;
-  // Open or close wrapper div
-}
-
-// Headers
-if (line.startsWith('# ')) renderedLine = `<h1>...</h1>`;
-if (line.startsWith('## ')) renderedLine = `<h2>...</h2>`;
-
-// Inline formatting (outside code blocks)
-renderedLine = renderedLine.replace(/`([^`]+)`/g, '<code>$1</code>');
-renderedLine = renderedLine.replace(/\*\*([^*]+)\*\*/g, '<strong>$1</strong>');
-```
-
-## Prompt output generation
-
-Keep it to items that can be acted on:
-
-```javascript
-function updatePrompt() {
-  const approved = state.suggestions.filter(s => s.status === 'approved');
-  const withComments = state.suggestions.filter(s => s.userComment?.trim());
-
-  if (approved.length === 0 && withComments.length === 0) {
-    // Show placeholder
-    return;
-  }
-
-  let prompt = 'Please update [DOCUMENT] with the following changes:\n\n';
-
-  if (approved.length > 0) {
-    prompt += '## Approved Improvements\n\n';
-    for (const s of approved) {
-      prompt += `**${s.lineRef}:** ${s.suggestion}`;
-      if (s.userComment?.trim()) {
-        prompt += `\n  → User note: ${s.userComment.trim()}`;
-      }
-      prompt += '\n\n';
-    }
-  }
-
-  // Additional feedback from non-approved items with comments
-  // Rejected items listed for context only
-}
-```
-
-## Styling highlights
-
-```css
-.doc-line.has-suggestion {
-  border-left: 3px solid #bf8700;  /* amber for pending */
-  background: rgba(191, 135, 0, 0.08);
-}
-
-.doc-line.approved {
-  border-left-color: #1a7f37;  /* green */
-  background: rgba(26, 127, 55, 0.08);
-}
-
-.doc-line.rejected {
-  border-left-color: #cf222e;  /* red */
-  background: rgba(207, 34, 46, 0.08);
-  opacity: 0.6;
-}
-```
-
-## Pre-populating suggestions
-
-When assembling a critique playground for a particular document:
-
-1. Read through the document's contents
-2. Review it and draft suggestions that include:
-   - Precise line references
-   - Clear suggestion text that can be acted on
-   - Category tags (clarity, completeness, performance, accessibility, ux)
-3. Bake both the document content and the suggestions array straight into the HTML
-
-## Example use cases
-
-- SKILL.md review (skill definition quality, completeness, clarity)
-- README critique (documentation quality, missing sections, unclear explanations)
-- Spec review (requirements clarity, missing edge cases, ambiguity)
-- Proposal feedback (structure, argumentation, missing context)
-- Code comment review (docstring quality, inline comment usefulness)

package/skills/pptx/SKILL.md

@@ -1,230 +0,0 @@
----
-name: pptx
-description: "Reach for this skill whenever a .pptx file appears in a task, whether as a source, a result, or both. Covers building slide decks, pitch decks, and presentations; opening, parsing, or pulling text out of any .pptx (including cases where that text feeds something else like a summary or email); revising or refreshing decks that already exist; merging or separating slide files; and handling templates, layouts, speaker notes, or comments. Activate it whenever someone says \"deck,\" \"slides,\" or \"presentation,\" or names a .pptx file, no matter what they intend to do with the result. Any time a .pptx must be opened, generated, or modified, this skill applies."
-license: WormClaude
----
-
-# PPTX Skill
-
-## Quick Reference
-
-| Task | Guide |
-|------|-------|
-| Read/analyze content | `extract-text 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, one `## Slide N` section per slide
-extract-text presentation.pptx
-
-# Visual overview
-python scripts/thumbnail.py presentation.pptx
-
-# Raw XML
-python scripts/office/unpack.py presentation.pptx unpacked/
-```
-
----
-
-## Editing Workflow
-
-**See [editing.md](editing.md) for the complete walkthrough.**
-
-1. Analyze template with `thumbnail.py`
-2. Unpack → manipulate slides → edit content → clean → pack
-
----
-
-## Creating from Scratch
-
-**See [pptxgenjs.md](pptxgenjs.md) for the complete walkthrough.**
-
-Reach for this path when there's no template or reference deck to work from.
-
----
-
-## Design Ideas
-
-**Avoid dull slides.** A white background with plain bullets impresses no one. Pull ideas from the list below for each slide.
-
-### Before Starting
-
-- **Pick a bold, content-informed color palette**: The palette should feel built specifically for THIS subject. If you could drop the same colors into an unrelated deck and they'd still fit, your choices aren't distinctive enough.
-- **Dominance over equality**: Let one color carry the bulk of the weight (60-70%), backed by 1-2 supporting tones and a single sharp accent. Avoid weighting every color the same.
-- **Dark/light contrast**: Use dark backgrounds on the title and closing slides and lighter ones for the body (a "sandwich" layout). Alternatively, go dark across the whole deck for a premium look.
-- **Commit to a visual motif**: Settle on ONE signature element and reuse it — rounded photo frames, icons set in colored circles, a heavy border on one edge. Keep it consistent on every slide.
