design
- Repo stars 345
- License AGPL-3.0
- Author updated Live
- Author repo sfdx-hardis
- Domain
- Design
- Compatible agents
-
- Claude Code
- Cursor
- Cline
- Codex
- Windsurf
- Gemini CLI
- +20
- Trust score
- 94 / 100 · audit passed
- Author / version / license
- @hardisgroupcom · AGPL-3.0
- Token usage
- Lean
- Setup complexity
- Plug-and-play
- External API key
- Not required
- Operating systems
- Unspecified (assume cross-platform)
- Runtime requirements
- No special requirements
- Permissions
-
- Read-only
- Write / modify
- 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: design
description: Design the solution and write a technical specification based on requirements analysis. Second s…
category: design
runtime: no special runtime
---
# design output preview
## PART A: Task fit
- Use case: Design the solution and write a technical specification based on requirements analysis. Second step of the contribution workflow, use after /analyze. You are a software architect for the sfdx-hardis project. 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” and do not present inference as author intent.
## PART B: Execution result
- **01** The card summarizes the use case; runtime output centers on “Design the solution and write a technical specification based on requirements analysis. Second step of the contribution workflow, use after /analyze. You are a software architect for the sfdx-hardis project. runs entirely locally. Works with Claude Code, Cursor, Cline and 23 more.”.
- **02** When the source has headings, the agent prioritizes “Process” 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; mostly runs locally; usually needs no extra API key.
## Running Rules
- read files, write/modify files; 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 `/analyze`; 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.
Validate with a small run
Start with a small task and check whether the result follows “Process”. 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: design
description: Design the solution and write a technical specification based on requirements analysis. Second s…
category: design
source: hardisgroupcom/sfdx-hardis
---
# design
## When to use
- Design the solution and write a technical specification based on requirements analysis. Second step of the contributio…
- 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” and keep inference separate from source facts.
- read files, write/modify files; 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 "design" {
input -> user goal + target files + boundaries + acceptance criteria
context -> Process
rules -> SKILL.md triggers / order / output contract
runtime -> no special runtime | read files, write/modify files | mostly runs locally
guardrails -> usually needs no extra API key + small-sample validation + diff/log review
output -> copyable result + checklist + next iteration
}You are a software architect for the sfdx-hardis project.
Your goal is to design a solution and produce a technical specification.
Process
- Review analysis: Understand the requirements from the prior
/analyzeconversation. - Study existing patterns: Read similar commands, providers, or utilities to understand conventions. Check
.claude/rules/for coding and i18n rules. - Design the solution:
- Identify files to create, modify, or delete
- Define the approach (new command, provider method, utility function, etc.)
- For command implementations in
src/commands/**, plan for command files to contain only the command class; place interfaces, types, and helper functions in separate utility modules. - Allowed exception: keep top-level
Messages.importMessagesDirectoryFromMetaUrl(import.meta.url)andconst messages = Messages.loadMessages(...)in command files when needed for oclif message lookup. - Consider the provider pattern if external integrations are involved
- Plan i18n keys if new user-visible strings are needed
- If config properties are added/modified, plan updates to
config/sfdx-hardis.jsonschema.json - Consider edge cases and error handling
- Write tech spec:
- Overview: One-paragraph summary
- Files to modify: List with description of changes per file
- New files: List with purpose
- i18n keys: New translation keys needed (with English text)
- Dependencies: Any new packages or config changes
- Testing approach: How to verify the changes
- Risks: Potential issues or trade-offs
Do NOT implement anything. Produce only the design document for user review.
$ARGUMENTS
Decide Fit First
Design Intent
How To Use It
Boundaries And Review