- 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-review-loop -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-review-loop -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-review-loop -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-review-loop -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-review-loop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 acts as the central orchestration engine driving the multi-agent review loop. It coordinates two distinct agent memory models:
The driver manages argument intake, resolves paths for reviewers and standards, unconditionally re-parses target line ranges before every iteration, spawns concurrent specialized Goldfish auditors based on configuration, and coordinates with the Elephant context to resolve findings.
A Goldfish runs in a fresh context with no conversation history. Spawn each
subagent with your harness's subagent tool (Antigravity: invoke_subagent; Claude Code: Agent; Codex: spawn_agent). Each subagent is defined in agents/<file>.md, and its
frontmatter name (for example egm-zoom-out) is the subagent type to request
where your harness registers named subagents. Otherwise spawn a general-purpose
subagent and tell it to read that persona file first. Pass the prompt verbatim
and wait for the report. If your harness cannot nest subagents,
use direct dispatch instead of the synthesizer. See docs/harnesses.md.
If your harness has no subagent tool, stop and tell the user: a review in the same
context is not a Goldfish review.
The caller or user provides exactly these parameters:
TargetFile: Absolute or relative path to target document.SemanticTarget: Descriptive targeting string (e.g., "Target the H4
block with SS-ID 'S1.12'"), or full file.Reviewers: List of reviewer names (shortnames or paths).Standards: Mapping of reviewer names to standard names (shortnames or
paths).GoldfishContext: A reading list (source files, directories, or
documentation URLs) fed to reviewers to establish their baseline. An empty
list from the caller counts as provided; do not ask for it again. Some
reviewers cannot open URLs, so before the first round save the raw page of
each URL as a new file in the working directory (or your harness's artifact
directory) and pass its absolute path instead. If a page cannot be saved,
ask the user for a local copy and end your turn; if no one can answer,
as in a headless run, leave it out, tell the user, and keep going.When resolving names in Reviewers and Standards:
design_critic,
structural, style, implementation_readiness,
codebase_details, comprehension, zoom_out) to agents/{name}.md.
The persona file defines the reviewer's core mandates, audit vectors, and
output format.feature-spec-standard,
implementation-readiness-standard, zoom-out-standard, heilmeier-standard,
re-implementation-standard) to resources/document_standards/{name}.md./), treat it as an
absolute or workspace-relative path and read it directly.Evaluate the provided inputs (TargetFile, SemanticTarget, Reviewers,
Standards, GoldfishContext).
design_critic (mapped to
resources/document_standards/feature-spec-standard.md) and
structural (mapped to resources/document_standards/feature-spec-standard.md).implementation_readiness
(mapped to resources/document_standards/implementation-readiness-standard.md)
and codebase_details.Execute the following sequence in a continuous loop:
Before every iteration, unconditionally re-scan TargetFile by reading it
and using the stable SemanticTarget string (e.g., locating the target header) to
dynamically determine the updated absolute start and end line numbers. This
ensures absolute accuracy even if the file was edited in prior rounds. (If full file mode is specified, confirm full-file line bounds).
agents/synthesizer.md / egm-synthesizer).
The synthesizer spawns the Goldfish review swarm in
parallel, deduplicates findings, writes the report artifact, and
returns a single summary message to avoid context pollution in the root
conversation. Pass it the Failed Reviewers rule below and
GoldfishContext, and tell it to give those files to each reviewer.
Its summary must give a status, completed or not run, for each
requested reviewer.Reviewers directly.
Instruct each subagent to first read its persona definition in
agents/{name}.md, then audit TargetFile at the resolved line range
against its designated standard in resources/document_standards/,
supplying GoldfishContext.FindingsList. Give each finding a stable id
(<reviewer>-<round>-<n>) and record its reviewer, severity, and affected
scope.TargetFile, the active line range, and the aggregated FindingsList
to the egm-resolve workflow.CONTEST vs. PROPOSE FIX.goldfish_review_report.md with your file-writing tool.TargetFile using your file-editing tool.Fresh reviewers sample differently each round, so a round with zero findings is rare even when the document improves. Use these rules instead:
On converged, go to Step 3. On cap or churn, write a short list of the open findings by severity, then ask the user one question: accept and proceed, continue past the cap, or return the document to drafting.
Crucial Turn-Taking Requirement: After the resolution phase finishes for a
given round, the loop driver MUST respect the turn-taking checkpoint in
egm-resolve. The driver must remain idle across human turns,
only looping back to Step 2.1 when the user explicitly confirms they wish to run
another round of review.
Upon completion (converged, cap or churn accepted by the user, or manual halt):
egm-review, exit
cleanly to hand execution back to the parent workflow.>-
---name: egm-review-loopdescription: >----# distributions/claude/skills/egm-review-loop/SKILL.md常見問題
從發布者下載 distributions/claude/skills/egm-review-loop/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。