gkt-node 3.3.0

package/assets/.agent/skills/trello-automation/SKILL.md

@@ -0,0 +1,181 @@
+---
+name: trello-automation
+description: "Automate Trello boards, cards, and workflows via Rube MCP (Composio). Create cards, manage lists, assign members, and search across boards programmatically."
+requires:
+  mcp: [rube]
+---
+
+# Trello Automation via Rube MCP
+
+Automate Trello board management, card creation, and team workflows through Composio's Rube MCP integration.
+
+## Prerequisites
+
+- Rube MCP must be connected (RUBE_SEARCH_TOOLS available)
+- Active Trello connection via `RUBE_MANAGE_CONNECTIONS` with toolkit `trello`
+- Always call `RUBE_SEARCH_TOOLS` first to get current tool schemas
+
+## Setup
+
+**Get Rube MCP**: Add `https://rube.app/mcp` as an MCP server in your client configuration. No API keys needed — just add the endpoint and it works.
+
+
+1. Verify Rube MCP is available by confirming `RUBE_SEARCH_TOOLS` responds
+2. Call `RUBE_MANAGE_CONNECTIONS` with toolkit `trello`
+3. If connection is not ACTIVE, follow the returned auth link to complete Trello auth
+4. Confirm connection status shows ACTIVE before running any workflows
+
+## Core Workflows
+
+### 1. Create a Card on a Board
+
+**When to use**: User wants to add a new card/task to a Trello board
+
+**Tool sequence**:
+1. `TRELLO_GET_MEMBERS_BOARDS_BY_ID_MEMBER` - List boards to find target board ID [Prerequisite]
+2. `TRELLO_GET_BOARDS_LISTS_BY_ID_BOARD` - Get lists on board to find target list ID [Prerequisite]
+3. `TRELLO_ADD_CARDS` - Create the card on the resolved list [Required]
+4. `TRELLO_ADD_CARDS_CHECKLISTS_BY_ID_CARD` - Add a checklist to the card [Optional]
+5. `TRELLO_ADD_CARDS_CHECKLIST_CHECK_ITEM_BY_ID_CARD_BY_ID_CHECKLIST` - Add items to the checklist [Optional]
+
+**Key parameters**:
+- `idList`: 24-char hex ID (NOT list name)
+- `name`: Card title
+- `desc`: Card description (supports Markdown)
+- `pos`: Position ('top'/'bottom')
+- `due`: Due date (ISO 8601 format)
+
+**Pitfalls**:
+- Store returned id (idCard) immediately; downstream checklist operations fail without it
+- Checklist payload may be nested (data.data); extract idChecklist from inner object
+- One API call per checklist item; large checklists can trigger rate limits
+
+### 2. Manage Boards and Lists
+
+**When to use**: User wants to view, browse, or restructure board layout
+
+**Tool sequence**:
+1. `TRELLO_GET_MEMBERS_BOARDS_BY_ID_MEMBER` - List all boards for the user [Required]
+2. `TRELLO_GET_BOARDS_BY_ID_BOARD` - Get detailed board info [Required]
+3. `TRELLO_GET_BOARDS_LISTS_BY_ID_BOARD` - Get lists (columns) on the board [Optional]
+4. `TRELLO_GET_BOARDS_MEMBERS_BY_ID_BOARD` - Get board members [Optional]
+5. `TRELLO_GET_BOARDS_LABELS_BY_ID_BOARD` - Get labels on the board [Optional]
+
+**Key parameters**:
+- `idMember`: Use 'me' for authenticated user
+- `filter`: 'open', 'starred', or 'all'
+- `idBoard`: 24-char hex or 8-char shortLink (NOT board name)
+
+**Pitfalls**:
+- Some runs return boards under response.data.details[]—don't assume flat top-level array
+- Lists may be nested under results[0].response.data.details—parse defensively
+- ISO 8601 timestamps with trailing 'Z' must be parsed as timezone-aware
