Tycana Skill for Claude
Persistent task management and productivity intelligence via MCP. Captures tasks from conversation, plans your day, tracks patterns, and gives personalized recommendations that improve over time.
Install
one command, takes just this skill from the repositorynpx skills add https://github.com/davepoon/buildwithclaude --skill tycanaMCP servers it needs
declared by the author in the skill headerGives your AI assistant persistent memory and intelligence about your work patterns.
The instruction itself
5 sections, as written by the authorTycana Productivity
Tycana gives Claude persistent memory about your work across conversations. Connect once via MCP, and every session includes your tasks, projects, deadlines, blockers, and computed intelligence from your patterns.
Homepage: tycana.com
Getting started: tycana.com/getting-started
Prerequisites
- Tycana MCP server connected at
https://app.tycana.com/mcp(OAuth 2.1) - Or install the Tycana Claude plugin:
/plugin install tycana
Available Tools
| Tool | Purpose |
|------|---------|
| capture | Create tasks from conversation context |
| complete | Mark items done with outcome and notes |
| plan_day | Generate prioritized daily plan |
| what_next | Energy-aware next action recommendation |
| review | Progress summary with pattern analysis |
| get_context | Load current work context |
| search | Find items by keyword or filter |
| list_items | List items with status/project filters |
| get_item | Get full detail on a specific item |
| update_item | Modify item properties |
| relate_items | Create blocking/dependency relationships |
| remember | Store personal preferences and constraints |
| cleanup_project | Archive completed items in a project |
| delete_item | Remove an item |
Example Prompts
"Plan my day"
"Remind me to update the deployment docs before Friday"
"What should I work on next? I have about an hour and low energy"
"How's the infrastructure project going?"
"Review my week"
"Brain dump — I've got a bunch of things rattling around"
Key Features
- Capture from conversation — mention something you need to do and it's captured with effort, energy, and project inferred from context
- Computed intelligence — velocity tracking, slip detection, effort calibration that improves over time
- Energy-aware recommendations — factors in your current energy level for task suggestions
- Project graph — items connect via blocking chains and dependencies, not flat lists
Other skills for the same job
different authors, same section of the catalogue
Guide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.
Intelligently organizes your files and folders across your computer by understanding context, finding duplicates, suggesting better structures, and automating cleanup tasks. Reduces cognitive load and keeps your digital workspace tidy without manual effort.
Generates creative domain name ideas for your project and checks availability across multiple TLDs (.com, .io, .dev, .ai, etc.). Saves hours of brainstorming and manual checking.
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
Implements Manus-style file-based planning for complex tasks. Creates task_plan.md, findings.md, and progress.md. Use when starting complex multi-step tasks, research projects, or any task requiring >5 tool calls.
Creative research ideation and exploration. Use for open-ended brainstorming sessions, exploring interdisciplinary connections, challenging assumptions, or identifying research gaps. Best for early-stage research planning when you do not have specific observations yet. For formulating testable hypotheses from data use hypothesis-generation.
Comprehensive GitHub project management with swarm-coordinated issue tracking, project board automation, and sprint planning
Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".
How to use it
Take davepoon/tycana from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.