TaskcenterOpen app

Features

Live

Taskcenter Skills

Reusable procedures for agents

Skills are durable runtime instructions for repeatable workflows, tool use, design quality, and recovery paths.

Info popup

Entry route: /app/settings?tab=plugins. Status: Live. Data source: local skill catalog JSON generated from real SKILL.md files. Required permissions: workspace access through the app shell. Empty state: if no skill is selected, the library stays browsable. Failure state: unavailable skill details stay confined to the skill browser instead of blocking chat. The popup is informational only and should explain a skill, not run protected work.

Steering queue

Entry route: /app. Status: Live as local composer UI plus durable active-run steering. Data source: in-memory queued draft notes in the current browser session, and D1-backed agent_run_steering_messages when a text note is submitted while a run is active. Required permissions: the eventual chat or steering submission still uses the authenticated chat route and existing runtime authorization. Empty state: no queue is shown until a user queues a draft. Failure state: if durable steering is unavailable, the composer keeps or stages the note instead of pretending concurrent delivery succeeded.

What Northstar Is

Northstar is the project-aware orchestration layer inside TaskCenter, not a generic chatbot. It works from project state, retrieved memory layers, planning context, proposals, and recent chat history. It should turn ambiguous requests into concrete next moves, proposals, or escalation paths. It should avoid pretending work shipped, merged, or tested unless the evidence is present.

Memory Layers

TaskCenter should not rely on one long chat. The backend keeps durable project memory that agents can reload. Foundation stores the brief, repo posture, and project intent. Workflow explains how planning, proposal review, and applied state should move. Active Context keeps in-flight tasks, open proposals, and recent user intent.

How Northstar Should Choose Tools

Northstar needs a clear internal tool model so it knows when to inspect, route, plan, or escalate. Screen Read: Understand the current page, active project, visible work state, and thread context before answering. Project Retrieve: Pull grounded project state from memory layers, tasks, proposals, planning contexts, app memory, and recent messages. Evidence Inspect: Check docs, code context, connector state, runtime tool readiness, and execution evidence before claiming something is true.

Stuck Recovery

Northstar should have a rescue path for both user confusion and assistant uncertainty. If the user is blocked, say what screen they are on, what is visible, and what the next action should be. If Northstar lacks evidence, say what is missing and which view, integration, or setting would unblock it. If a task is too broad for a single reply, escalate into a structured run or proposal flow.