Monitors context window health throughout a session and rides peak context quality for maximum output fidelity. Activates automatically after plan-interview and intent-framed-agent. Stays active through execution and hands off cleanly to simplify-and-harden and self-improvement when the wave completes naturally or exits via handoff. Use this skill whenever a multi-step agent task is underway and session continuity or context drift is a concern. Especially important for long-running tasks, complex refactors, or any work where degraded context would silently corrupt the output. Trigger even if the user doesn't say "context surfing" — if an agent task is running across multiple steps with intent and a plan already established, this skill is live.

Monitors context window health throughout a session and rides peak context quality for maximum output fidelity. Activates automatically after plan-interview and intent-framed-agent. Stays active through execution and hands off cleanly to simplify-and-harden and self-improvement when the wave completes naturally or exits via handoff. Use this skill whenever a multi-step agent task is underway and session continuity or context drift is a concern. Especially important for long-running tasks, complex refactors, or any work where degraded context would silently corrupt the output. Trigger even if the user doesn't say "context surfing" — if an agent task is running across multiple steps with intent and a plan already established, this skill is live.

Handle user interaction with map views including hit testing, feature highlighting, sketching, and event handling.

Create and schedule LinkedIn posts with text, images, videos, and documents via Publora MCP

When the user needs to choose between technologies, frameworks, or tools — or says "which framework should I use", "compare X vs Y", "should we migrate from X to Y", "what database should I use", "calculate TCO".

When the user needs to review an existing contract, assess risk in proposed terms, or evaluate a contract before signing.

When the user asks for a code review, shares code for feedback, or says "review this", "check my code", "what's wrong with this". Also activate when reviewing a pull request or diff.

When the user needs to draft, review, or update terms of service for their SaaS product or web application.

When the user needs to write a monthly or quarterly investor update, prepare a board deck, or communicate company progress to stakeholders.

Automate Anchor Browser tasks via Rube MCP (Composio). Always search tools first for current schemas.

Run Codex CLI, Claude Code, OpenCode, or Pi Coding Agent via background process for programmatic control.

Send SMS messages and make outbound phone calls via Twilio