+
+### 3. Move Cards Between Lists
+
+**When to use**: User wants to change a card's status by moving it to another list
+
+**Tool sequence**:
+1. `TRELLO_GET_SEARCH` - Find the card by name or keyword [Prerequisite]
+2. `TRELLO_GET_BOARDS_LISTS_BY_ID_BOARD` - Get destination list ID [Prerequisite]
+3. `TRELLO_UPDATE_CARDS_BY_ID_CARD` - Update card's idList to move it [Required]
+
+**Key parameters**:
+- `idCard`: Card ID from search
+- `idList`: Destination list ID
+- `pos`: Optional ordering within new list
+
+**Pitfalls**:
+- Search returns partial matches; verify card name before updating
+- Moving doesn't update position within new list; set pos if ordering matters
+
+### 4. Assign Members to Cards
+
+**When to use**: User wants to assign team members to cards
+
+**Tool sequence**:
+1. `TRELLO_GET_BOARDS_MEMBERS_BY_ID_BOARD` - Get member IDs from the board [Prerequisite]
+2. `TRELLO_ADD_CARDS_ID_MEMBERS_BY_ID_CARD` - Add a member to the card [Required]
+
+**Key parameters**:
+- `idCard`: Target card ID
+- `value`: Member ID to assign
+
+**Pitfalls**:
+- UPDATE_CARDS_ID_MEMBERS replaces entire member list; use ADD_CARDS_ID_MEMBERS to append
+- Member must have board permissions
+
+### 5. Search and Filter Cards
+
+**When to use**: User wants to find specific cards across boards
+
+**Tool sequence**:
+1. `TRELLO_GET_SEARCH` - Search by query string [Required]
+
+**Key parameters**:
+- `query`: Search string (supports board:, list:, label:, is:open/archived operators)
+- `modelTypes`: Set to 'cards'
+- `partial`: Set to 'true' for prefix matching
+
+**Pitfalls**:
+- Search indexing has delay; newly created cards may not appear for several minutes
+- For exact name matching, use TRELLO_GET_BOARDS_CARDS_BY_ID_BOARD and filter locally
+- Query uses word tokenization; common words may be ignored as stop words
+
+### 6. Add Comments and Attachments
+
+**When to use**: User wants to add context to an existing card
+
+**Tool sequence**:
+1. `TRELLO_ADD_CARDS_ACTIONS_COMMENTS_BY_ID_CARD` - Post a comment on the card [Required]
+2. `TRELLO_ADD_CARDS_ATTACHMENTS_BY_ID_CARD` - Attach a file or URL [Optional]
+
+**Key parameters**:
+- `text`: Comment text (1-16384 chars, supports Markdown and @mentions)
+- `url` OR `file`: Attachment source (not both)
+- `name`: Attachment display name
+- `mimeType`: File MIME type
+
+**Pitfalls**:
+- Comments don't support file attachments; use the attachment tool separately
+- Attachment deletion is irreversible
+
+## Common Patterns
+
+### ID Resolution
+Always resolve display names to IDs before operations:
+- **Board name → Board ID**: `TRELLO_GET_MEMBERS_BOARDS_BY_ID_MEMBER` with idMember='me'
+- **List name → List ID**: `TRELLO_GET_BOARDS_LISTS_BY_ID_BOARD` with resolved board ID
+- **Card name → Card ID**: `TRELLO_GET_SEARCH` with query string
+- **Member name → Member ID**: `TRELLO_GET_BOARDS_MEMBERS_BY_ID_BOARD`
+
+### Pagination
+Most list endpoints return all items. For boards with 1000+ cards, use `limit` and `before` parameters on card listing endpoints.
+
+### Rate Limits
+300 requests per 10 seconds per token. Use `TRELLO_GET_BATCH` for bulk read operations to stay within limits.
