Agent skill
trello-cli
Install this agent skill to your Project
npx add-skill https://github.com/ZenoxZX/trello-cli/tree/main/plugins/trello-cli/skills/trello-cli
SKILL.md
Trello CLI
Manage Trello boards, lists, and cards using the trello-cli command.
Important Rules
- Only activate when "Trello" is mentioned - Do not interfere with Notion, Jira, or other tools
- Check JSON output after each command -
ok: truemeans success,ok: falsemeans error - Follow the workflow: First find board ID, then list ID, then perform card operations
Quick Reference
Board & List
trello-cli --get-boards # List all boards
trello-cli --get-lists <board-id> # Get lists in board
Cards
trello-cli --get-all-cards <board-id> # All cards in board
trello-cli --create-card <list-id> "<name>" # Create card
trello-cli --create-card <list-id> "<name>" --desc "<desc>" --due "2025-01-15"
trello-cli --update-card <card-id> --name "<name>" --desc "<desc>"
trello-cli --move-card <card-id> <list-id> # Move card
trello-cli --delete-card <card-id> # Delete card
trello-cli --get-comments <card-id> # Get comments
trello-cli --add-comment <card-id> "<text>" # Add comment
Attachments
trello-cli --list-attachments <card-id> # List attachments
trello-cli --upload-attachment <card-id> <file-path> [--name "<name>"]
trello-cli --attach-url <card-id> <url> [--name "<name>"]
trello-cli --delete-attachment <card-id> <attach-id>
Note: Downloading attachments is not supported - Trello's download API requires browser authentication. Use --attach-url to link attachments between cards.
Checklists
trello-cli --get-checklists <card-id> # Get checklists on card
trello-cli --create-checklist <card-id> "<name>" # Create checklist
trello-cli --delete-checklist <checklist-id> # Delete checklist
trello-cli --add-checklist-item <checklist-id> "<name>" # Add item
trello-cli --update-checklist-item <card-id> <item-id> <state> # complete/incomplete
trello-cli --delete-checklist-item <checklist-id> <item-id> # Delete item
Typical Workflows
List All Tasks
trello-cli --get-boards # → Get board ID
trello-cli --get-all-cards <id> # → See all cards
Add New Task
trello-cli --get-boards # → Get board ID
trello-cli --get-lists <id> # → Find "To Do" or "Backlog" list ID
trello-cli --create-card <list-id> "<task-name>"
Move to Done
trello-cli --get-lists <board-id> # → Find "Done" list ID
trello-cli --move-card <card-id> <done-list-id>
When Uncertain
If you encounter an error or don't know how to proceed:
trello-cli --help
For detailed command reference, see REFERENCE.md.
Example Scenarios
User: "Show my Trello tasks"
→ Run --get-boards, then --get-all-cards <board-id>
User: "Add a new task to Trello"
→ Run --get-boards, --get-lists, then --create-card
User: "Move the card to Done on Trello"
→ Run --get-lists to find Done ID, then --move-card
User: "Update the Trello card description"
→ Run --update-card <card-id> --desc "<new-desc>"
User: "Upload this file to the Trello card"
→ Run --upload-attachment <card-id> "<file-path>"
User: "Link an attachment to another Trello card"
→ Run --list-attachments <source-card-id> to get the URL, then --attach-url <target-card-id> <url>
User: "Add a checklist to this Trello card"
→ Run --create-checklist <card-id> "<checklist-name>", then --add-checklist-item for each item
User: "Mark the checklist item as done on Trello"
→ Run --update-checklist-item <card-id> <item-id> complete
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
verl-rl-training
Provides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL). Use when implementing RLHF, GRPO, PPO, or other RL algorithms for LLM post-training at scale with flexible infrastructure backends.
openrlhf-training
High-performance RLHF framework with Ray+vLLM acceleration. Use for PPO, GRPO, RLOO, DPO training of large models (7B-70B+). Built on Ray, vLLM, ZeRO-3. 2× faster than DeepSpeedChat with distributed architecture and GPU resource sharing.
gguf-quantization
GGUF format and llama.cpp quantization for efficient CPU/GPU inference. Use when deploying models on consumer hardware, Apple Silicon, or when needing flexible quantization from 2-8 bit without GPU requirements.
Claude Code Guide
Master guide for using Claude Code effectively. Includes configuration templates, prompting strategies "Thinking" keywords, debugging techniques, and best practices for interacting with the agent.
qdrant-vector-search
High-performance vector similarity search engine for RAG and semantic search. Use when building production RAG systems requiring fast nearest neighbor search, hybrid search with filtering, or scalable vector storage with Rust-powered performance.
behavioral-modes
AI operational modes (brainstorm, implement, debug, review, teach, ship, orchestrate). Use to adapt behavior based on task type.
Didn't find tool you were looking for?