aiden-runtime 3.19.5 → 3.19.7

package/workspace-templates/skills/linear/skill.json

@@ -0,0 +1,25 @@
+{
+  "name": "linear",
+  "version": "1.0.0",
+  "description": "Manage Linear issues, projects, and cycles via the Linear GraphQL API",
+  "author": "aiden",
+  "license": "MIT",
+  "tools": [],
+  "trigger_phrases": [],
+  "compatible_agents": [
+    "aiden"
+  ],
+  "min_agent_version": "3.0.0",
+  "tags": [
+    "linear",
+    "issues",
+    "project-management",
+    "graphql",
+    "engineering",
+    "sprint",
+    "cycle",
+    "team",
+    "tasks"
+  ],
+  "created": "2026-04-27T17:11:39.895Z"
+}

package/workspace-templates/skills/nano-pdf/SKILL.md

@@ -0,0 +1,113 @@
+---
+name: nano-pdf
+description: Edit PDFs with natural-language instructions using the nano-pdf CLI tool
+category: productivity
+version: 1.0.0
+origin: aiden
+license: Apache-2.0
+tags: pdf, edit, merge, split, compress, redact, nano-pdf, cli, document, watermark
+---
+
+# nano-pdf — Natural-Language PDF Editing
+
+Use the `nano-pdf` CLI to perform common PDF operations — merge, split, compress, add watermarks, redact text, and more — via simple natural-language or flag-based commands.
+
+## When to Use
+
+- User wants to merge multiple PDFs into one
+- User wants to split a PDF into individual pages or page ranges
+- User wants to compress a large PDF to reduce file size
+- User wants to add a watermark or page numbers to a PDF
+- User wants to redact or remove specific pages
+
+## How to Use
+
+### 1. Install nano-pdf
+
+```powershell
+pip install nano-pdf
+# Verify installation
+nano-pdf --version
+```
+
+### 2. Merge multiple PDFs
+
+```powershell
+nano-pdf merge report1.pdf report2.pdf appendix.pdf --output merged.pdf
+```
+
+### 3. Split a PDF into individual pages
+
+```powershell
+# Split every page into a separate file
+nano-pdf split document.pdf --output ./pages/
+
+# Split a specific range into a new file
+nano-pdf split document.pdf --pages 1-5 --output extract.pdf
+```
+
+### 4. Compress a PDF
+
+```powershell
+# Default compression
+nano-pdf compress large_file.pdf --output compressed.pdf
+
+# Aggressive compression (lower image quality)
+nano-pdf compress large_file.pdf --level high --output compressed.pdf
+```
+
+### 5. Add a watermark
+
+```powershell
+nano-pdf watermark input.pdf --text "CONFIDENTIAL" --output watermarked.pdf
+# Custom font size and opacity
+nano-pdf watermark input.pdf --text "DRAFT" --size 60 --opacity 0.3 --output draft.pdf
+```
+
+### 6. Add page numbers
+
+```powershell
+nano-pdf number input.pdf --position bottom-right --output numbered.pdf
+```
+
+### 7. Remove specific pages
+
+```powershell
+# Remove pages 3 and 7 from a 10-page PDF
+nano-pdf remove input.pdf --pages 3,7 --output trimmed.pdf
+```
+
+### 8. Rotate pages
+
+```powershell
+# Rotate all pages 90 degrees clockwise
+nano-pdf rotate input.pdf --degrees 90 --output rotated.pdf
+
+# Rotate only page 2
+nano-pdf rotate input.pdf --degrees 180 --pages 2 --output rotated.pdf
+```
+
+### 9. Extract images from a PDF
+
+```powershell
+nano-pdf extract-images input.pdf --output ./images/
+```
+
+## Examples
+
+**"Merge contract.pdf and appendix.pdf into one file"**
+→ Use step 2: `nano-pdf merge contract.pdf appendix.pdf --output final_contract.pdf`
+
+**"Compress this 50MB report so I can email it"**
+→ Use step 4 with `--level high` to aggressively reduce size.
+
+**"Split the quarterly report — I only need pages 10 to 15"**
+→ Use step 3 with `--pages 10-15`.
+
+## Cautions
+
+- nano-pdf preserves PDF/A compliance when the input is already PDF/A — check if needed for legal documents
+- Aggressive compression (`--level high`) reduces image resolution — not suitable for print-quality output
+- Encrypted or password-protected PDFs cannot be processed without first removing the password
+- Very large PDFs (> 200 MB) may require chunked processing — split first, process, then merge
+- nano-pdf is a Python package — confirm it is installed before use (`pip show nano-pdf`)

