cpp-coding-standards
OfficialC++ coding standards based on the C++ Core Guidelines (isocpp.github.io). Use when writing, reviewing, or refactoring C++ code to enforce modern, safe, and idiomatic practices.
What this skill does
When applied, it prepends a system prompt before your request is sent — no extra calls and no change to how you are billed beyond the added tokens.
--- name: cpp-coding-standards description: C++ coding standards based on the C++ Core Guidelines (isocpp.github.io). Use when writing, reviewing, or refactoring C++ code to enforce modern, safe, and idiomatic practices. origin: ECC --- # C++ Coding Standards (C++ Core Guidelines) Comprehensive coding standards for modern C++ (C++17/20/23) derived from the [C++ Core Guidelines](https://isocpp.github.io/CppCoreGuidelines/CppCoreGuidelines). Enforces type safety, resource safety, immutability, and clarity. ## When to Use - Writing new C++ code (classes, functions, templates) - Reviewing or refactoring existing C++ code - Making architectural decisions in C++ projects - Enforcing consistent style across a C++ codebase - Choosing between language features (e.g., `enum` vs `enum class`, raw pointer vs smart pointer) ### When NOT to Use - Non-C++ projects - Legacy C codebases that cannot adopt modern C++ features - Embedded/bare-metal contexts where specific guidelines conflict with hardware constraints (adapt selectively) ## Cross-Cutting Principles These themes recur across the entire guidelines and form the foundation: 1. **RAII everywhere** (P.8, R.1, E.6, CP.20): Bind resource lifetime to object lifetime 2. **Immutability by default** (P.10, Con.1-5, ES.25): Start with `const`/`constexpr`; mutability is the exception 3. **Type safety** (P.4, I.4, ES.46-49, Enum.3): Use the type system to prevent errors at compile time 4. **Express intent** (P.3, F.1, NL.1-2, T.10): Names, types, and concepts should communicate purpose 5. **Minimize complexity** (F.2-3, ES.5, Per.4-5): Simple code is correct code 6. **Value semantics over pointer semantics** (C.10, R.3-5, F.20, CP.31): Prefer returning by value and scoped objects ## Philosophy & Interfaces (P.*, I.*) ### Key Rules | Rule | Summary | |------|---------| | **P.1** | Express ideas directly in code | | **P.3** | Express intent | | **P.4** | Ideally, a program should be statically type safe | | **P.5** | Prefer
Use this skill
Add a "skill" field with the skill’s ID to your chat completion request. It is applied server-side before your prompt is sent — no extra calls.
{
"model": "gpt-4o-mini",
"skill": "imp-564525be-18e3-4579-9717-36140f1b63b6",
"messages": [{ "role": "user", "content": "…" }]
}Install the skill, enable it in your dashboard and (optionally) limit it to specific models. It then applies automatically to every matching request — with no "skill" field to send each time.
Set it up in your dashboardMore skills
Delegate coding work to Codex, Claude Code, or OpenCode as background workers; not simple edits or read-only code lookup.
Create, edit, audit, tidy, validate, or restructure AgentSkills and SKILL.md files.
Search and analyze your own session logs (older/parent conversations) using jq.
Create, view, edit, delete, search, move, or export Apple Notes via the memo CLI on macOS.
Diagnose OpenClaw Android, iOS, or macOS node pairing, QR/setup code, route, auth, and connection failures.
Set up and use 1Password CLI for sign-in, desktop integration, and reading or injecting secrets.
List, add, edit, complete, or delete Apple Reminders and reminder lists via remindctl.
Create, search, and manage Bear notes via grizzly CLI.