egm-drift-report
egm-drift-report is a skill in google/elephant-goldfish-model, last changed 27 Oct 2026. It can name web addresses. Our pattern check flagged nothing at commit a8380ab on 27 Oct 2026.
Pattern check: nothing flagged · commit a8380ab · 27 Oct 2026
InstallRuns drift detection on all design documents to check for document and code consistency. Produces an actionable report with differences. Use when the user asks to detect drift or check for consistency across all design documents or READMEs in a directory.
- Licence
- Apache 2.0
- Repo stars
- 3.7k
- Folder last changed
- 27 Oct 2026 (opens in a new tab)
- Publisher
- Files
- 3 files
- Checked
- a8380ab (opens in a new tab) · 27 Oct 2026
Install
Each tab says whether it installs commit a8380ab, the one we checked, or the latest version.
No tab for your agent? Use Any agent for OpenCode, Goose, Windsurf (Devin Desktop), Zed, Roo Code, Factory Droid, Junie, Amp and Antigravity, and Claude Code for Cline. Kiro needs the folder copied by hand.
Pinned to commit a8380ab, the one we checked.
From your project's root folder:
tmp="$(mktemp -d)" &&
git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/google/elephant-goldfish-model.git "$tmp" &&
git -C "$tmp" fetch -q --depth 1 origin a8380ab5f0aba392c97e31c79f9a6666b3f09f14 &&
git -C "$tmp" sparse-checkout set -- distributions/claude/skills/egm-drift-report &&
git -C "$tmp" checkout -q a8380ab5f0aba392c97e31c79f9a6666b3f09f14 &&
mkdir -p .claude/skills &&
mkdir .claude/skills/egm-drift-report &&
cp -R "$tmp"/distributions/claude/skills/egm-drift-report/. .claude/skills/egm-drift-report/ &&
rm -rf "$tmp"If Claude Code was already running and this created the skills folder, run /reload-skills.
Pinned to commit a8380ab, the one we checked.
Skills in the Claude apps belong to your account rather than to a project.
Make egm-drift-report.zip, with the skill folder at the top level:
tmp="$(mktemp -d)" &&
git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/google/elephant-goldfish-model.git "$tmp" &&
git -C "$tmp" fetch -q --depth 1 origin a8380ab5f0aba392c97e31c79f9a6666b3f09f14 &&
git -C "$tmp" sparse-checkout set -- distributions/claude/skills/egm-drift-report &&
git -C "$tmp" checkout -q a8380ab5f0aba392c97e31c79f9a6666b3f09f14 &&
out="$(mktemp -d)" &&
cp -R "$tmp"/distributions/claude/skills/egm-drift-report "$out"/egm-drift-report &&
(cd "$out" && zip -qr - egm-drift-report) > egm-drift-report.zip &&
rm -rf "$tmp" "$out"In Claude, open Customize > Skills, select +, then + Create skill > Upload a skill, and choose egm-drift-report.zip.
On Free, Pro and Max plans, turn on Code execution and file creation (Create and edit files in newer settings) under Settings > Capabilities.
Pinned to commit a8380ab, the one we checked.
From your project's root folder:
tmp="$(mktemp -d)" &&
git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/google/elephant-goldfish-model.git "$tmp" &&
git -C "$tmp" fetch -q --depth 1 origin a8380ab5f0aba392c97e31c79f9a6666b3f09f14 &&
git -C "$tmp" sparse-checkout set -- distributions/claude/skills/egm-drift-report &&
git -C "$tmp" checkout -q a8380ab5f0aba392c97e31c79f9a6666b3f09f14 &&
mkdir -p .agents/skills &&
mkdir .agents/skills/egm-drift-report &&
cp -R "$tmp"/distributions/claude/skills/egm-drift-report/. .agents/skills/egm-drift-report/ &&
rm -rf "$tmp"Codex picks up new skills on its own; restart it if this one does not appear.
Pinned to commit a8380ab, the one we checked.
From your project's root folder:
tmp="$(mktemp -d)" &&
git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/google/elephant-goldfish-model.git "$tmp" &&
git -C "$tmp" fetch -q --depth 1 origin a8380ab5f0aba392c97e31c79f9a6666b3f09f14 &&
git -C "$tmp" sparse-checkout set -- distributions/claude/skills/egm-drift-report &&
git -C "$tmp" checkout -q a8380ab5f0aba392c97e31c79f9a6666b3f09f14 &&
mkdir -p .cursor/skills &&
mkdir .cursor/skills/egm-drift-report &&
cp -R "$tmp"/distributions/claude/skills/egm-drift-report/. .cursor/skills/egm-drift-report/ &&
rm -rf "$tmp"Pinned to commit a8380ab, the one we checked.