package/workspace-templates/skills/nano-pdf/skill.json

@@ -0,0 +1,26 @@
+{
+  "name": "nano-pdf",
+  "version": "1.0.0",
+  "description": "Edit PDFs with natural-language instructions using the nano-pdf CLI tool",
+  "author": "aiden",
+  "license": "MIT",
+  "tools": [],
+  "trigger_phrases": [],
+  "compatible_agents": [
+    "aiden"
+  ],
+  "min_agent_version": "3.0.0",
+  "tags": [
+    "pdf",
+    "edit",
+    "merge",
+    "split",
+    "compress",
+    "redact",
+    "nano-pdf",
+    "cli",
+    "document",
+    "watermark"
+  ],
+  "created": "2026-04-27T17:11:39.938Z"
+}

package/workspace-templates/skills/notion/SKILL.md

@@ -0,0 +1,108 @@
+---
+name: notion
+description: Read, create, and update Notion pages and databases via the Notion REST API
+category: productivity
+version: 1.0.0
+origin: aiden
+license: Apache-2.0
+tags: notion, notes, database, pages, workspace, api, knowledge-base, tasks
+---
+
+# Notion API Integration
+
+Interact with Notion workspaces through the official REST API. Requires an Internal Integration token (`NOTION_TOKEN`) and pages/databases shared with that integration.
+
+## When to Use
+
+- User wants to read content from a Notion page
+- User wants to create a new page or database entry
+- User wants to query a Notion database with filters
+- User wants to append blocks to an existing page
+- User wants to search across their Notion workspace
+
+## How to Use
+
+### 1. Set up the integration token
+
+The user must create an Internal Integration at https://www.notion.so/my-integrations and share their pages/databases with it.
+
+```powershell
+# Set token in session (or add to .env)
+$env:NOTION_TOKEN = "ntn_..."
+```
+
+### 2. Search workspace
+
+```powershell
+$headers = @{ "Authorization" = "Bearer $env:NOTION_TOKEN"; "Notion-Version" = "2022-06-28"; "Content-Type" = "application/json" }
+$body    = '{"query": "meeting notes"}'
+$resp    = Invoke-RestMethod -Uri "https://api.notion.com/v1/search" -Method Post -Headers $headers -Body $body
+$resp.results | Select-Object -ExpandProperty properties | ConvertTo-Json -Depth 5
+```
+
+### 3. Read a page
+
+```powershell
+$pageId  = "your-page-id"   # from Notion URL: notion.so/Page-Title-<pageId>
+$headers = @{ "Authorization" = "Bearer $env:NOTION_TOKEN"; "Notion-Version" = "2022-06-28" }
+$page    = Invoke-RestMethod -Uri "https://api.notion.com/v1/pages/$pageId" -Headers $headers
+$blocks  = Invoke-RestMethod -Uri "https://api.notion.com/v1/blocks/$pageId/children" -Headers $headers
+$blocks.results | ForEach-Object { $_.paragraph.rich_text.plain_text }
+```
+
+### 4. Query a database
+
+```powershell
+$dbId    = "your-database-id"
+$headers = @{ "Authorization" = "Bearer $env:NOTION_TOKEN"; "Notion-Version" = "2022-06-28"; "Content-Type" = "application/json" }
+$filter  = '{"filter": {"property": "Status", "select": {"equals": "In Progress"}}}'
+$resp    = Invoke-RestMethod -Uri "https://api.notion.com/v1/databases/$dbId/query" -Method Post -Headers $headers -Body $filter
+$resp.results | ForEach-Object { $_.properties.Name.title.plain_text }
+```
+
+### 5. Create a page in a database
+
+```powershell
+$dbId    = "your-database-id"
+$headers = @{ "Authorization" = "Bearer $env:NOTION_TOKEN"; "Notion-Version" = "2022-06-28"; "Content-Type" = "application/json" }
+$payload = @{
+  parent     = @{ database_id = $dbId }
+  properties = @{
+    Name = @{ title = @(@{ text = @{ content = "My New Page" } }) }
+  }
+} | ConvertTo-Json -Depth 10
+Invoke-RestMethod -Uri "https://api.notion.com/v1/pages" -Method Post -Headers $headers -Body $payload
+```
+
+### 6. Append text blocks to a page
+
+```powershell
+$pageId  = "your-page-id"
+$headers = @{ "Authorization" = "Bearer $env:NOTION_TOKEN"; "Notion-Version" = "2022-06-28"; "Content-Type" = "application/json" }
+$payload = @{
+  children = @(@{
+    object    = "block"
+    type      = "paragraph"
+    paragraph = @{ rich_text = @(@{ type = "text"; text = @{ content = "Appended content here." } }) }
+  })
+} | ConvertTo-Json -Depth 10
+Invoke-RestMethod -Uri "https://api.notion.com/v1/blocks/$pageId/children" -Method Patch -Headers $headers -Body $payload
+```
+
+## Examples
+
+**"Show me all In Progress tasks in my Notion project database"**
+→ Use step 4 with a Status filter. Ask for database ID from the Notion URL.
+
+**"Create a new meeting notes page in Notion for today"**
+→ Use step 5 to create a page, then step 6 to append an agenda block.
+
+**"Search my Notion workspace for anything about Q2 planning"**
+→ Use step 2 with query `Q2 planning`.
+
+## Cautions
+
+- Integration must be explicitly shared with each page/database — it won't see everything by default
+- Page IDs are the 32-character hex string at the end of Notion URLs
+- API rate limit is 3 requests/second per integration — add delays for bulk operations
+- Rich text properties have nested structure — always check `rich_text[0].plain_text` for text values

