⏳ This skill is pending AI review.
Scores will appear once the review pipeline completes.
egm-bootstrap
Bootstrap directory README.md files across a repository subtree.
Choose how to use this skill
You do not need every option. Choose the path your AI client supports. The stable page stays the same; versioned files are immutable.
1. Native installer
This listing has no registered native installer command. Use the complete package or source fallback below, depending on what your client supports.
Do not guess an installer command or replace an existing version without reviewing the diff.
2. Complete package recommended
Download the ZIP when available. It includes SKILL.md plus the references, security notes and version metadata.
No complete ProSkills package is published for this listing yet.3. Prompt-only
Copy the prompt above when the agent can read the stable page or when you want to adopt the workflow without installing a skill.
Need only the instruction file?
Download SKILL.md only if your client requires a single file. The complete ZIP is safer for a full installation because it preserves the references and release context.
No path installs or executes anything by itself. Your agent still needs access to the project files. Before updating, compare the installed version and review the diff.
// RATINGS
Not yet listed on ClawHub or SkillsMP
// README
Elephant-Goldfish Model (EGM)
Elephant-Goldfish Model (EGM) is an open-source plugin for Spec-Driven Development with AI coding agents. Deep-context Elephant sessions draft specifications, and isolated zero-context Goldfish subagents stress-test them before you write code.
Install
| Harness | Install |
|---|---|
| Any AI agent | Ask your agent: Install https://github.com/google/elephant-goldfish-model |
| Antigravity | agy plugin install https://github.com/google/elephant-goldfish-model (or /plugin in IDE) |
| Claude Code | claude plugin marketplace add google/elephant-goldfish-model && claude plugin install egm@egm |
| Codex | codex plugin marketplace add google/elephant-goldfish-model && codex plugin add egm@egm |
| Claude Cowork / ChatGPT | See Harnesses for desktop and workspace setup |
Quickstart
- Ideate & Stress-Test: Run
/egm-brainstormto explore problem boundaries and test early concepts with a Goldfish swarm. - Draft: Run
/egm-draftto convert the concept brief into a living design document underdocs/designs/<feature>.md. - Review & Resolve: Run
/egm-review docs/designs/<feature>.mdto run the multi-stage Goldfish reviewer swarm. - Submit & Implement: Submit the verified design doc via pull request and implement code against the approved specification.
In Claude Code, commands use the /egm: prefix (for example /egm:egm-brainstorm).
For detailed setup guides and walkthroughs, see Getting Started, Harnesses, and Framework Architecture.
Skills
| Skill | Command | Description |
|---|---|---|
| Brainstorm | /egm-brainstorm | Zero-doc ideation tool using a multi-lens Goldfish shootdown swarm to stress-test early concepts. |
| Draft | /egm-draft | Iterative, section-by-section markdown design specification compiler. |
| Review | /egm-review | Multi-stage verification pipeline orchestrator (Zoom Out -> Comprehension -> Critic -> Readiness). |
| Review Loop | /egm-review-loop | Concurrent review subagent dispatch engine supporting direct and hierarchical dispatch. |
| Review Resolve | /egm-resolve | Interactive triage and automated patch application engine for review findings. |
| Drift Report | /egm-drift-report | Sequential AST scanner detecting divergence between checked-in specs and live code. |
| Bootstrap | /egm-bootstrap | Recursive bottom-up codebase documentation generator and sentinel-block upserting engine. |
Philosophy
EGM uses two animal metaphors to structure AI agents across the software development lifecycle:
- 🐘 The Elephant (Remembers Everything): Deep-context agents load system history, architecture diagrams, component boundaries, and user journeys. The Elephant runs structured brainstorming, probes operational limits, and drafts comprehensive specifications.
- 🐠 The Goldfish (Zero-Context Memory): Stateless, isolated subagents read only the draft spec and live source code, without conversational bias. The Goldfish swarm stress-tests designs from conflicting perspectives. Personas in
agents/include Design Critic, Naive Reader, Tech Lead, Codebase Auditor, Structural Validator, Style Editor, and Zoom Out Architect. - 🧑💻 The Human (Owns the Outcomes): AI is an exploration partner and automated auditor, while human engineers own architectural decisions, trade-offs, and final outcomes.
For the foundational essay introducing this methodology, see Dave Rensin's article: Elephants, Goldfish, and the New Golden Age of Software Engineering.
Contributing
We welcome community contributions! Please review Harnesses and our Contribution Guidelines before submitting pull requests.
License
Apache 2.0 License applies to this project - see the LICENSE file for details.
This is not an officially supported Google product.
// HOW IT'S BUILT
KEY FILES