erne-plan
- Repo stars 36
- License MIT
- Author updated Live
- Author repo everything-react-native-expo
- Domain
- Design
- Compatible agents
-
- Claude Code
- Cursor
- Cline
- Codex
- Windsurf
- Gemini CLI
- +20
- Trust score
- 94 / 100 · audit passed
- Author / version / license
- @JubaKitiashvili · MIT
- Token usage
- Lean
- Setup complexity
- Guided setup
- External API key
- Not required
- Operating systems
- Unspecified (assume cross-platform)
- Runtime requirements
- No special requirements
- Permissions
-
- Read-only
- Write / modify
- Shell exec
- Network behavior
- Local-only
- Install commands
- 26 variants
Profile is derived at build time from SKILL.md and install vectors. Subject to drift from author intent.
Heads up: 未限定 allowed-tools，默认拥有全部工具权限。
---
name: erne-plan
description: ERNE — Design feature architecture using the architect agent You are executing the /erne-plan co…
category: design
runtime: no special runtime
---
# erne-plan output preview
## PART A: Task fit
- Use case: ERNE — Design feature architecture using the architect agent You are executing the /erne-plan command. Use the architect agent to design a feature architecture. [1-2 sentence description of the feature] runs entirely locally. Works with Claude Code, Cursor, Cline and 23 more..
- Inputs: target material, constraints, expected output, and acceptance criteria.
- Evidence boundary: follow “Process / Architecture Output / Overview” and do not present inference as author intent.
## PART B: Execution result
- **01** The card summarizes the use case; runtime output centers on “ERNE — Design feature architecture using the architect agent You are executing the /erne-plan command. Use the architect agent to design a feature architecture. [1-2 sentence description of the feature] runs entirely locally. Works with Claude Code, Cursor, Cline and 23 more.”.
- **02** When the source has headings, the agent prioritizes “Process / Architecture Output / Overview” so the result follows the author’s structure.
- **03** Typical output includes task judgment, concrete steps, required commands or file edits, validation, and follow-up options.
- **04** Risk context follows the fingerprint: read files, write/modify files, run shell commands; mostly runs locally; usually needs no extra API key.
## Running Rules
- read files, write/modify files, run shell commands; mostly runs locally; usually needs no extra API key.
- Validate with a small sample before expanding scope.
- Return the result, validation criteria, and next iteration options. Choose the trigger
The source mentions slash commands such as `/erne-plan`; use them first when your agent supports command triggers.
Provide inputs and boundaries
Name target files or source material, expected output, forbidden changes, and whether network or shell access is allowed. Permission fingerprint: read files, write/modify files, run shell commands.
Validate with a small run
Start with a small task and check whether the result follows “Process / Architecture Output / Overview”. Inspect diffs, logs, previews, or tests before expanding scope.
Review before delivery
Confirm the final output includes a concrete result, evidence, and next action. If it stays generic, tighten inputs, boundaries, and acceptance criteria.
---
name: erne-plan
description: ERNE — Design feature architecture using the architect agent You are executing the /erne-plan co…
category: design
source: JubaKitiashvili/everything-react-native-expo
---
# erne-plan
## When to use
- ERNE — Design feature architecture using the architect agent You are executing the /erne-plan command. Use the archite…
- Use it when the task has clear inputs, repeatable steps, and validation criteria.
## What to provide
- Target material, scope, expected result, and forbidden changes.
- Whether network, commands, file writes, or external services are allowed.
## Execution rules
- Organize steps around “Process / Architecture Output / Overview” and keep inference separate from source facts.
- read files, write/modify files, run shell commands; mostly runs locally; usually needs no extra API key.
- Validate with a small sample before expanding the task.
## Output requirements
- Return the deliverable, key evidence, validation method, and next action.
- Mark missing information as unknown; do not invent commands, platforms, or dependencies. Evidence boundary and execution chain
The author source anchors workflow facts; repository files anchor sources and commands; Fluxly only adds fit, limitations, and quality judgment.
skill "erne-plan" {
input -> user goal + target files + boundaries + acceptance criteria
context -> Process / Architecture Output / Overview
rules -> SKILL.md triggers / order / output contract
runtime -> no special runtime | read files, write/modify files, run shell commands | mostly runs locally
guardrails -> usually needs no extra API key + small-sample validation + diff/log review
output -> copyable result + checklist + next iteration
}/erne-plan — Feature Architecture Design
You are executing the /erne-plan command. Use the architect agent to design a feature architecture.
Process
- Understand the requirement — Ask clarifying questions if the feature description is vague
- Analyze existing codebase — Read relevant files, understand current navigation structure, state management, and API patterns
- Design the architecture — Using the architect agent's process:
- Decompose into components and screens
- Plan Expo Router file structure
- Select state management approach (Zustand / TanStack Query / local)
- Design data flow and API layer
- Consider platform-specific requirements
- Output the plan — Use the architect agent's output format:
Architecture Output
## Overview
[1-2 sentence description of the feature]
## File Structure
[New files to create with paths]
## Component Design
[Component hierarchy and responsibilities]
## Data Flow
[State management approach, API calls, caching strategy]
## Navigation
[New routes, layout changes, deep link support]
## Implementation Tasks
[Ordered list of implementation steps]- Review with user — Present the plan and ask for approval before implementation
Notes
- Reference the active platform rules layer (
rules/expo/patterns.mdorrules/bare-rn/patterns.md) for conventions - Consider whether this is Expo managed, bare RN, or has native modules
- Include test strategy in the plan
Decide Fit First
Design Intent
How To Use It
Boundaries And Review