-
-### Color Palettes
-
-Match the colors to your subject rather than reaching for plain blue. Treat these palettes as starting points:
-
-| 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
-
-**Give every slide a visual anchor** — an image, chart, icon, or shape. Slides that are only text don't stick.
-
-**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
-
-**Go for a distinctive font pairing** — skip the automatic Arial. Choose a header face with character and team it with a clean body face.
-
-| 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
-- Let the layout breathe—don't pack every inch
-
-### Avoid (Common Mistakes)
-
-- **Don't reuse one layout throughout** — alternate columns, cards, and callouts from slide to slide
-- **Don't center body text** — keep paragraphs and lists left-aligned; reserve centering for titles
-- **Don't skimp on size contrast** — push titles to 36pt+ so they separate from 14-16pt body copy
-- **Don't fall back on blue** — choose colors tied to the actual subject
-- **Don't mix spacing randomly** — settle on 0.3" or 0.5" gaps and stick with one
-- **Don't polish a single slide and ignore the others** — either commit across the board or keep everything plain
-- **Don't build text-only slides** — bring in images, icons, charts, or other visuals; steer clear of bare title + bullets
-- **Don't overlook text box padding** — when lining up lines or shapes with text edges, set `margin: 0` on the text box or shift the shape to compensate for the padding
-- **Don't use low-contrast elements** — both icons and text must stand out clearly from the background; avoid pale text on pale backgrounds or dark text on dark backgrounds
-- **NEVER use accent lines under titles** — they're a telltale sign of AI-generated slides; rely on whitespace or background color instead
-- **Don't add decorative full-width colored bars/rectangles** — header/footer bars, side ribbons, or colored stripes look like AI slop unless the user specifically asks for them
-- **Don't reach for cream/beige backgrounds by default** — with no background specified, go with white (`FFFFFF`) or the user's brand colors; skip warm-neutral defaults like `F5F5DC`, `FAF0E6`, `FAEBD7`, `FFF8E1`
-- **Don't ship text that spills out of its shape** — if it won't fit, shrink the font, break it across slides, or grow the container; never leave content clipped or running past its bounds
-
----
-
-## QA (Required)
-
-Expect the first render to carry a handful of genuine problems — overlaps, overflow, things out of alignment. Track those down, fix them, and then stop. Don't keep tweaking coordinates by tiny amounts or hunt for a flawless render.
-
-Act instead of narrating: keep the chatter between tool calls to a minimum. Run the check, make the fix, keep going.
-
-### Content QA
-
-```bash
-extract-text output.pptx
-```
-
-Look for dropped content, typos, and wrong ordering.
-
-**With templates, scan for placeholder text left behind:**
-
-```bash
-extract-text output.pptx | grep -iE "\bx{3,}\b|lorem|ipsum|\bTODO|\[insert|this.*(page|slide).*layout"
-```
-
-If grep turns up matches, resolve them before calling the job done.
-
-### Visual QA
-
-**⚠️ USE SUBAGENTS** — even for just 2-3 slides. After staring at the code you'll perceive what you intended rather than what's actually rendered. A subagent comes in with fresh eyes.
-
-Render the slides to images (see [Converting to Images](#converting-to-images)), then hand over this prompt:
-
-```
-Visually inspect these slides for user-visible defects.
-
-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 user-visible issues. Skip sub-pixel positioning and cosmetic nitpicks a viewer wouldn't notice.
-
-Read and analyze these images — run `ls -1 "$PWD"/slide-*.jpg` and use the exact absolute paths it prints:
-1. <absolute-path>/slide-N.jpg — (Expected: [brief description])
-2. <absolute-path>/slide-N.jpg — (Expected: [brief description])
-...
-```
-
-### Verification Loop
-
-1. Build slides → render to images → inspect
-2. **Start with text bounds** — for each text box, verify the rendered text stays inside its shape. Overflow is the most frequent defect and always shows up to the viewer.
-3. Note any further problems you spot
-4. Fix them
-5. Re-check only the slides you changed
-6. **Halt after a single fix-and-verify pass** unless a fresh *user-visible* defect surfaces (overlap, overflow, missing content). Don't loop over sub-pixel placement, small color adjustments, or anything a viewer wouldn't catch.
-
----
-
-## Converting to Images
-
-Turn a presentation into one image per slide for visual review:
-
-```bash
-python scripts/office/soffice.py --headless --convert-to pdf output.pptx
-rm -f slide-*.jpg
-pdftoppm -jpeg -r 150 output.pdf slide
-ls -1 "$PWD"/slide-*.jpg
-```
-
-**Feed the absolute paths printed above straight into the view tool.** The `rm` wipes out leftover images from earlier runs. `pdftoppm` zero-pads according to the page count: `slide-1.jpg` for decks below 10 pages, `slide-01.jpg` for 10-99, and `slide-001.jpg` from 100 up.
-
-**Once you've made fixes, run all four commands again** — the PDF has to be rebuilt from the updated `.pptx` before `pdftoppm` can pick up your changes.
-
----
-
-## Dependencies
-
-- `pip install Pillow` - thumbnail grids
-- `npm install -g pptxgenjs` - building from scratch
-- LibreOffice (`soffice`) - PDF conversion (set up automatically for sandboxed environments through `scripts/office/soffice.py`)
-- Poppler (`pdftoppm`) - PDF to images