package/workspace-templates/skills/notion/skill.json

@@ -0,0 +1,24 @@
+{
+  "name": "notion",
+  "version": "1.0.0",
+  "description": "Read, create, and update Notion pages and databases via the Notion REST API",
+  "author": "aiden",
+  "license": "MIT",
+  "tools": [],
+  "trigger_phrases": [],
+  "compatible_agents": [
+    "aiden"
+  ],
+  "min_agent_version": "3.0.0",
+  "tags": [
+    "notion",
+    "notes",
+    "database",
+    "pages",
+    "workspace",
+    "api",
+    "knowledge-base",
+    "tasks"
+  ],
+  "created": "2026-04-27T17:11:39.995Z"
+}

package/workspace-templates/skills/obsidian/SKILL.md

@@ -0,0 +1,115 @@
+---
+name: obsidian
+description: Read, search, and create notes in Obsidian vaults using file system operations and CLI tools
+category: productivity
+version: 1.0.0
+origin: aiden
+license: Apache-2.0
+tags: obsidian, notes, vault, markdown, knowledge-base, zettelkasten, wiki, pkm
+---
+
+# Obsidian Vault Operations
+
+Interact with Obsidian vaults directly through the file system. Obsidian notes are plain Markdown files, so you can read, search, create, and link notes without launching the Obsidian app.
+
+## When to Use
+
+- User wants to search notes across an Obsidian vault
+- User wants to create a new note in a specific vault folder
+- User wants to find all notes tagged with a given tag
+- User wants to read a specific note by name
+- User wants to find backlinks or internal wiki-links across notes
+
+## How to Use
+
+### 1. Locate the vault
+
+Obsidian vaults are folders containing `.md` files and a `.obsidian/` config dir. Ask the user for the vault path or search common locations.
+
+```powershell
+# Find Obsidian vaults on Windows (searches common locations)
+Get-ChildItem "$env:USERPROFILE" -Recurse -Filter ".obsidian" -Directory -ErrorAction SilentlyContinue |
+  Select-Object -ExpandProperty Parent | Select-Object FullName
+```
+
+### 2. Search notes by keyword
+
+```powershell
+# Full-text search across all notes in vault
+$vault = "C:\Users\shiva\Documents\MyVault"
+Get-ChildItem $vault -Recurse -Filter "*.md" |
+  Select-String -Pattern "your keyword" -SimpleMatch |
+  Select-Object Path, LineNumber, Line |
+  Format-Table -AutoSize
+```
+
+### 3. Search notes by tag
+
+Obsidian tags appear as `#tag` in note body or `tags: [tag]` in frontmatter.
+
+```powershell
+$vault = "C:\Users\shiva\Documents\MyVault"
+$tag   = "project"
+Get-ChildItem $vault -Recurse -Filter "*.md" |