From your project's root folder:
tmp="$(mktemp -d)" &&
git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/google/elephant-goldfish-model.git "$tmp" &&
git -C "$tmp" fetch -q --depth 1 origin a8380ab5f0aba392c97e31c79f9a6666b3f09f14 &&
git -C "$tmp" sparse-checkout set -- distributions/claude/skills/egm-drift-report &&
git -C "$tmp" checkout -q a8380ab5f0aba392c97e31c79f9a6666b3f09f14 &&
mkdir -p .github/skills &&
mkdir .github/skills/egm-drift-report &&
cp -R "$tmp"/distributions/claude/skills/egm-drift-report/. .github/skills/egm-drift-report/ &&
rm -rf "$tmp"In a running Copilot CLI session, run /skills reload.
Or install it with gh skill, which also installs the commit we checked. Needs GitHub CLI 2.90 or later.
gh skill install google/elephant-goldfish-model distributions/claude/skills/egm-drift-report/SKILL.md@a8380ab5f0aba392c97e31c79f9a6666b3f09f14 --agent github-copilot --scope projectPinned to commit a8380ab, the one we checked.
From your project's root folder:
tmp="$(mktemp -d)" &&
git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/google/elephant-goldfish-model.git "$tmp" &&
git -C "$tmp" fetch -q --depth 1 origin a8380ab5f0aba392c97e31c79f9a6666b3f09f14 &&
git -C "$tmp" sparse-checkout set -- distributions/claude/skills/egm-drift-report &&
git -C "$tmp" checkout -q a8380ab5f0aba392c97e31c79f9a6666b3f09f14 &&
mkdir -p .gemini/skills &&
mkdir .gemini/skills/egm-drift-report &&
cp -R "$tmp"/distributions/claude/skills/egm-drift-report/. .gemini/skills/egm-drift-report/ &&
rm -rf "$tmp"In a running session, run /skills reload.
Or use Gemini CLI’s own installer. Installs the latest version, not the one we checked.
gemini skills install https://github.com/google/elephant-goldfish-model.git --path distributions/claude/skills/egm-drift-report --scope workspacePinned to commit a8380ab, the one we checked.
Codex, Cursor, Copilot, VS Code, Gemini CLI, OpenCode, Goose, Amp and Zed all read .agents/skills; Claude Code and Kiro list only their own folders.
From your project's root folder:
tmp="$(mktemp -d)" &&
git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/google/elephant-goldfish-model.git "$tmp" &&
git -C "$tmp" fetch -q --depth 1 origin a8380ab5f0aba392c97e31c79f9a6666b3f09f14 &&
git -C "$tmp" sparse-checkout set -- distributions/claude/skills/egm-drift-report &&
git -C "$tmp" checkout -q a8380ab5f0aba392c97e31c79f9a6666b3f09f14 &&
mkdir -p .agents/skills &&
mkdir .agents/skills/egm-drift-report &&
cp -R "$tmp"/distributions/claude/skills/egm-drift-report/. .agents/skills/egm-drift-report/ &&
rm -rf "$tmp"Or use the skills CLI from skills.sh. Installs the latest version, not the one we checked. The skills CLI reports installs to skills.sh unless you set DISABLE_TELEMETRY=1.
npx skills@1.7.4 add google/elephant-goldfish-model --skill egm-drift-reportWhat it can touch
From the files and frontmatter at commit a8380ab. This is how much a skill can do, not whether it is risky.
What it can touch: Scripts or outside hosts
Names web addresses
It mentions outside web addresses the agent may visit. We list them but don't follow them.
Pattern check
Pattern check: nothing flagged · commit a8380ab · 27 Oct 2026
We checked every text file in this skill, at commit a8380ab on 27 Oct 2026, against 45 published patterns such as download-and-run commands, hidden text and credential access. We don't run the skill, we don't read the web pages it points to, and we can't judge everything its instructions might lead an agent to do. In published tests, pattern checks like this one missed most malicious skills. Read the skill before you install it — especially anything it asks you to download or run.
How the check worksReport an incorrect finding
Outside links we did not follow
- http://www.w3.org/2000/svg
Format check
Each agent reads SKILL.md a little differently. We check the file against each one's published rules; we don't run the skill in any agent.