+
+## Known Pitfalls
+
+- **ID Requirements**: Nearly every tool requires IDs, not display names. Always resolve names to IDs first.
+- **Board ID Format**: Board IDs must be 24-char hex or 8-char shortLink. URL slugs like 'my-board' are NOT valid.
+- **Search Delays**: Search indexing has delays; newly created/updated cards may not appear immediately.
+- **Nested Responses**: Response data is often nested (data.data or data.details[]); parse defensively.
+- **Rate Limiting**: 300 req/10s per token. Batch reads with TRELLO_GET_BATCH.
+
+## Quick Reference
+
+| Task | Tool Slug | Key Params |
+|------|-----------|------------|
+| List user's boards | TRELLO_GET_MEMBERS_BOARDS_BY_ID_MEMBER | idMember='me', filter='open' |
+| Get board details | TRELLO_GET_BOARDS_BY_ID_BOARD | idBoard (24-char hex) |
+| List board lists | TRELLO_GET_BOARDS_LISTS_BY_ID_BOARD | idBoard |
+| Create card | TRELLO_ADD_CARDS | idList, name, desc, pos, due |
+| Update card | TRELLO_UPDATE_CARDS_BY_ID_CARD | idCard, idList (to move) |
+| Search cards | TRELLO_GET_SEARCH | query, modelTypes='cards' |
+| Add checklist | TRELLO_ADD_CARDS_CHECKLISTS_BY_ID_CARD | idCard, name |
+| Add comment | TRELLO_ADD_CARDS_ACTIONS_COMMENTS_BY_ID_CARD | idCard, text |
+| Assign member | TRELLO_ADD_CARDS_ID_MEMBERS_BY_ID_CARD | idCard, value (member ID) |
+| Attach file/URL | TRELLO_ADD_CARDS_ATTACHMENTS_BY_ID_CARD | idCard, url OR file |
+| Get board members | TRELLO_GET_BOARDS_MEMBERS_BY_ID_BOARD | idBoard |
+| Batch read | TRELLO_GET_BATCH | urls (comma-separated paths) |

package/assets/.agent/skills/trigger-dev/SKILL.md

@@ -0,0 +1,67 @@
+---
+name: trigger-dev
+description: "Trigger.dev expert for background jobs, AI workflows, and reliable async execution with excellent developer experience and TypeScript-first design. Use when: trigger.dev, trigger dev, background task, ai background job, long running task."
+source: vibeship-spawner-skills (Apache 2.0)
+---
+
+# Trigger.dev Integration
+
+You are a Trigger.dev expert who builds reliable background jobs with
+exceptional developer experience. You understand that Trigger.dev bridges
+the gap between simple queues and complex orchestration - it's "Temporal
+made easy" for TypeScript developers.
+
+You've built AI pipelines that process for minutes, integration workflows
+that sync across dozens of services, and batch jobs that handle millions
+of records. You know the power of built-in integrations and the importance
+of proper task design.
+
+## Capabilities
+
+- trigger-dev-tasks
+- ai-background-jobs
+- integration-tasks
+- scheduled-triggers
+- webhook-handlers
+- long-running-tasks
+- task-queues
+- batch-processing
+
+## Patterns
+
+### Basic Task Setup
+
+Setting up Trigger.dev in a Next.js project
+
+### AI Task with OpenAI Integration
+
+Using built-in OpenAI integration with automatic retries
+
+### Scheduled Task with Cron
+
+Tasks that run on a schedule
+
+## Anti-Patterns
+
+### ❌ Giant Monolithic Tasks
+
+### ❌ Ignoring Built-in Integrations
+
+### ❌ No Logging
+
+## ⚠️ Sharp Edges
+
+| Issue | Severity | Solution |
+|-------|----------|----------|
+| Task timeout kills execution without clear error | critical | # Configure explicit timeouts: |
+| Non-serializable payload causes silent task failure | critical | # Always use plain objects: |
+| Environment variables not synced to Trigger.dev cloud | critical | # Sync env vars to Trigger.dev: |
+| SDK version mismatch between CLI and package | high | # Always update together: |
+| Task retries cause duplicate side effects | high | # Use idempotency keys: |
+| High concurrency overwhelms downstream services | high | # Set queue concurrency limits: |
+| trigger.config.ts not at project root | high | # Config must be at package root: |
+| wait.for in loops causes memory issues | medium | # Batch instead of individual waits: |
+
+## Related Skills
+
+Works well with: `nextjs-app-router`, `vercel-deployment`, `ai-agents-architect`, `llm-architect`, `email-systems`, `stripe-integration`

package/assets/.agent/skills/tutorial-engineer/SKILL.md

@@ -0,0 +1,139 @@
+---
+name: tutorial-engineer
+description: Creates step-by-step tutorials and educational content from code.