+  Select-String -Pattern "#$tag\b|tags:.*\b$tag\b" -SimpleMatch:$false |
+  Select-Object Path | Sort-Object Path -Unique
+```
+
+### 4. Read a specific note
+
+```powershell
+$note = "C:\Users\shiva\Documents\MyVault\Daily\2026-04-17.md"
+Get-Content $note -Raw
+```
+
+### 5. Create a new note
+
+```powershell
+$vault   = "C:\Users\shiva\Documents\MyVault"
+$folder  = "Projects"
+$title   = "New Project Idea"
+$date    = Get-Date -Format "yyyy-MM-dd"
+$content = @"
+---
+title: $title
+date: $date
+tags: [project, idea]
+---
+
+# $title
+
+Write your note content here.
+"@
+$path = Join-Path $vault $folder "$title.md"
+New-Item -ItemType Directory -Force -Path (Split-Path $path) | Out-Null
+Set-Content -Path $path -Value $content -Encoding UTF8
+Write-Host "Created: $path"
+```
+
+### 6. Find all backlinks to a note
+
+```powershell
+$vault    = "C:\Users\shiva\Documents\MyVault"
+$noteName = "Index"   # without .md
+Get-ChildItem $vault -Recurse -Filter "*.md" |
+  Select-String -Pattern "\[\[$noteName(\|[^\]]*)?\]\]" |
+  Select-Object Path | Sort-Object Path -Unique
+```
+
+## Examples
+
+**"Search my Obsidian vault for notes about async/await"**
+→ Use step 2 with keyword `async/await`. Ask user for vault path first if not known.
+
+**"Create a daily note for today in my vault"**
+→ Use step 5 with folder `Daily`, title as today's date `2026-04-17`, and standard daily note frontmatter.
+
+**"Find all notes tagged #book-review in my vault"**
+→ Use step 3 with tag `book-review`.
+
+## Cautions
+
+- Never delete notes without explicit user confirmation — deletions are hard to recover
+- Obsidian vaults can be very large; use `-Recurse` with care on deep vault trees
+- The `.obsidian/` directory contains config/plugins — do not modify it
+- If the user has Obsidian open, writing files simultaneously is safe (Obsidian watches for changes), but avoid writing the same file from two places at once

package/workspace-templates/skills/obsidian/skill.json

@@ -0,0 +1,24 @@
+{
+  "name": "obsidian",
+  "version": "1.0.0",
+  "description": "Read, search, and create notes in Obsidian vaults using file system operations and CLI tools",
+  "author": "aiden",
+  "license": "MIT",
+  "tools": [],
+  "trigger_phrases": [],
+  "compatible_agents": [
+    "aiden"
+  ],
+  "min_agent_version": "3.0.0",
+  "tags": [
+    "obsidian",
+    "notes",
+    "vault",
+    "markdown",
+    "knowledge-base",
+    "zettelkasten",
+    "wiki",
+    "pkm"
+  ],
+  "created": "2026-04-27T17:11:40.306Z"
+}

