Egm Resolve

google/elephant-goldfish-model/skills/egm-resolve

by google72d06f52a2482885d9a64bd24b291c6e8628942cApache-2.021K starsListed Nov 17, 2026Updated Nov 17, 2026Repository updated today

The Elephant resolution skill. Ingests flat deficiency reports from concurrent Goldfish reviewers, applies automated fixes for PROPOSE FIX items via UI multiple-choice gates, and presents interactive negotiation/re-sync checkpoints.

AI-generated overview

Resolves reviewer deficiency findings on a document: contests, escalates, proposes fixes, and gates edits through user approval.

What it does
Takes a target file, a line range and a flat list of findings from concurrent reviewers, then assigns each finding one category: CONTEST, ESCALATE, PROPOSE FIX or DECLINE. It writes a prioritized markdown report named goldfish_review_report.md with per-finding rationale and precise proposed edits. It then pauses for the user to accept all fixes, continue without changes, walk through items one by one, or give custom instructions, applies accepted edits, and re-verifies the file before handing back counts of accepted, contested, escalated and declined items.
When to use it
Use when a document has been reviewed by multiple reviewers and their findings need triage and resolution. Suited to workflows where proposed textual fixes should be applied only after explicit human approval, and to orchestration loops that need a clean handoff summary.
Requirements
Runs as instructions only, with no bundled scripts. Needs a file-reading and file-editing tool, a writable working or artifact directory for the report, and an interactive user for the approval gate. Recommended to run in the persistent session that produced the document.

Goldfish Review: Resolve

When running in Codex or ChatGPT Work, first read Codex integration. In Claude Code or Cowork, read ${CLAUDE_PLUGIN_ROOT}/docs/claude.md first.

Overview

This skill instructs the agent on how to operate within the primary Elephant context window to parse flat deficiency reports from concurrent Goldfish reviewers. It defends accurate design choices, applies automated textual repairs, and manages interactive negotiation checkpoints.

Prerequisites & Context Strategy

  • Context Recommendation (Elephant Memory): This skill should be run in the persistent conversation session that generated the target document (the Elephant) to recall earlier reasoning and craft higher-quality fixes.

Inputs

The caller or orchestration driver provides exactly these parameters:

  • TargetFile: Absolute or relative path to target document.
  • LineRange: Exact line numbers (or full file).
  • FindingsList: Aggregated flat list of findings from Goldfish reviewers.

Execution Workflow

Step 1: Intake Validation & Gather Context

  1. Hybrid Execution UX: Detect if execution arguments are present:

    • Automated Mode: If all parameters are provided, execute silently as a subprocess.
    • Standalone Human Mode: If parameters are omitted, trigger a friendly onboarding flow. Prompt for one piece of input at a time, waiting for the user's response after each turn. Once all inputs are specified, display the final setup and verify the user is ready to continue.
  2. Read TargetFile at LineRange by reading it and parse the FindingsList.

Step 2: Evaluate & Categorize

Give each finding exactly one category:

  • CONTEST: The critique is inaccurate or relies on a misunderstanding of the codebase. Cite evidence that the reviewer could read: a file and symbol, or a decision recorded in the document.
  • ESCALATE: The critique is inaccurate, but the evidence is outside every file the reviewer could read (for example, a team convention or a verbal decision). State that fact. Do not fix the finding. Give it to the user.
  • PROPOSE FIX: The critique is valid. Define precise textual replacements or structural formatting adjustments to resolve the gap.
  • DECLINE: The finding is a Nit. Record it. Do not fix it. You can use PROPOSE FIX for a Nit if the fix is worth it.

Apply these rules:

  • A contest must be checkable. "This was intentional" is not evidence. If you cannot cite evidence the reviewer could read, use ESCALATE or PROPOSE FIX.
  • Do not add context only to satisfy a reviewer. Add context when a human reader of the document needs it. If only a zero-context subagent needs it, use ESCALATE.
  • Do not contest a comprehension gap. If a fresh reader could not follow the document, the document is missing context.
  • Do not change a severity. If you think a Blocker is a Nit, CONTEST it and state the reason.
  • You wrote the document under review. A wish to contest is not evidence that the reviewer is wrong.

Step 3: Report Fixes

Construct the final report and save it named goldfish_review_report.md in the working directory (or your harness's artifact directory, if it has one) using your file-writing tool. Use this layout:

markdown
# Goldfish Annotated Review Report
**Target:** `[TargetFile]` (`[LineRange]`)
## Prioritized Findings & AI Suggestions
{{range findings, ordered by Severity}}### [Issue 1] [`[ReviewerPersona]`] - Severity: [Blocker | Major | Nit]*   **Affected Scope:** [Lines Start-End]([RelativePath]#L[Start]-L[End]) ([Sub-header])*   **Discrepancy Description:** [copied from FindingsList]*   **Rationale:** [copied from FindingsList]*   ***AI Suggestion:*** [CONTEST | ESCALATE | PROPOSE FIX | DECLINE]*   ***Justification:*** [Detailed reason]*   ***Proposed Edit:***    *   Location: [Line/Header]    *   Change: [Precise replacement string or deletion note]{{end}}

Step 4: Interactive Resolution Gate

If any finding is ESCALATE, list those findings first in the chat message. They need the user's knowledge, not only approval.

