← Resolve AICONTENT HISTORY

Update to Resolve AI

Snapshot Sep 30, 2026 · 22:59 UTC · version 1.0.0

Collection source: not recorded for this historical snapshot.

WHAT CHANGED · RULE-BASED ANALYSIS

First saved snapshot

No earlier snapshot is available to establish a change.

Compare saved observations

Download comparison JSON
Full technical diff · 0 changed fields
Full snapshot data
{
  "name": "steer",
  "description": "Steer a Resolve investigation by sending it a new finding, hypothesis, or directive to redirect it. Use when the user wants to promote a local observation back to Resolve — phrases like \"tell Resolve I found X\", \"steer this investigation\", \"send Resolve this observation\", or \"promote this back to Resolve\".",
  "included_files": [],
  "skill_md_contents": "---\n# Copyright 2026 Resolve AI, Inc.\n# SPDX-License-Identifier: Apache-2.0\nname: steer\ndescription: Steer a Resolve investigation by sending it a new finding, hypothesis, or directive to redirect it. Use when the user wants to promote a local observation back to Resolve — phrases like \"tell Resolve I found X\", \"steer this investigation\", \"send Resolve this observation\", or \"promote this back to Resolve\".\nversion: 0.1.0\nargument-hint: <message>\nlicense: Apache-2.0\n---\n\n# Steer Investigation\n\nSend a directive to an active investigation. This is the canonical channel for promoting local observations into Resolve's investigation flow.\n\n## Arguments\n\nIf `$ARGUMENTS` is non-empty, use it as the base of the steer message. Enrich with conversation context as below before calling `steer_investigation`.\n\nIf `$ARGUMENTS` is empty, ask the user once what they want to steer Resolve with. Treat their next reply as the base.\n\n## Enriching with conversation context\n\nBefore calling the tool, expand the base message with conversation signals **that directly support the finding being promoted**. Be ruthlessly selective:\n\n- Specific file paths or code snippets that demonstrate the finding\n- Error messages or log lines from this conversation that back up the observation\n- Git context (branch, commit) if the finding is tied to a local change\n- URLs the user referenced that informed the finding\n\nIf a piece of context doesn't strengthen the steer, leave it out.\n\n## Composing the message\n\nA good steer message is:\n\n- **Specific.** \"Latency spike correlates with the 14:52 deploy of the affected service\" beats \"I think it's the deploy.\"\n- **Anchored.** Reference times, services, files, or theory IDs from `get_investigation` when relevant.\n- **Actionable.** Either an observation Resolve should integrate, or a directive for the agent teams (\"focus on the connection pool theory\").\n- **Markdown.** Bullets, file paths, code references — anything the human side of an investigation would benefit from.\n\n## After steering\n\nEffects surface via:\n\n- The activity timeline — re-read via `read_file` on the timeline path from `get_investigation`.\n- Updated theories on next `get_investigation`.\n- **Live, if the user wants to watch the effect land:** follow any returned stream with the host's long-running command mechanism.\n"
}

SHA-256: 3fee105fffaeb3f7187ef43c85e03d59be7deee1ca72a854b80e29c5fcde2988