egm-draft
Skill from google/elephant-goldfish-model
Install
npx skills add google/elephant-goldfish-model --skill egm-draft
Runs the open skills CLI and installs the skill for your agent (Claude Code, Codex, Cursor …). Alternatively copy the skill folder into .claude/skills/ or upload it in Claude.ai under Settings → Skills.
As a Claude Code plugin
/plugin marketplace add google/elephant-goldfish-model
/plugin install egm@egm
This skill is part of the plugin “egm”. In Claude Code the plugin installs it together with the plugin’s other skills, commands and hooks.
What does the egm-draft skill do?
Description from the SKILL.md in the source repository.
Works with Celebrity Agent
Questions about egm-draft
What does the egm-draft skill do?
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.
How do I install egm-draft?
In a terminal: npx skills add google/elephant-goldfish-model --skill egm-draft. The skills CLI asks which agents to install it for. In Claude.ai you can upload the skill folder as a ZIP under Settings → Skills.
Which agents can use egm-draft?
Skills use the open SKILL.md format, which Claude Code, Claude.ai, the Claude API, OpenAI Codex, Cursor, Gemini CLI and other agents support.
Is egm-draft safe to use?
Our automatic check found no risky patterns (piped shell scripts, hidden characters, secret access, prompt overrides). It is not a full audit – read the SKILL.md and any scripts before installing.
Which tool is egm-draft for?
egm-draft comes from the makers of Celebrity Agent and helps your agent work with it.
More skills from google/elephant-goldfish-model
Bootstrap directory README.md files across a repository subtree.
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.
Runs drift detection on all design documents to check for document and code consistency. Produces an actionable report with differences.
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.
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.
Orchestrates the EGM Goldfish Review Protocol. Used as part of the EGM process to perform design document reviews.
Related skills in Design & Media
Read first to make, edit, animate or render any video with HyperFrames (HTML rendered to video), including launch films, explainers, music videos, charts, maps, vertical clips, title cards, captions and overlays.
Get or make any media for a HyperFrames video - music, sound effects, images, icons, logos, voiceover, avatar and generated video, transcripts, cutouts, colour grades and looks - with HeyGen or free …
Design mobile app screens with Sleek, edit Sleek projects, and implement their designs in React Native or HTML.
A relentless interview to sharpen a plan or design, which also creates docs (ADR's and glossary) as we go.
Generate AI videos with Google Veo, Seedance 2.0, HappyHorse, Wan, Grok and 40+ models via inference.sh CLI.
Generate AI images with GPT-Image-2, FLUX, Gemini, Grok, Seedream, Reve and 50+ models via inference.sh CLI.
Create AI avatar and talking head videos via inference.sh CLI. Recommended: P-Video-Avatar (fastest, cheapest, built-in TTS). Also: OmniHuman, Fabric, PixVerse. Audio: Inworld TTS-2 (100+ languages, emotion steering for characters), ElevenLabs, Kokoro.
Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable …