Agent skill

Design First

by rohitg00 in rohitg00/skillkit

Guides the creation of technical design documents before writing code, producing architecture diagrams, data models, API interface definitions, implementation plans, and multi-option trade-off…

Apache-2.0Auto-check passedAgent Workflows

Install Design First

skills CLI
$ npx skills add rohitg00/skillkit --skill design-first -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install rohitg00/skillkit design-first --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/rohitg00/skillkit.git skills-src && mkdir -p .claude/skills && cp -r skills-src/packages/core/src/methodology/packs/planning/design-first .claude/skills/design-first && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
design-first
GitHub stars
1.5k
Token cost
~1.5k tokens
SKILL.md length
494 words
Files
1
Skills in repo
14
Repo updated
First seen
Licence
Apache-2.0

At a glance

Guides the creation of technical design documents before writing code, producing architecture diagrams, data models, API interface definitions, implementation plans, and multi-option trade-off…

  • Works in 4 steps: Understand the Problem → Explore Options → Design the Solution → …
  • The user asks to plan a feature
  • SKILL.md covers Core Principle, When to Use Design First, Design Process and Design Document Template, plus 4 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Design First is an agent skill from rohitg00/skillkit. Guides the creation of technical design documents before writing code, producing architecture diagrams, data models, API interface definitions, implementation plans, and multi-option trade-off analyses. Use when the user asks to plan a feature, architect a system, design an API, explore implementation approaches, or requests a technical design or spec before coding — especially for complex features involving multiple components, ambiguous requirements, or significant architectural changes.

Its SKILL.md is about 1.5k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Agent Workflows, covering Planning, Diagrams and Software architecture. The repository describes itself as: Supercharge AI coding agents with portable skills. Install, translate & share skills across Claude Code, Cursor, Codex, Copilot & 40 more. The licence is Apache-2.0.

When your agent uses it

  • The user asks to plan a feature
  • Architect a system
  • Explore implementation approaches
  • Requests a technical design

Example prompts

  • “Use the design-first skill to guide the creation of technical design documents before writing code, producing architecture diagrams, data models…”
  • “/design-first”

Workflow steps

4 steps, taken from the step headings in SKILL.md.

  1. Understand the Problem
  2. Explore Options
  3. Design the Solution
  4. Validate the Design

What it can do on your machine

Read from SKILL.md and the folder at commit d2e5c34. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are typescript and markdown).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Design First loads about 1.5k tokens when it runs. Until then it costs about 127 tokens; SKILL.md has 494 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~127
When it runs · the whole SKILL.md, loaded when a task matches
~1.5k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from rohitg00/skillkit at commit d2e5c34, republished under its Apache-2.0 licence (© rohitg00). 494 words, ~1,459 tokens.

Download SKILL.mdSave it as .claude/skills/design-first/SKILL.md (or your agent's skills folder).
name
design-first
description
Guides the creation of technical design documents before writing code, producing architecture diagrams, data models, API interface definitions, implementation plans, and multi-option trade-off analyses. Use when the user asks to plan a feature, architect a system, design an API, explore implementation approaches, or requests a technical design or spec before coding — especially for complex features involving multiple components, ambiguous requirements, or significant architectural changes.
version
1.0.0
triggers
design first, plan before code, architecture, how should I implement, design document
tags
planning, design, architecture, thinking
difficulty
intermediate
estimatedTime
20
relatedSkills
planning/task-decomposition, planning/verification-gates

Design First Methodology

You are following a design-first approach. Before writing any code, design the solution.

Core Principle

Think first, code second.

When to Use Design First

Apply this methodology when:

  • Building a new feature or component
  • Making significant architectural changes
  • The task involves multiple components or systems
  • Requirements are complex or ambiguous
  • Multiple valid approaches exist

Skip for trivial changes (typos, simple bug fixes, config changes).

Design Process

Phase 1: Understand the Problem

Before designing, ensure clarity on:

Requirements Checklist:

  • What is the user/business need?
  • What are the inputs and outputs?
  • What are the constraints (performance, security, compatibility)?
  • What are the edge cases?
  • What are the non-requirements (out of scope)?

Questions to Ask:

  • What exactly should this do?
  • What should it NOT do?
  • How will users interact with it?
  • How will it integrate with existing systems?
  • What happens when things go wrong?
Phase 2: Explore Options

Generate multiple approaches before choosing:

markdown
## Option A: [Approach Name]

**Description:** [Brief explanation]

**Pros:**
- [Advantage 1]
- [Advantage 2]

**Cons:**
- [Disadvantage 1]
- [Disadvantage 2]

**Complexity:** Low/Medium/High

---

## Option B: [Approach Name]
...

Evaluate options against:

  • Requirements fit
  • Implementation complexity
  • Maintenance burden
  • Performance characteristics
  • Team familiarity
Phase 3: Design the Solution

Create a design document covering:

