- name
SKILL.md
技能檔案保留在發布者的儲存庫中。
在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add google/elephant-goldfish-model --skill egm-resolve -a cursor -y在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add google/elephant-goldfish-model --skill egm-resolve -a claude-code -y在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add google/elephant-goldfish-model --skill egm-resolve -a codex -y在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add google/elephant-goldfish-model --skill egm-resolve -a grok -y在 Grok Bot 聊天中傳送複製的訊息。Bot 會從 GitHub 取得這個 SKILL.md,並加入你所有 Bot 共用的技能中。
Install this skill: https://github.com/google/elephant-goldfish-model/tree/HEAD/distributions/claude/skills/egm-resolve來自發布者
When running in Codex or ChatGPT Work, first read Codex integration.
In Claude Code or Cowork, read ${CLAUDE_PLUGIN_ROOT}/docs/claude.md first.
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.
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.Hybrid Execution UX: Detect if execution arguments are present:
Read TargetFile at LineRange by reading it and parse the FindingsList.
Give each finding exactly one category:
Apply these rules:
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:
# 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}}
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:
goldfish_review_report.md in
chat or the file and leave comments/edits to approve, reject, or contest
specific items.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):
For each item i, output a visible chat message formatting the full
finding details and explanation in rich 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):
PROPOSE FIX: Ask the user to reply with Accept proposed
fix, Skip / ignore, or Discuss.CONTEST: Ask the user to reply with Skip / agree with
contest, Overrule contest (propose fix), or Discuss.ESCALATE: Ask the user to reply with Confirm (no change),
Add the fact to the document, or Discuss.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.
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.
TargetFile, verify that the
file remains structurally coherent and valid markdown.Status: resolved line at the top).egm-review-loop)
with the count of accepted fixes, contested items, escalated items,
declined items, and remaining unaddressed issues.>-
---name: egm-resolvedescription: >----# distributions/claude/skills/egm-resolve/SKILL.md常見問題
從發布者下載 distributions/claude/skills/egm-resolve/SKILL.md,或複製路徑後開啟儲存庫。PlugMCP 只收錄這項技能,不代管檔案。
發布者將它存放在 https://github.com/google/elephant-goldfish-model。
Claude、Cursor、Codex 和 Grok Build 可以讀取你從發布者儲存庫加入的 SKILL.md。在聊天中傳送技能的 GitHub 資料夾連結,Grok Bot 就會安裝它。