Before proceeding, output a visible chat message to the user: *"I have compiled the audit findings into goldfish_review_report.md. Please review the findings there and choose how you would like to proceed:

  • Comment directly on the file: Review goldfish_review_report.md in chat or the file and leave comments/edits to approve, reject, or contest specific items.
  • Auto accept: Reply "auto accept" to batch-apply all proposed fixes (skipping contested items).
  • Continue to next phase: Reply "continue" or "no changes" to proceed without applying fixes.
  • Interactive breakdown: Reply "interactive breakdown" for a guided, item-by-item walkthrough in chat with detailed explanations for each proposed edit or contested finding before making decisions.
  • Custom instruction / Wildcard request: Reply with any custom instruction, question, or out-of-band request."*

You MUST immediately yield active execution by calling zero tools in this turn payload. You must stop execution and go idle, waiting for the human developer to comment on/edit the artifact or reply in the chat.

Interpret the user's action/response as follows:

  • "Auto accept" / "Accept all suggestions" / User clicks "Proceed" without contesting: Apply all fixes where the AI suggestion was PROPOSE FIX directly to TargetFile at LineRange in a single batch using your file-editing tool. Any items categorized as CONTEST, ESCALATE, or DECLINE are explicitly bypassed. Then proceed to Step 5.

  • "Continue to next phase" / "No changes": Do not apply any automated fixes. Then proceed to Step 5.

  • "Interactive breakdown": Enter a sequential breakdown loop over ALL finding items (all categories except DECLINE):

    1. For each item i, output a visible chat message formatting the full finding details and explanation in rich markdown:

      markdown
      ### Breakdown Item [i]: [Issue Title] [`[ReviewerPersona]`]* **Scope:** [Lines Start-End]([RelativePath]#L[Start]-L[End]) ([Sub-header])* **Description:** [Description]* **AI Suggestion:** [CONTEST | ESCALATE | PROPOSE FIX]* **Explanation & Justification:** [Detailed reason and background explaining why the fix is proposed or why the finding is contested]* **Proposed Edit:** [Precise replacement text or deletion note]

      Then prompt the user in chat for their decision on this item (calling zero tools and going idle):

      • If PROPOSE FIX: Ask the user to reply with Accept proposed fix, Skip / ignore, or Discuss.
      • If CONTEST: Ask the user to reply with Skip / agree with contest, Overrule contest (propose fix), or Discuss.
      • If ESCALATE: Ask the user to reply with Confirm (no change), Add the fact to the document, or Discuss.
    2. Record the user's decisions in an internal memory checklist (e.g., Item 1: Accepted, Item 2: Ignored, Item 3: Overruled). Do NOT call any file editing tools during this sequential loop.

    3. Once all items have been decided, summarize the accepted edits, execute them using your file-editing tool, and proceed to Step 5.

  • Custom instruction / Out-of-band edit: If the user provides targeted instructions, apply them and proceed.

Step 5: Post-Resolution Synchronization & Exit

  1. Re-verify Lines: If changes were made to TargetFile, verify that the file remains structurally coherent and valid markdown.
  2. Mark the report as resolved (add a Status: resolved line at the top).
  3. Handoff: Exit cleanly back to the caller (such as egm-review-loop) with the count of accepted fixes, contested items, escalated items, declined items, and remaining unaddressed issues.

Source and attribution

Source:google/elephant-goldfish-modelinskills/egm-resolveat commit72d06f5

License: Apache-2.0

Content belongs to its original authors. SourceWeft indexes it from a public repository.

Add a badge to your README

Show readers this skill is listed on SourceWeft. The badge links to this page.

Preview of the “Listed on SourceWeft” badge
[![Listed on SourceWeft](https://sourceweft.com/badge/skills/gh-google-elephant-goldfish-model-egm-resolve-skills-egm-resolve-736b313ffc9d3682.svg)](https://sourceweft.com/skills/gh-google-elephant-goldfish-model-egm-resolve-skills-egm-resolve-736b313ffc9d3682?utm_source=readme&utm_medium=badge)

Report or request removal

More from google/elephant-goldfish-model

Egm Drift Report

google

Featured

Compares design documents and READMEs against the codebase and writes a markdown report of every divergence found.

Software Development21Kupdated today

Egm Review Loop

google

Featured

Executes the Antagonistic-Review process from the Elephant-Goldfish Model (EGM) via an automated multi-agent review loop to audit documents against qualitative standards and structural templates, and automatically apply approved fixes. Use when reviewing design docs, READMEs, feature specifications, implementation plans, or verifying document completeness and tone.

Awaiting classification21Kupdated today

Egm Draft

google

Featured

Drafts a design document section-by-section using the concepts brief from egm-brainstorm (or user notes). This is the second step in the Elephant-Goldfish (EGM) feature flow. Use when you are ready to write a design doc after aligning on requirements + solution.

Awaiting classification21Kupdated today

Egm Bootstrap

google

Featured

Generates and corrects EGM-compliant README.md contract files across a repository directory tree using parallel subagents.

Documents & Office21Kupdated today

Egm Brainstorm

google

Featured

Interactive ideation and brainstorming skill for the Elephant & Goldfish Model (EGM). Helps turn half-baked concepts into structured hypotheses via clarifying questions, review, and iterative refinement. Produces an RFC summary for human review or more detailed design with egm-draft.

Awaiting classification21Kupdated today

Egm Review

google

Featured

Orchestrates the EGM Goldfish Review Protocol. Used as part of the EGM process to perform design document reviews. Executes five review phases: Initial Zoom Out Review, Comprehension Review, Design Critique, Intermediate Zoom Out Review, and Implementation Readiness.

Awaiting classification21Kupdated today