generic-automation-and-it/smooth-ai-stockanalysis / .agents/skills/create-hld
create-hld
VerifiedInvoke 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.
| File | Kind | Size |
|---|---|---|
| AGENTS.md | markdown | 2.4 KB |
| SKILL.md | skill md | 6.5 KB |
| agents/openai.yaml | config | 360 B |
| assets/AGENTS.template.md | markdown | 1.3 KB |
| assets/LADR.template.md | markdown | 1.1 KB |
| assets/NFR.template.md | markdown | 1.1 KB |
| assets/README.template.md | markdown | 2.1 KB |
| assets/c4-context.template.md | markdown | 2.0 KB |
| assets/examples.README.template.md | markdown | 505 B |
| references/diagram-selection.md | markdown | 2.2 KB |
| references/status-vocabulary.md | markdown | 1.6 KB |
| scripts/hld-agents-rules.shexecutable | script | 3.3 KB |
| scripts/scaffold-hld.shexecutable | script | 4.7 KB |
AGENTS.md
View on GitHub# create-hld — AGENTS.md
## TL;DR
Authoring skill for design-only HLD folders under `docs/hlds/NNN-<slug>/`. The skill carries the *judgment* (what intent/decisions/NFRs to write); `scripts/scaffold-hld.sh` only lays down the deterministic skeleton from `assets/` templates.
## Requirements
- Scaffold HLDs into this repository's visible `docs/hlds/NNN-<slug>/` tree. Keep the script, usage text, skill instructions, and Codex registration aligned with that contract.
- Do not treat a generic downstream template's `.docs/` convention as an in-repository tooling reference. Consumers of that template choose their own documentation layout.
## Non-Negotiables
- **Two AGENTS.md quality contracts exist — do not cross them.** `scripts/hld-agents-rules.sh` is the *HLD variant* (no architecture section — diagrams live in `diagrams/`). The repo-wide `.github/instructions/meta/knowledge-conventional-contexts-quality.instructions.md` keeps its System Context section. A scaffolded HLD's AGENTS.md follows the script, not the repo-wide rule.
- **Output dir is `docs/hlds/` (plural)** to match the repo's documented HLD location (root `AGENTS.md`). The upstream source used singular `.docs/hld/`; if syncing changes back, keep plural here.
- **Templates are placeholder-substituted by `sed`**, not by an agent. Only `{{INDEX}} {{SLUG}} {{SLUG_UPPER}} {{TITLE}} {{DATE}}` are substituted — any other `{{...}}` in an asset survives verbatim into the scaffolded file.
## Key Behaviors
- The index is `max(existing NNN)+1`, computed by globbing `docs/hlds/[0-9][0-9][0-9]-*/`. A non-conforming folder name (no 3-digit prefix) is silently ignored, so a stray dir won't shift numbering.
- Scripts are `bash` + coreutils only and discover repo root via `git rev-parse` — no Claude-specific behaviour, so Codex/Copilot/Cursor run them identically. Both must stay executable (`chmod +x`).
- Complexity tier is **high** (`claude: opus`): multi-turn clarification gates + architectural judgment, unlike the script-driven low-tier skills.
## Changelog
| Date | Change | Ref |
|:-----|:-------|:----|
| 2026-07-23 | Corrected the HLD scaffold contract to the visible `docs/hlds/` tree and documented the generic template's intentional `.docs/` exception. | #74 |
| 2026-06-16 | Initial version — ported from upstream `create-hld`, made project-agnostic (Linear→tracker, `.docs/hld`→`.docs/hlds`, dropped historical TEMPLATE_HLD.md and repo-specific reference HLDs). | |
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| 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: 322k | Updated | Claude CodeCodex | Verified | Install |
| 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: 198k | Updated | Claude CodeCodex | Verified | Install |
| 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: 198k | Updated | Claude CodeCodex | Verified | Install |
| 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: 198k | Updated | Claude CodeCodex | Verified | Install |