Agent Skills specPasses with warnings
The open format from agentskills.io, held to what the strictest agents enforce, so one folder loads everywhere.
- Warning
Fields outside the spec: disable-model-invocation (read by Claude Code and VS Code). Uploads to the Claude apps and API, and the spec's validator, reject the file; most agents ignore these fields. O1
Fix: Delete them for a portable skill, or keep them if you only target the agents that read them.
- Warning
Paths that may not work once the skill is installed: line 14: ../../docs/codex.md (outside the skill folder). B6
Fix: Use forward-slash paths relative to SKILL.md, and copy shared files into the skill.
- Warning
Claude CodePasses with warnings
Claude Code reads its own extra fields, ignores unknown ones, and still loads a skill whose frontmatter is broken, without its fields.
- Warning
Paths that may not work once the skill is installed: line 14: ../../docs/codex.md (outside the skill folder). B6
Fix: Use forward-slash paths relative to SKILL.md, and copy shared files into the skill.
- Warning
Claude apps & API uploadFails
Uploading to claude.ai or the Claude API, or packaging with Anthropic's script, accepts only the six spec fields and stops on anything else.
- Error
Upload and packaging fail on fields outside the spec: disable-model-invocation. O1
Fix: Delete them, and keep your own data under metadata as text values.
- Warning
Paths that may not work once the skill is installed: line 14: ../../docs/codex.md (outside the skill folder). B6
Fix: Use forward-slash paths relative to SKILL.md, and copy shared files into the skill.
- Note
The description is 255 characters. The claude.ai Help Center says 200 at most, though Anthropic's API docs and validator allow 1,024. D4
Fix: If the claude.ai upload refuses it, trim the description to 200 characters.
- Error
OpenAI (Codex & API)Passes with warnings
Codex finds SKILL.md by its exact name and needs a description; OpenAI's Skills API checks the frontmatter against the spec and caps uploads.
- Warning
Fields outside the spec: disable-model-invocation. Codex ignores them; OpenAI doesn't say whether its upload accepts them. O1
Fix: Delete them, or move your own data under metadata as text values.
- Warning
Paths that may not work once the skill is installed: line 14: ../../docs/codex.md (outside the skill folder). B6
Fix: Use forward-slash paths relative to SKILL.md, and copy shared files into the skill.
- Warning
VS Code & CopilotPasses with warnings
VS Code reads skills one folder below .github/skills, .claude/skills or .agents/skills and falls back to the folder name when the name is missing or differs; GitHub's Copilot docs require the exact name SKILL.md.
- Warning
Paths that may not work once the skill is installed: line 14: ../../docs/codex.md (outside the skill folder). B6
Fix: Use forward-slash paths relative to SKILL.md, and copy shared files into the skill.
- Warning
SKILL.md
Files
3 files
| Path | Size |
|---|---|
| SKILL.md (opens in a new tab) | 3.1 KB |
| agents/openai.yaml (opens in a new tab) | 204 B |
| assets/icon.svg (opens in a new tab) | 281 B |
Copies
These share its SKILL.md or its name and description but not all its files, so we list them separately.
More from google/elephant-goldfish-model
egm-bootstrap
google/elephant-goldfish-model
Bootstrap directory README.md files across a repository subtree.
- Runs shell commands
- Names web addresses
Pattern check: Nothing flaggedApache 2.0 · 3.7k repo stars · Updated 27 Oct 2026
egm-bootstrap
google/elephant-goldfish-model
Bootstrap directory README.md files across a repository subtree.
- Runs shell commands
- Names web addresses
Pattern check: Nothing flaggedApache 2.0 · 3.7k repo stars · Updated 27 Oct 2026
egm-brainstorm
google/elephant-goldfish-model
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.
- Runs shell commands
- Names web addresses
Pattern check: Nothing flaggedApache 2.0 · 3.7k repo stars · Updated 27 Oct 2026
egm-brainstorm
google/elephant-goldfish-model
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.
- Runs shell commands
- Names web addresses
Pattern check: Nothing flaggedApache 2.0 · 3.7k repo stars · Updated 27 Oct 2026
egm-draft
google/elephant-goldfish-model
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.
- Names web addresses
Pattern check: 1 item to reviewApache 2.0 · 3.7k repo stars · Updated 27 Oct 2026
egm-draft
google/elephant-goldfish-model
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.
- Names web addresses
Pattern check: 1 item to reviewApache 2.0 · 3.7k repo stars · Updated 27 Oct 2026