package/workspace-templates/skills/ocr-and-documents/SKILL.md

@@ -0,0 +1,125 @@
+---
+name: ocr-and-documents
+description: Extract text from PDFs, images, scans, and Word documents using Python libraries and CLI tools
+category: productivity
+version: 1.0.0
+origin: aiden
+license: Apache-2.0
+tags: ocr, pdf, image, text-extraction, documents, docx, scan, pymupdf, tesseract, pdf-parse
+---
+
+# OCR and Document Text Extraction
+
+Extract readable text from PDFs, scanned images, and Word documents using Python libraries available in most environments. No cloud API required.
+
+## When to Use
+
+- User wants to read text from a PDF file
+- User wants to extract text from a scanned image or photo of a document
+- User wants to read a `.docx` Word document programmatically
+- User wants to convert a multi-page document to plain text for analysis
+- User wants to extract specific pages or sections from a PDF
+
+## How to Use
+
+### 1. Extract text from a PDF (pymupdf — fastest)
+
+```python
+import fitz  # pip install pymupdf
+
+doc  = fitz.open("document.pdf")
+text = "\n\n".join(page.get_text() for page in doc)
+print(text[:2000])  # preview first 2000 chars
+doc.close()
+```
+
+### 2. Extract text from a PDF (pdf-parse via Node.js)
+
+```javascript
+// requires: npm install pdf-parse (already in DevOS dependencies)
+const pdfParse = require('pdf-parse')
+const fs       = require('fs')
+const data     = await pdfParse(fs.readFileSync('document.pdf'))
+console.log(data.text.slice(0, 2000))
+console.log(`Pages: ${data.numpages}`)
+```
+
+### 3. OCR a scanned image (Tesseract)
+
+Requires Tesseract installed: `winget install UB-Mannheim.TesseractOCR`
+
+```python
+import pytesseract          # pip install pytesseract
+from PIL import Image       # pip install Pillow
+
+img  = Image.open("scan.png")
+text = pytesseract.image_to_string(img, lang="eng")
+print(text)
+```
+
+### 4. OCR with preprocessing for better accuracy
+
+```python
+import pytesseract
+from PIL import Image, ImageFilter, ImageOps
+
+img = Image.open("scan.jpg")
+img = ImageOps.grayscale(img)
+img = img.filter(ImageFilter.SHARPEN)
+img = img.point(lambda p: 255 if p > 128 else 0)  # binarize
+text = pytesseract.image_to_string(img, config="--psm 6")
+print(text)
+```
+
+### 5. Extract text from a Word .docx file
+
+```python
+from docx import Document   # pip install python-docx
+
+doc   = Document("report.docx")
+paras = [p.text for p in doc.paragraphs if p.text.strip()]
+text  = "\n".join(paras)
+print(text)
+```
+
+### 6. Extract a specific page range from a PDF
+
+```python
+import fitz
+
+doc    = fitz.open("big_report.pdf")
+pages  = range(4, 9)   # pages 5-9 (0-indexed)
+text   = "\n\n".join(doc[i].get_text() for i in pages)
+print(text)
+```
+
+### 7. Extract tables from a PDF
+
+```python
+import pdfplumber   # pip install pdfplumber
+
+with pdfplumber.open("financial_report.pdf") as pdf:
+  for page in pdf.pages:
+    for table in page.extract_tables():
+      for row in table:
+        print("\t".join(str(cell or "") for cell in row))
+```
+
+## Examples
+
+**"Read the text from this PDF contract"**
+→ Use step 1 (pymupdf) or step 2 (pdf-parse) depending on whether Python or Node is preferred.
+
+**"Extract the table from page 3 of this quarterly report PDF"**
+→ Use step 7 (pdfplumber) targeting `pdf.pages[2]` for page 3.
+
+**"Read the text from this scanned invoice image"**
+→ Use step 3 or 4 (Tesseract). For low-quality scans, use step 4 with preprocessing.
+
+## Cautions
+
+- Scanned PDFs (image-only) have no embedded text — Tesseract OCR is required
+- Tesseract accuracy drops on handwriting, decorative fonts, or low-resolution images (< 150 DPI)
+- pymupdf (`fitz`) extracts only programmatically embedded text — it won't OCR scanned pages
+- Large PDFs can use significant memory — process page by page for files > 100 MB
+- For non-English text, specify the language code in Tesseract: `lang="hin"` for Hindi, `"deu"` for German

package/workspace-templates/skills/ocr-and-documents/skill.json

@@ -0,0 +1,26 @@
+{
+  "name": "ocr-and-documents",
+  "version": "1.0.0",
+  "description": "Extract text from PDFs, images, scans, and Word documents using Python libraries and CLI tools",
+  "author": "aiden",
+  "license": "MIT",
+  "tools": [],
+  "trigger_phrases": [],
+  "compatible_agents": [
+    "aiden"
+  ],
+  "min_agent_version": "3.0.0",
+  "tags": [
+    "ocr",
+    "pdf",
+    "image",
+    "text-extraction",
+    "documents",
+    "docx",
+    "scan",
+    "pymupdf",
+    "tesseract",
+    "pdf-parse"
+  ],
+  "created": "2026-04-27T17:11:40.330Z"
+}