Isurwars/Correlation / .agents/skills/to-spec
to-spec
VerifiedTransform brainstorming notes, feature requests, or design discussions into an actionable, formal technical specification. Use when user asks to "spec this out", "write a spec", or before kicking off major architectural work.
To-Spec
Turn unstructured discussions, user requests, or grilling sessions into a crisp, unambiguous technical specification for the Correlation suite.
Phase 1: Information Gathering & Scope Extraction
Extract and establish the core technical boundaries:
- Problem Statement: What physics or software deficiency is being solved?
- Domain Scope: Which structural analysis calculators or modules are affected (
RDF,PDF,SQ,PAD,Rings,MSD,VACF,VDOS,LEF, ML potentials)? - Consumers & Interfaces: Is this consumed by Slint UI, Python bindings (pybind11), C++ Core API, or CLI?
- Explicit Non-Goals: What is intentionally omitted from this milestone?
Phase 2: Specification Document Template
Generate a structured technical specification using the following schema:
# Spec: [Feature / Module Name]
## 1. Overview & Architectural Motivation
[Concise executive summary of the addition or change.]
## 2. API Contract & Modern C++ Interfaces
- **Header:** `include/path/to/Header.hpp`
- **Class / Struct Definitions:** (Follow C++23 concepts, RAII, immutable by default)
- **Error Handling:** Use `std::expected<T, ErrorCode>` or clear exception boundaries.
## 3. Data Flow & Algorithmic Design
- **Input Data Structures:** Trajectory coordinates, simulation cell metrics, element types.
- **Parallelization Strategy:** OpenMP reduction / TBB parallel loop, memory alignment (`alignas(64)`).
- **Time & Space Complexity:** Bounds on execution time ($O(N^2)$, $O(N \log N)$ via neighbor lists) and RAM footprint.
## 4. UI / Slint Integration (If Applicable)
- **Slint Properties & Models:** VectorModel bindings, reactive callbacks, error states.
- **Thread Dispatch:** Safe worker-to-GUI dispatch mechanisms.
## 5. Test & Quality Plan
- **Unit Tests:** Atomic mathematical tests in `tests/unit/`.
- **Functional Tests:** Golden-sample regression tests with benchmark datasets in `tests/functional/`.
- **Complexity Gate:** Verify cognitive complexity $\le 25$.
Phase 3: Review & Understanding Lock
- Present the completed specification to the User (Lead Architect).
- Prompt: "Does this specification accurately capture all technical invariants and constraints? Please confirm to proceed to ticket breakdown or implementation."
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: 197k | 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: 197k | 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: 197k | Updated | Claude CodeCodex | Verified | Install |