+  Transforms complex concepts into progressive learning experiences with
+  hands-on examples. Use PROACTIVELY for onboarding guides, feature tutorials,
+  or concept explanations.
+metadata:
+  model: sonnet
+---
+
+## Use this skill when
+
+- Working on tutorial engineer tasks or workflows
+- Needing guidance, best practices, or checklists for tutorial engineer
+
+## Do not use this skill when
+
+- The task is unrelated to tutorial engineer
+- You need a different domain or tool outside this scope
+
+## Instructions
+
+- Clarify goals, constraints, and required inputs.
+- Apply relevant best practices and validate outcomes.
+- Provide actionable steps and verification.
+- If detailed examples are required, open `resources/implementation-playbook.md`.
+
+You are a tutorial engineering specialist who transforms complex technical concepts into engaging, hands-on learning experiences. Your expertise lies in pedagogical design and progressive skill building.
+
+## Core Expertise
+
+1. **Pedagogical Design**: Understanding how developers learn and retain information
+2. **Progressive Disclosure**: Breaking complex topics into digestible, sequential steps
+3. **Hands-On Learning**: Creating practical exercises that reinforce concepts
+4. **Error Anticipation**: Predicting and addressing common mistakes
+5. **Multiple Learning Styles**: Supporting visual, textual, and kinesthetic learners
+
+## Tutorial Development Process
+
+1. **Learning Objective Definition**
+   - Identify what readers will be able to do after the tutorial
+   - Define prerequisites and assumed knowledge
+   - Create measurable learning outcomes
+
+2. **Concept Decomposition**
+   - Break complex topics into atomic concepts
+   - Arrange in logical learning sequence
+   - Identify dependencies between concepts
+
+3. **Exercise Design**
+   - Create hands-on coding exercises
+   - Build from simple to complex
+   - Include checkpoints for self-assessment
+
+## Tutorial Structure
+
+### Opening Section
+- **What You'll Learn**: Clear learning objectives
+- **Prerequisites**: Required knowledge and setup
+- **Time Estimate**: Realistic completion time
+- **Final Result**: Preview of what they'll build
+
+### Progressive Sections
+1. **Concept Introduction**: Theory with real-world analogies
+2. **Minimal Example**: Simplest working implementation
+3. **Guided Practice**: Step-by-step walkthrough
+4. **Variations**: Exploring different approaches
+5. **Challenges**: Self-directed exercises
+6. **Troubleshooting**: Common errors and solutions
+
+### Closing Section
+- **Summary**: Key concepts reinforced
+- **Next Steps**: Where to go from here
+- **Additional Resources**: Deeper learning paths
+
+## Writing Principles
+
+- **Show, Don't Tell**: Demonstrate with code, then explain
+- **Fail Forward**: Include intentional errors to teach debugging
+- **Incremental Complexity**: Each step builds on the previous
+- **Frequent Validation**: Readers should run code often
+- **Multiple Perspectives**: Explain the same concept different ways
+
+## Content Elements
+
+### Code Examples
+- Start with complete, runnable examples
+- Use meaningful variable and function names
+- Include inline comments for clarity
+- Show both correct and incorrect approaches
+
+### Explanations
+- Use analogies to familiar concepts
+- Provide the "why" behind each step
+- Connect to real-world use cases
+- Anticipate and answer questions
+
+### Visual Aids
+- Diagrams showing data flow
+- Before/after comparisons
+- Decision trees for choosing approaches
+- Progress indicators for multi-step processes
+
+## Exercise Types
+
+1. **Fill-in-the-Blank**: Complete partially written code
+2. **Debug Challenges**: Fix intentionally broken code
+3. **Extension Tasks**: Add features to working code
+4. **From Scratch**: Build based on requirements
+5. **Refactoring**: Improve existing implementations
+
+## Common Tutorial Formats
+
+- **Quick Start**: 5-minute introduction to get running
+- **Deep Dive**: 30-60 minute comprehensive exploration
+- **Workshop Series**: Multi-part progressive learning
+- **Cookbook Style**: Problem-solution pairs
+- **Interactive Labs**: Hands-on coding environments
+
+## Quality Checklist
+
+- Can a beginner follow without getting stuck?
+- Are concepts introduced before they're used?
+- Is each code example complete and runnable?
+- Are common errors addressed proactively?
+- Does difficulty increase gradually?
+- Are there enough practice opportunities?
+
+## Output Format
+
+Generate tutorials in Markdown with:
+- Clear section numbering
+- Code blocks with expected output
+- Info boxes for tips and warnings
+- Progress checkpoints
+- Collapsible sections for solutions
+- Links to working code repositories
+
+Remember: Your goal is to create tutorials that transform learners from confused to confident, ensuring they not only understand the code but can apply concepts independently.

package/assets/.agent/skills/twitter-automation/SKILL.md

@@ -0,0 +1,231 @@
+---
+name: twitter-automation
+description: "Automate Twitter/X tasks via Rube MCP (Composio): posts, search, users, bookmarks, lists, media. Always search tools first for current schemas."
+requires:
+  mcp: [rube]
+---
+
+# Twitter/X Automation via Rube MCP
+
+Automate Twitter/X operations through Composio's Twitter toolkit via Rube MCP.
+
+## Prerequisites
+
+- Rube MCP must be connected (RUBE_SEARCH_TOOLS available)
+- Active Twitter connection via `RUBE_MANAGE_CONNECTIONS` with toolkit `twitter`
+- Always call `RUBE_SEARCH_TOOLS` first to get current tool schemas
+
+## Setup
+
+**Get Rube MCP**: Add `https://rube.app/mcp` as an MCP server in your client configuration. No API keys needed — just add the endpoint and it works.
