Update to Resolve AI

{
  "name": "ask",
  "description": "Send Resolve a question or a request to investigate — continuing an existing chat or investigation, or starting a fresh one. Use when the user wants to send a message to Resolve — phrases like \"ask Resolve about X\", \"follow up with Resolve\", \"what does Resolve think about Y\", \"have Resolve check Z\", or wants Resolve to clarify a finding.",
  "included_files": [],
  "skill_md_contents": "---\n# Copyright 2026 Resolve AI, Inc.\n# SPDX-License-Identifier: Apache-2.0\nname: ask\ndescription: Send Resolve a question or a request to investigate — continuing an existing chat or investigation, or starting a fresh one. Use when the user wants to send a message to Resolve — phrases like \"ask Resolve about X\", \"follow up with Resolve\", \"what does Resolve think about Y\", \"have Resolve check Z\", or wants Resolve to clarify a finding.\nversion: 0.1.0\nargument-hint: <message>\nlicense: Apache-2.0\n---\n\n# Ask Resolve\n\nUse when the user wants Resolve to answer a question or do more investigation work.\n\n## Arguments\n\nIf `$ARGUMENTS` is non-empty, use it as the user's base message and proceed (enrich with conversation context as below, then call `ask`).\n\nIf `$ARGUMENTS` is empty (skill invoked without a clear question), ask the user once what they want to ask Resolve. Treat their next reply as the base message.\n\n## Composing the message\n\nBefore calling `ask`, enrich the user's base message with context from the current conversation **that directly supports the specific question being asked**.\n\n**Be ruthlessly selective.** Do not dump every file you've read, every command you've run, or the conversation transcript. Include only what makes the question more answerable. If a piece of context isn't load-bearing for this specific message, leave it out.\n\nCandidates to consider (include only those tied to the question):\n\n- File paths the user opened or edited **in the path of investigating this exact issue**\n- Error messages, log lines, or stack traces that name the symptom the user is asking about\n- Git context (branch, recent commits, working changes) **when the question is about a change being made**\n- URLs the user referenced that frame this question (Slack threads, dashboards, related canvases)\n- A one-line framing of what the user is working on — only if the question doesn't stand on its own\n\nFormat the enriched message as the user's question first, then a brief `## Local context` block with only the relevant items. Most asks need 1–3 lines of context, not a dump.\n\n## Picking scope\n\nDefault to whatever investigation/chat is currently in context:\n\n- The user just engaged an investigation via `investigate` → scope the ask to it.\n- A chat is already in flight under that investigation → continue it.\n- The user switches to a different investigation mid-conversation → start fresh there.\n- No active context → standalone Resolve chat.\n\n## After asking\n\nCall `ask` with the selected scope and enriched message, then surface the returned URL.\n\nIf the response includes a `stream_command`, follow it using Codex's long-running command mechanism:\n\n- Run the command with `functions.exec_command`.\n- Request network escalation if sandbox networking blocks the stream.\n"
}