Skip to content

generic-automation-and-it/smooth-ai-stockanalysis / .agents/skills/create-hld

create-hld

Verified

Invoke to author a High-Level Design (HLD) at discovery / prototyping phase. Design-only: delivers intent + spec for AI and humans to build against — no implementation plan, no code outside examples/. Trigger keywords: "HLD", "high level design", "design doc", "architecture design", "create a design". Also triggers on /create-hld.

FileKindSize
AGENTS.mdmarkdown2.4 KB
SKILL.mdskill md6.5 KB
agents/openai.yamlconfig360 B
assets/AGENTS.template.mdmarkdown1.3 KB
assets/LADR.template.mdmarkdown1.1 KB
assets/NFR.template.mdmarkdown1.1 KB
assets/README.template.mdmarkdown2.1 KB
assets/c4-context.template.mdmarkdown2.0 KB
assets/examples.README.template.mdmarkdown505 B
references/diagram-selection.mdmarkdown2.2 KB
references/status-vocabulary.mdmarkdown1.6 KB
scripts/hld-agents-rules.shexecutablescript3.3 KB
scripts/scaffold-hld.shexecutablescript4.7 KB

assets/README.template.md

View on GitHub
# {{TITLE}} — High-Level Design

| | |
|---|---|
| **Status** | In Discovery |
| **Owner** | <team / handle> |
| **Tracker** | [<project / epic name>](<url>) |
| **Last updated** | {{DATE}} |

> Discovery / prototyping HLD. This document delivers **intent + spec** — what we are
> building and why, the decisions behind it, and the quality bar it must meet. It does
> **not** contain an implementation plan; execution (phasing, sub-issues, sequencing) is
> tracked in the issue/work tracker.

## Intent

<2–4 sentences. What is being introduced and why now. State the problem and the
target outcome. No marketing language.>

## Key Goals

### 1. <Goal>

<1–4 paragraphs: the change, the pattern/principle behind it, the side effects.
Concrete examples beat abstractions.>

**Acceptance criteria / DoD**

- <Observable, testable condition that means this goal is met.>
- <Another condition. These are the design's definition-of-done, not test cases.>

### 2. <Goal>

<...>

**Acceptance criteria / DoD**

- <...>

## Core Separation of Concerns

> <One blockquoted thesis sentence — the load-bearing premise the design rests on.>

<1–2 paragraphs expanding the thesis.>

## Guiding Principle — <Tagline>

> <One blockquoted slogan.>

- <Ownership / independence rule.>
- <What we will deliberately NOT do.>

---

## Diagrams

- [System Context (C1) + supporting diagrams](./diagrams/c4-context.md)

## Architecture Decisions (LADRs)

LADRs 01–N are strategic (*what* and *why*); later LADRs are tactical (*how*). Each is a
single decision — a horizontal concern spanning this HLD. See [`./ladrs/`](./ladrs/).

| LADR | Decision | Status |
|------|----------|--------|
| [LADR-01](./ladrs/LADR-01-example.md) | <Title — one-line summary> | Draft |

## Non-Functional Requirements

Each NFR is a horizontal quality concern spanning the whole design, with a measurable
target, a verification mechanism, and acceptance criteria. See [`./nfrs/`](./nfrs/).

| NFR | Attribute | Target (summary) | Status |
|-----|-----------|------------------|--------|
| [NFR-01](./nfrs/NFR-01-example.md) | <Attribute> | <measurable target> | Draft |
brainstormingobra/superpowersYou MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or planning anything new, in software or out of it (a talk, a business, a renovation).Stars: 322kUpdated Claude CodeCodexVerifiedInstall
brand-guidelinesanthropics/skillsApplies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
frontend-designanthropics/skillsGuidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
mcp-builderanthropics/skillsGuide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).Stars: 198kUpdated Claude CodeCodexVerifiedInstall