design-rules
- Repo stars 43
- Author updated Live
- Author repo claude-kit
- Domain
- Design
- Compatible agents
-
- Claude Code
- Cursor
- Cline
- Codex
- Windsurf
- Gemini CLI
- +20
- Trust score
- 88 / 100 · community maintained
- Author / version / license
- @hex0xdeadbeef · no license declared
- 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-rules
description: Design phase rules for /designer command. Load at /designer startup (step 0). Covers spec qualit…
category: design
runtime: no special runtime
---
# design-rules output preview
## PART A: Task fit
- Use case: Design phase rules for /designer command. Load at /designer startup (step 0). Covers spec quality, design checklist, approach evaluation criteria. Guidelines for the /designer command to produce high-quality design specs that reduce plan-review iterations. runs entirely locally. Works with Claude Code, Cursor, Cline and 23 more..
- Inputs: target material, constraints, expected output, and acceptance criteria.
- Evidence boundary: follow “Purpose / Instructions / Step 1: Load at /designer startup” and do not present inference as author intent.
## PART B: Execution result
- **01** The card summarizes the use case; runtime output centers on “Design phase rules for /designer command. Load at /designer startup (step 0). Covers spec quality, design checklist, approach evaluation criteria. Guidelines for the /designer command to produce high-quality design specs that reduce plan-review iterations. runs entirely locally. Works with Claude Code, Cursor, Cline and 23 more.”.
- **02** When the source has headings, the agent prioritizes “Purpose / Instructions / Step 1: Load at /designer startup” 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 `/designer`; 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 “Purpose / Instructions / Step 1: Load at /designer startup”. 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-rules
description: Design phase rules for /designer command. Load at /designer startup (step 0). Covers spec qualit…
category: design
source: hex0xdeadbeef/claude-kit
---
# design-rules
## When to use
- Design phase rules for /designer command. Load at /designer startup (step 0). Covers spec quality, design checklist, a…
- 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 “Purpose / Instructions / Step 1: Load at /designer startup” 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-rules" {
input -> user goal + target files + boundaries + acceptance criteria
context -> Purpose / Instructions / Step 1: Load at /designer startup
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
}Design Rules
Purpose
Guidelines for the /designer command to produce high-quality design specs that reduce plan-review iterations.
Instructions
Step 1: Load at /designer startup
Read this SKILL.md for overview. Supporting files loaded on-demand per phase.
Step 2: Use phase-driven loading
- Phase 3 (PROPOSE) → read Spec Quality for approach evaluation criteria
- Phase 4 (WRITE SPEC) → read Design Checklist for self-verification
- Phase 5 (USER GATE) → verify checklist before presenting to user
Spec Quality Criteria
| Criterion | Required | Check |
|---|---|---|
| Context describes current state | Yes | Not just "add X" but "currently Y exists, need X because Z" |
| Scope has IN and OUT | Yes | OUT items have explicit reasons |
| At least 2 approaches compared | Yes | With pros/cons for each |
| Selected approach has rationale | Yes | References constraints from requirements |
| Key decisions are numbered | Yes | Each has rationale and impact |
| Risks have severity and mitigation | Yes | HIGH risks must have concrete mitigation |
| Acceptance criteria are verifiable | Yes | Each can be checked as pass/fail |
Anti-Patterns
| Anti-Pattern | Why Bad | Fix |
|---|---|---|
| "The obvious approach is..." | Skips exploration, may miss better options | Always compare at least 2 |
| Spec without OUT scope | Scope creep during planning | Explicitly list what's excluded |
| Vague acceptance criteria ("works well") | Can't verify | Make criteria concrete and testable |
| No risks identified | Every design has risks | Identify at least 1 per approach |
| Copying task description as context | No analysis | Describe current state, not just goal |
Common Issues
Designer skips CLARIFY phase
Cause: Task seems clear. Fix: Even "clear" tasks benefit from scope IN/OUT confirmation. At minimum, confirm scope.
User rejects all approaches
Cause: Missing constraint not captured. Fix: Ask: "What constraint am I missing?" — don't generate more approaches without new information.
References
- Spec Quality — detailed quality criteria, approach evaluation matrix
- Design Checklist — phase-by-phase self-verification
Decide Fit First
Design Intent
How To Use It
Boundaries And Review