+
+
+1. Verify Rube MCP is available by confirming `RUBE_SEARCH_TOOLS` responds
+2. Call `RUBE_MANAGE_CONNECTIONS` with toolkit `twitter`
+3. If connection is not ACTIVE, follow the returned auth link to complete Twitter OAuth
+4. Confirm connection status shows ACTIVE before running any workflows
+
+## Core Workflows
+
+### 1. Create and Manage Posts
+
+**When to use**: User wants to create, delete, or look up tweets/posts
+
+**Tool sequence**:
+1. `TWITTER_USER_LOOKUP_ME` - Get authenticated user info [Prerequisite]
+2. `TWITTER_UPLOAD_MEDIA` / `TWITTER_UPLOAD_LARGE_MEDIA` - Upload media [Optional]
+3. `TWITTER_CREATION_OF_A_POST` - Create a new post [Required]
+4. `TWITTER_POST_LOOKUP_BY_POST_ID` - Look up a specific post [Optional]
+5. `TWITTER_POST_DELETE_BY_POST_ID` - Delete a post [Optional]
+
+**Key parameters**:
+- `text`: Post text content (max 280 weighted characters)
+- `media__media_ids`: Array of media ID strings for attachments
+- `reply__in_reply_to_tweet_id`: Tweet ID to reply to
+- `quote_tweet_id`: Tweet ID to quote
+- `id`: Post ID for lookup/delete
+
+**Pitfalls**:
+- Post text is limited to 280 weighted characters; some characters count as more than one
+- Posting is NOT idempotent; retrying on timeout will create duplicate posts
+- Media IDs must be numeric strings, not integers
+- UPLOAD_LARGE_MEDIA is for videos/GIFs; UPLOAD_MEDIA for images
+- Always call USER_LOOKUP_ME first to get the authenticated user's ID
+
+### 2. Search Posts
+
+**When to use**: User wants to find tweets matching specific criteria
+
+**Tool sequence**:
+1. `TWITTER_RECENT_SEARCH` - Search recent tweets (last 7 days) [Required]
+2. `TWITTER_FULL_ARCHIVE_SEARCH` - Search full archive (Academic access) [Optional]
+3. `TWITTER_RECENT_SEARCH_COUNTS` - Get tweet count matching query [Optional]
+
+**Key parameters**:
+- `query`: Search query using Twitter search operators
+- `max_results`: Results per page (10-100)
+- `next_token`: Pagination token
+- `start_time`/`end_time`: ISO 8601 time range
+- `tweet__fields`: Comma-separated fields to include
+- `expansions`: Related objects to expand
+
+**Pitfalls**:
+- RECENT_SEARCH covers only the last 7 days; use FULL_ARCHIVE_SEARCH for older tweets
+- FULL_ARCHIVE_SEARCH requires Academic Research or Enterprise access
+- Query operators: `from:username`, `to:username`, `is:retweet`, `has:media`, `-is:retweet`
+- Empty results return `meta.result_count: 0` with no `data` field
+- Rate limits vary by endpoint and access level; check response headers
+
+### 3. Look Up Users
+
+**When to use**: User wants to find or inspect Twitter user profiles
+
+**Tool sequence**:
+1. `TWITTER_USER_LOOKUP_ME` - Get authenticated user [Optional]
+2. `TWITTER_USER_LOOKUP_BY_USERNAME` - Look up by username [Optional]
+3. `TWITTER_USER_LOOKUP_BY_ID` - Look up by user ID [Optional]
+4. `TWITTER_USER_LOOKUP_BY_IDS` - Batch look up multiple users [Optional]
+
+**Key parameters**:
+- `username`: Twitter handle without @ prefix
+- `id`: Numeric user ID string
+- `ids`: Comma-separated user IDs for batch lookup
+- `user__fields`: Fields to return (description, public_metrics, etc.)
+
+**Pitfalls**:
+- Usernames are case-insensitive but must not include the @ prefix
+- User IDs are numeric strings, not integers
+- Suspended or deleted accounts return errors, not empty results
+- LOOKUP_BY_IDS accepts max 100 IDs per request
+
+### 4. Manage Bookmarks
+
+**When to use**: User wants to save, view, or remove bookmarked tweets
+
+**Tool sequence**:
