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

references/diagram-selection.md

View on GitHub
# Diagram Selection — investigate, then recommend

The C1 System Context is the **mandatory floor**. Everything else is earned: investigate the
design, then recommend the smallest set of diagrams that makes the architecture clear. Do not
add a diagram by default — add it because it answers a question the C1 cannot.

Surface recommendations to the user **before** writing them, each with a one-line rationale.

## The floor

| Diagram | Mermaid | Always include |
|---|---|---|
| System Context (C1) | `C4Context` | Yes — every HLD. System + immediate external actors/dependencies, with `Rel()` protocols. No internals. |

## Recommend when the design warrants it

| Diagram | Mermaid | Recommend when… |
|---|---|---|
| Container view (C2) | `C4Container` | The system is >1 deployable/runtime unit, or the split between units is a load-bearing decision. |
| Flow | `flowchart TD` / `graph TB` | There is a process or decision path worth showing end-to-end (routing, branching, state transitions). This is the diagram people actually read. |
| Sequence | `sequenceDiagram` | An interaction has 3+ steps **or** any side effect (email, queue message, external API call, push notification). Participants are roles, not class names. 5–10 steps max. |
| Data model | `erDiagram` | 3+ related entities with non-obvious relationships. Skip for single-entity or obvious-named relations. |
| Domain types | `classDiagram` | Key types/contracts and their relationships drive the design and aren't obvious from the data model. |

## Rules

- **Each diagram earns its place.** If it restates the C1 or the prose, drop it.
- **One concern per diagram.** A sequence diagram shows one flow; add another file for another flow.
- **No code.** Diagrams describe structure and interaction, not implementation. Code samples go in `examples/`.
- **Roles over names.** Use logical participant/container names ("Handler", "Gateway"), not concrete class or file names — the design predates the code.
- **Render-clean.** Verify Mermaid parses (no syntax errors) before marking the HLD ready.
- Multiple diagrams may live as sections in `diagrams/c4-context.md`, or as separate files in `diagrams/` (e.g. `sequence-checkout.md`) when they grow large.
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