System Overview
┌─────────────┐    ┌─────────────┐    ┌─────────────┐
│   Client    │───▶│   Service   │───▶│  Database   │
└─────────────┘    └─────────────┘    └─────────────┘
Data Model
typescript
interface Order {
  id: string;
  customerId: string;
  items: OrderItem[];
  status: OrderStatus;
  createdAt: Date;
  total: Money;
}
API/Interface Design
typescript
// Public interface
interface OrderService {
  createOrder(customerId: string, items: OrderItem[]): Promise<Order>;
  getOrder(orderId: string): Promise<Order | null>;
  cancelOrder(orderId: string): Promise<void>;
}
Key Algorithms/Logic
Order Total Calculation:
1. Sum item prices (price × quantity)
2. Apply discounts (percentage-based first, then fixed)
3. Calculate tax (rate based on customer location)
4. Add shipping (free over threshold, otherwise flat rate)
Error Handling
  • What errors can occur?
  • How should they be handled?
  • What should users see?
Phase 4: Validate the Design

Before implementing, validate:

Self-Review:

  • Does it meet all requirements?
  • Are there simpler alternatives?
  • What could go wrong?
  • Is it testable?

External Validation:

  • Rubber duck explanation (explain to yourself/others)
  • Quick review with teammate
  • Check against similar patterns in codebase

Design Document Template

Use DESIGN_TEMPLATE.md as the standard artifact for each feature. It covers:

  • Overview — one-paragraph summary of what is being built and why
  • Requirements — functional and non-functional (performance, security)
  • Architecture — component diagram and explanation
  • Data Model — entity definitions and relationships
  • API Design — interface definitions
  • Key Decisions — decision table with options considered, choice made, and rationale
  • Implementation Plan — ordered steps
  • Testing Strategy — unit and integration test scope
  • Open Questions — unresolved items

Create this file at the start of each design session and keep it updated as the design evolves.

Show full SKILL.md (164 more words)Show less

Design Levels

High-Level Design (Architecture)
  • System components and their interactions
  • Data flow between systems
  • Technology choices
  • Deployment architecture
Mid-Level Design (Module/Component)
  • Class/module structure
  • Interfaces and contracts
  • State management
  • Error handling strategy
Low-Level Design (Implementation)
  • Algorithm details
  • Data structures
  • Method signatures
  • Edge case handling

Anti-Patterns to Avoid

Anti-PatternMitigation
Big Design Up Front (BDUF)Design enough to start; refine as you learn
Analysis ParalysisTime-box the design phase; decide at 70% confidence
Design in IsolationAlign with existing codebase patterns and team conventions

Integration with Implementation

After design is approved:

  1. Review the design one more time before coding
  2. Break into tasks using task-decomposition skill
  3. Implement incrementally - verify design assumptions as you code
  4. Update design if you discover issues during implementation

The design document is living — update it as you learn.

Signals You Need More Design

  • "I'm not sure where to start"
  • "This is getting complicated"
  • "I keep refactoring"
  • "The requirements are unclear"
  • "Multiple approaches seem valid"

Stop and design before proceeding.

© rohitg00, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in packages/core/src/methodology/packs/planning/design-first of rohitg00/skillkit.

Open the folder on GitHubat commit d2e5c34

Compare with similar skills

Design First next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Design First compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Design First this skillrohitg00/skillkit1.5k—~1.5kAutomated safety check: PassApache-2.0
Engineering Plan Reviewgarrytan/gstack136k—~13kAutomated safety check: NotesMIT
Plan Previewu-ichi/reviewable-html-workbench2981 repos~1.8kAutomated safety check: PassMIT
Solution ArchitectIBM/ibm-watsonx-orchestrate-adk178—~8.4kAutomated safety check: PassMIT
Cl Executeclosedloop-ai/claude-plugins122—~6.4kAutomated safety check: PassApache-2.0
Plannotator Visual Explainerbacknotprop/plannotator9.2k—~1.7kAutomated safety check: PassApache-2.0

Similar skills

  • Reviews an execution plan or design doc before coding, covering architecture, data flow, edge cases, test coverage and performance, one issue at a time.

    136k GitHub stars~13k tokensUpdated today
    DevelopmentAuto-check: notes
  • Plan Preview

    u-ichi/reviewable-html-workbench

    Plan Mode の <proposedplan を出す直前に、計画の段階・依存関係・検証観点を一時HTMLで視覚確認したい時に使う agent-internal skill。Use this agent-internal skill to create a temporary HTML preview for a plan just before presenting…

    298 GitHub starsUsed in 1 repo~1.8k tokens
    Agent WorkflowsAuto-check passed
  • Solution Architect

    IBM/ibm-watsonx-orchestrate-adk

    Official

    Expert guidance for creating high-level solution architecture documents from business requirements, use cases, or problem statements.