+1. `TWITTER_USER_LOOKUP_ME` - Get authenticated user ID [Prerequisite]
+2. `TWITTER_BOOKMARKS_BY_USER` - List bookmarked posts [Required]
+3. `TWITTER_ADD_POST_TO_BOOKMARKS` - Bookmark a post [Optional]
+4. `TWITTER_REMOVE_A_BOOKMARKED_POST` - Remove bookmark [Optional]
+
+**Key parameters**:
+- `id`: User ID (from USER_LOOKUP_ME) for listing bookmarks
+- `tweet_id`: Tweet ID to bookmark or unbookmark
+- `max_results`: Results per page
+- `pagination_token`: Token for next page
+
+**Pitfalls**:
+- Bookmarks require the authenticated user's ID, not username
+- Bookmarks are private; only the authenticated user can see their own
+- Pagination uses `pagination_token`, not `next_token`
+
+### 5. Manage Lists
+
+**When to use**: User wants to view or manage Twitter lists
+
+**Tool sequence**:
+1. `TWITTER_USER_LOOKUP_ME` - Get authenticated user ID [Prerequisite]
+2. `TWITTER_GET_A_USER_S_OWNED_LISTS` - List owned lists [Optional]
+3. `TWITTER_GET_A_USER_S_LIST_MEMBERSHIPS` - List memberships [Optional]
+4. `TWITTER_GET_A_USER_S_PINNED_LISTS` - Get pinned lists [Optional]
+5. `TWITTER_GET_USER_S_FOLLOWED_LISTS` - Get followed lists [Optional]
+6. `TWITTER_LIST_LOOKUP_BY_LIST_ID` - Get list details [Optional]
+
+**Key parameters**:
+- `id`: User ID for listing owned/member/followed lists
+- `list_id`: List ID for specific list lookup
+- `max_results`: Results per page (1-100)
+
+**Pitfalls**:
+- List IDs and User IDs are numeric strings
+- Lists endpoints require the user's numeric ID, not username
+
+### 6. Interact with Posts
+
+**When to use**: User wants to like, unlike, or view liked posts
+
+**Tool sequence**:
+1. `TWITTER_USER_LOOKUP_ME` - Get authenticated user ID [Prerequisite]
+2. `TWITTER_RETURNS_POST_OBJECTS_LIKED_BY_THE_PROVIDED_USER_ID` - Get liked posts [Optional]
+3. `TWITTER_UNLIKE_POST` - Unlike a post [Optional]
+
+**Key parameters**:
+- `id`: User ID for listing liked posts
+- `tweet_id`: Tweet ID to unlike
+
+**Pitfalls**:
+- Like/unlike endpoints require user ID from USER_LOOKUP_ME
+- Liked posts pagination may be slow for users with many likes
+
+## Common Patterns
+
+### Search Query Syntax
+
+**Operators**:
+- `from:username` - Posts by user
+- `to:username` - Replies to user
+- `@username` - Mentions user
+- `#hashtag` - Contains hashtag
+- `"exact phrase"` - Exact match
+- `has:media` - Contains media
+- `has:links` - Contains links
+- `is:retweet` / `-is:retweet` - Include/exclude retweets
+- `is:reply` / `-is:reply` - Include/exclude replies
+- `lang:en` - Language filter
+
+**Combinators**:
+- Space for AND
+- `OR` for either condition
+- `-` prefix for NOT
+- Parentheses for grouping
+
+### Media Upload Flow
+
+```
+1. Upload media with TWITTER_UPLOAD_MEDIA (images) or TWITTER_UPLOAD_LARGE_MEDIA (video/GIF)
+2. Get media_id from response
+3. Pass media_id as string in media__media_ids array to TWITTER_CREATION_OF_A_POST
+```
+
+## Known Pitfalls
+
+**Character Limits**:
+- Standard posts: 280 weighted characters
+- Some Unicode characters count as more than 1
+- URLs are shortened and count as fixed length (23 characters)
+
+**Rate Limits**:
+- Vary significantly by access tier (Free, Basic, Pro, Enterprise)
+- Free tier: very limited (e.g., 1,500 posts/month)
+- Check `x-rate-limit-remaining` header in responses
+
+**Idempotency**:
+- Post creation is NOT idempotent; duplicate posts will be created on retry
+- Implement deduplication logic for automated posting
+
+## Quick Reference
+
+| Task | Tool Slug | Key Params |
+|------|-----------|------------|
+| Create post | TWITTER_CREATION_OF_A_POST | text |
+| Delete post | TWITTER_POST_DELETE_BY_POST_ID | id |
+| Look up post | TWITTER_POST_LOOKUP_BY_POST_ID | id |
+| Recent search | TWITTER_RECENT_SEARCH | query |
+| Archive search | TWITTER_FULL_ARCHIVE_SEARCH | query |
+| Search counts | TWITTER_RECENT_SEARCH_COUNTS | query |
+| My profile | TWITTER_USER_LOOKUP_ME | (none) |
+| User by name | TWITTER_USER_LOOKUP_BY_USERNAME | username |
+| User by ID | TWITTER_USER_LOOKUP_BY_ID | id |
+| Users by IDs | TWITTER_USER_LOOKUP_BY_IDS | ids |
+| Upload media | TWITTER_UPLOAD_MEDIA | media |
+| Upload video | TWITTER_UPLOAD_LARGE_MEDIA | media |
+| List bookmarks | TWITTER_BOOKMARKS_BY_USER | id |
+| Add bookmark | TWITTER_ADD_POST_TO_BOOKMARKS | tweet_id |
+| Remove bookmark | TWITTER_REMOVE_A_BOOKMARKED_POST | tweet_id |
+| Unlike post | TWITTER_UNLIKE_POST | tweet_id |
+| Liked posts | TWITTER_RETURNS_POST_OBJECTS_LIKED_BY_THE_PROVIDED_USER_ID | id |
+| Owned lists | TWITTER_GET_A_USER_S_OWNED_LISTS | id |
+| List memberships | TWITTER_GET_A_USER_S_LIST_MEMBERSHIPS | id |
+| Pinned lists | TWITTER_GET_A_USER_S_PINNED_LISTS | id |
+| Followed lists | TWITTER_GET_USER_S_FOLLOWED_LISTS | id |
+| List details | TWITTER_LIST_LOOKUP_BY_LIST_ID | list_id |

package/assets/.agent/skills/typescript-pro/SKILL.md

@@ -0,0 +1,55 @@
+---
+name: typescript-pro
+description: Master TypeScript with advanced types, generics, and strict type
+  safety. Handles complex type systems, decorators, and enterprise-grade
+  patterns. Use PROACTIVELY for TypeScript architecture, type inference
+  optimization, or advanced typing patterns.
+metadata:
+  model: opus
+---
+You are a TypeScript expert specializing in advanced typing and enterprise-grade development.
+
+## Use this skill when
+
+- Designing TypeScript architectures or shared types
+- Solving complex typing, generics, or inference issues
+- Hardening type safety for production systems
+
+## Do not use this skill when
+
+- You only need JavaScript guidance
+- You cannot enforce TypeScript in the build pipeline
+- You need UI/UX design rather than type design
+
+## Instructions
+
+1. Define runtime targets and strictness requirements.
+2. Model types and contracts for critical surfaces.
+3. Implement with compiler and linting safeguards.
+4. Validate build performance and developer ergonomics.
+
+## Focus Areas
+- Advanced type systems (generics, conditional types, mapped types)
+- Strict TypeScript configuration and compiler options
+- Type inference optimization and utility types
+- Decorators and metadata programming
+- Module systems and namespace organization
+- Integration with modern frameworks (React, Node.js, Express)
+
+## Approach
+1. Leverage strict type checking with appropriate compiler flags
+2. Use generics and utility types for maximum type safety
+3. Prefer type inference over explicit annotations when clear
+4. Design robust interfaces and abstract classes
+5. Implement proper error boundaries with typed exceptions
+6. Optimize build times with incremental compilation
+
+## Output
+- Strongly-typed TypeScript with comprehensive interfaces
+- Generic functions and classes with proper constraints
+- Custom utility types and advanced type manipulations
+- Jest/Vitest tests with proper type assertions
+- TSConfig optimization for project requirements
+- Type declaration files (.d.ts) for external libraries
+
+Support both strict and gradual typing approaches. Include comprehensive TSDoc comments and maintain compatibility with latest TypeScript versions.