reclaim-tasks
About
This Claude Skill enables developers to manage tasks in Reclaim.ai via the `reclaim` CLI, handling CRUD operations like creating, updating, listing, completing, and deleting tasks. It is used for working with calendar scheduling, task priorities, time blocking, and task duration management. Before use, developers must ensure the CLI is installed and must follow a mandatory confirmation workflow for all write operations.
Documentation
Reclaim Tasks
Manage CRUD operations for tasks in Reclaim.ai using the reclaim CLI.
Installation Check
IMPORTANT: Before using any Reclaim commands, always check if the reclaim CLI is installed:
which reclaim
If not installed, install it automatically based on the system:
All systems (requires Ruby):
gem install reclaim
If automatic installation fails, inform the user that they need to install Ruby first, then run gem install reclaim.
After installation, verify it works:
reclaim --help
Mandatory Confirmation Workflow
CRITICAL: For ALL write operations (create, update, complete, delete), you MUST:
- Parse the user's request and construct the
reclaimcommand - Use the AskUserQuestion tool to show the command and get confirmation
- Only execute the command after user approval
Read operations (list, get, list-schemes) can execute immediately without confirmation.
Quick Command Reference
Read Operations (no confirmation needed)
reclaim # List active tasks (default)
reclaim list active # List active tasks (explicit)
reclaim list completed # List completed tasks
reclaim list overdue # List overdue tasks
reclaim get TASK_ID # Get task details
reclaim list-schemes # List available time schemes
Write Operations (REQUIRE confirmation)
# Create
reclaim create --title "TITLE" [OPTIONS]
# Update
reclaim update TASK_ID [OPTIONS]
# Complete
reclaim complete TASK_ID
# Delete
reclaim delete TASK_ID
Common Options
--title TITLE- Task title--due DATE- Due date (YYYY-MM-DD or YYYY-MM-DDTHH:MM:SS, or "none" to clear)--priority P1|P2|P3|P4- Task priority--duration HOURS- Duration in hours (0.25 = 15min, 1.5 = 90min)--split [CHUNK_SIZE]- Allow task splitting (optional min chunk size)--defer DATE- Start after this date (or "none" to clear)--start DATE- Specific start time (or "none" to clear)--time-scheme SCHEME- Time scheme ID or alias (work, personal, etc.)--notes TEXT- Task notes/description
Example Workflow with Confirmation
User request: "Create a task called 'Write proposal' due Friday, P1 priority, 3 hours"
Your response:
- Construct command:
reclaim create --title "Write proposal" --due 2025-11-07 --priority P1 --duration 3 - Use AskUserQuestion to confirm:
Ready to create this Reclaim task: Command: reclaim create --title "Write proposal" --due 2025-11-07 --priority P1 --duration 3 This will create a P1 task with 3 hours duration due on 2025-11-07. Proceed? - After approval, execute the command
Additional Resources
- EXAMPLES.md - Comprehensive examples for all workflows
- REFERENCE.md - Complete option and command reference
Date Formats
- Standard:
YYYY-MM-DD(e.g., 2025-11-07) - With time:
YYYY-MM-DDTHH:MM:SS(e.g., 2025-11-07T14:30:00) - Clear date:
none,clear, ornull
Priority Levels
P1- Highest priorityP2- High priorityP3- Medium priorityP4- Low priority
Time Scheme Aliases
work,working hours,business hours→ Work time schemespersonal,off hours,private→ Personal time schemes
Understanding Task Status
CRITICAL: The reclaim list active output shows status COMPLETE with checkmarks (✓) for tasks that are
done scheduling (past their assigned time blocks), NOT tasks that are marked as "done".
- Status: COMPLETE in API (✓ symbol) = Task's scheduled time is in the past
- Status: SCHEDULED (○ symbol) = Task's scheduled time is in the future
A task is only truly "done" after you run reclaim complete TASK_ID. Until then, all tasks in
the active list are open work items, regardless of checkmarks or "COMPLETE" status in the API
response.
Quick Install
/plugin add https://github.com/benjaminjackson/reclaim-skills/tree/main/reclaim-tasksCopy and paste this command in Claude Code to install this skill
GitHub 仓库
Related Skills
sglang
MetaSGLang is a high-performance LLM serving framework that specializes in fast, structured generation for JSON, regex, and agentic workflows using its RadixAttention prefix caching. It delivers significantly faster inference, especially for tasks with repeated prefixes, making it ideal for complex, structured outputs and multi-turn conversations. Choose SGLang over alternatives like vLLM when you need constrained decoding or are building applications with extensive prefix sharing.
evaluating-llms-harness
TestingThis Claude Skill runs the lm-evaluation-harness to benchmark LLMs across 60+ standardized academic tasks like MMLU and GSM8K. It's designed for developers to compare model quality, track training progress, or report academic results. The tool supports various backends including HuggingFace and vLLM models.
llamaguard
OtherLlamaGuard is Meta's 7-8B parameter model for moderating LLM inputs and outputs across six safety categories like violence and hate speech. It offers 94-95% accuracy and can be deployed using vLLM, Hugging Face, or Amazon SageMaker. Use this skill to easily integrate content filtering and safety guardrails into your AI applications.
langchain
MetaLangChain is a framework for building LLM applications using agents, chains, and RAG pipelines. It supports multiple LLM providers, offers 500+ integrations, and includes features like tool calling and memory management. Use it for rapid prototyping and deploying production systems like chatbots, autonomous agents, and question-answering services.