    178 GitHub stars~8.4k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed
  • Cl Execute

    closedloop-ai/claude-plugins

    Draft and upload ClosedLoop implementation plans with Mermaid scope flowcharts, then execute one ClosedLoop feature ticket or a parent-approved coherent multi-ticket feature end to end on Codex…

    122 GitHub stars~6.4k tokensUpdated today
    Agent WorkflowsAuto-check passed
  • Plannotator Visual Explainer

    backnotprop/plannotator

    Builds self-contained HTML explainers for plans, pull requests and technical concepts in Plannotator's theme, then opens them in its annotation view.

    9.2k GitHub stars~1.7k tokensUpdated today
    Agent WorkflowsAuto-check passed
  • Audit Flow

    zebbern/claude-code-guide

    Interactive system flow tracing across CODE, API, AUTH, DATA, NETWORK layers with SQLite persistence and Mermaid export.

    4.7k GitHub stars~4.2k tokensUpdated today
    DevelopmentAuto-check passed

More from rohitg00/skillkit

All 14 skills in this repo
  • Find Skills

    rohitg00/skillkit

    Discovers, searches, and installs skills from multiple AI agent skill marketplaces (400K+ skills) using the SkillKit CLI.

    1.5k GitHub stars~1.2k tokensUpdated 4 mo ago
    Auto-check passed
  • Handoff Protocols

    rohitg00/skillkit

    Manages work transitions between team members or agents by creating structured handoff documents, summarizing project status, documenting key decisions, blockers, and open questions, and generating…

    1.5k GitHub stars~1.5k tokensUpdated 4 mo ago
    Auto-check passed
  • Hypothesis Testing

    rohitg00/skillkit

    Applies the scientific method to debugging by helping users form specific, testable hypotheses, design targeted experiments, and systematically confirm or reject theories to find root causes.

    1.5k GitHub stars~1.5k tokensUpdated 4 mo ago
    Auto-check passed
  • Parallel Investigation

    rohitg00/skillkit

    Coordinates parallel investigation threads to simultaneously explore multiple hypotheses or root causes across different system areas.

    1.5k GitHub stars~1.4k tokensUpdated 4 mo ago
    Auto-check passed
  • Red Green Refactor

    rohitg00/skillkit

    Guides the red-green-refactor TDD workflow: write a failing test first, implement the minimum code to make it pass, then refactor while keeping tests green.

    1.5k GitHub stars~1.3k tokensUpdated 4 mo ago
    Auto-check passed
  • Root Cause Analysis

    rohitg00/skillkit

    Performs systematic root cause analysis to identify the true source of bugs, errors, and unexpected behavior through structured investigation phases — not just treating symptoms.

    1.5k GitHub stars~1.4k tokensUpdated 4 mo ago
    Auto-check passed

Questions about Design First

What does Design First do?

Guides the creation of technical design documents before writing code, producing architecture diagrams, data models, API interface definitions, implementation plans, and multi-option trade-off…. Design First is an agent skill from rohitg00/skillkit. Guides the creation of technical design documents before writing code, producing architecture diagrams, data models, API interface definitions, implementation plans, and multi-option trade-off analyses.

When should I use Design First?

Design First fits situations like: the user asks to plan a feature; architect a system; explore implementation approaches; requests a technical design.

How do I install Design First in Claude Code?

Run `npx skills add rohitg00/skillkit --skill design-first -a claude-code`. Or copy the skill folder (packages/core/src/methodology/packs/planning/design-first in rohitg00/skillkit) into .claude/skills/design-first in your project. Claude Code loads it when a task matches its description.

How do I install Design First in Codex?

Run `npx skills add rohitg00/skillkit --skill design-first -a codex`. Or copy the skill folder (packages/core/src/methodology/packs/planning/design-first in rohitg00/skillkit) into .agents/skills/design-first in your project. Codex loads it when a task matches its description.

Can I use Design First in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add rohitg00/skillkit --skill design-first -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/design-first, .gemini/skills/design-first, .github/skills/design-first and .opencode/skills/design-first in your project.

What does Design First need to run?

SKILL.md names no scripts, command-line tools or credentials: Design First is instructions for the agent only.

Does Design First access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Design First safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Design First use?

Design First is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Design First use?

About 1.5k tokens (SKILL.md is roughly 5.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Design First?

Skills that share tags, products or a category with Design First: Engineering Plan Review (garrytan/gstack, 136k stars), Plan Preview (u-ichi/reviewable-html-workbench, 298 stars), Solution Architect (IBM/ibm-watsonx-orchestrate-adk, 178 stars) and Cl Execute (closedloop-ai/claude-plugins, 122 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Design First?

rohitg00 (a GitHub user) maintains it in rohitg00/skillkit, which has 1,546 GitHub stars. The repository holds 14 skills in this directory. The repository was last updated on June 2, 2026.

Source: rohitg00/skillkit on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.