Index of every page on this site: llms.txt
All skills
google avatar

/egm-draft

@70406c4
by googlegoogle/elephant-goldfish-model22k stars
1,589
Run it yourself

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.

Use this Skill: https://skilld.dev/gh/google/elephant-goldfish-model/egm-draft

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

referencesdesign_doc.md

≈1.4k tokens on demand. Your agent reads this file only when SKILL.md points to it.

[Feature/Project Name]

  • Author: [Author Name or GitHub Handle]
  • Status: [Draft | Proposed | In Review | Approved]
  • Date: [YYYY-MM-DD]

Overview

<!-- Provide a high-level summary of the feature, the business or technical problem it solves, and its context within the system. Keep it concise so both humans and agents can quickly parse the main objective. -->

The Problem

[Summarize the problem and the proposed solution here.]

Goals

<!-- What will this feature achieve? Be specific, measurable, and clear. These goals represent the absolute criteria for success. -->
  • Goal 1
  • Goal 2

Non-Goals

<!-- Explicitly state what is out of scope. This is crucial to prevent feature creep and to define strict boundaries for the implementation agent. -->
  • Non-Goal 1
  • Non-Goal 2

Open Questions

<!-- List unresolved design questions, technical unknowns, or dependencies requiring investigation. Unanswered questions are retained here across drafting sessions to preserve conversational memory and prevent future sessions from re-asking questions that were already discussed. Remove answered questions as they are resolved. -->
  • Question 1: [Description of technical unknown or open question]
  • Question 2: [Description of technical unknown or open question]

Critical User Journeys (CUJs)

<!-- Define the end-to-end user journeys this design enables. Each CUJ must contain: 1. Given: Preconditions, starting state, and environment configurations. 2. When: The trigger, user action, or system event. 3. Then: The expected outcome, verification criteria, and postconditions. -->

CUJ 1: [Journey Title]

  • Given: [Preconditions]
  • When: [Actions]
  • Then: [Expected Outcomes]

CUJ 2: [Journey Title]

  • Given: [Preconditions]
  • When: [Actions]
  • Then: [Expected Outcomes]

Technical Plan (Architecture)

<!-- Detail the high-level design, architectural choices, system data flows, and component interactions. Include ASCII or Mermaid diagrams to clearly model the relationships. -->

[Explain your architectural choices, data structures, and system component mapping here.]

[Optional ASCII Architecture Diagram]

Alternatives Considered

<!-- Document other architectural approaches or designs that were evaluated and rejected. Explain the pros, cons, and the technical reasoning for why the chosen plan is superior. -->

Alternative A: [Alternative Title]

  • Pros: [List benefits]
  • Cons: [List drawbacks]
  • Reason for Rejection: [Why this option was not selected (e.g., "Rejected by author: technical rationale"). Do not attribute a rejection to a maintainer without linking their issue, discussion, or PR.]

Non-Functional Requirements

<!-- Analyze non-functional concerns only if they represent critical risks for this design: - Security & Privacy: (Data sensitivity, auth/auth, secrets management). - Performance & Latency: (Execution runtime, storage footprint, LLM token overhead). - Rollout & Rollback: (Feature flags, backward compatibility, rollback commands). -->

[Detail any critical non-functional requirements here. If none are critical, this section can be omitted or stated as "None".]


Additional Resources

<!-- Specify the external resources and context that were used during the design discussion. Optional. If none were provided omit this section.-->
  • Important project docs referenced
  • Important docs/ referenced
  • Related work

Future Improvements

<!-- Specify areas that have room for future improvement here. If none were provided omit this section.-->
  • The idea: What could be improved?

Detailed Implementation Plan

<!-- Specify exactly which files must be created or modified. Do not use vague language or TBDs. -->

Target Files to Create/Modify

1. [File Path 1] ([Create | Modify])
  • Type / Scope: [e.g., Python Service, C++ Library, TypeScript Module, Build Configuration]
  • Proposed Changes: [Describe the new APIs, class/function signatures, or behavioral logic here. Focus on the minimal required details for implementation.]
2. [File Path 2] ([Create | Modify])
  • Type / Scope: [e.g., Unit Test, E2E Test Driver]
  • Proposed Changes: [Describe the test coverage, expected test cases, or mock assertions.]

Verification Plan

<!-- Specify what unit, integration, or manual tests must pass to validate the implementation. What metrics should be measured to verify success? -->
  • Compilation/Build: [e.g., npm run build, cargo build, make]
  • Unit Tests: [e.g., pytest, npm test, cargo test]
  • Static Analysis & Linting: [e.g., eslint, ruff check, golangci-lint]
  • Test Coverage Requirement: [e.g., 85%+ branch coverage]
  • E2E/Integration: [e.g., Integration test command or automated eval runner]

<!-- Provenance: Indicates initial structural drafting via EGM. -->

Drafted with EGM

Source: SKILL.md on GitHub

No rule matched.

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

No alerts16d3 checks · Risk SAFE
  • Gen Agent Trust Hub17d

    This skill provides a structured workflow for drafting technical design documents section-by-section. It focuses on maintaining consistency between brainstorming and drafting phases and emphasizes clear, jargon-free communication.

  • Socket16d

    No alerts

  • Snyk17d

    Risk: LOW · No issues

Signed by skilld at 70406c4. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 3 days ago.

Activeupdated 3 weeks ago
disable-model-invocation
true

README badge

README badge for google/elephant-goldfish-model/egm-draft