cpp-coding-standards

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.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-organized, highly actionable C++ standards reference with strong code examples and a validation checklist, but it is a long monolithic document that restates rules Claude largely knows and makes no use of reference files for progressive disclosure.

Suggestions

Move the detailed per-rule tables and full implementations (e.g., Buffer Rule-of-Five, FileHandle RAII) into reference files under references/, keeping SKILL.md as a concise overview that links to them — this addresses both progressive_disclosure and conciseness.

Trim rule tables that restate C++ Core Guidelines rules Claude already knows; retain only the rules most often misapplied with one tight DO/DON'T example per topic.

Add a brief 'Core principles / quick start' summary at the top that points into the detailed sections, so the body functions as a navigable overview with one-level-deep references instead of a single monolithic reference.

Dimension	Reasoning	Score
Conciseness	The body avoids explaining basic concepts but is a dense ~725-line monolithic reference that restates rules (RAII, const-correctness) Claude largely already knows; full implementations like the Buffer Rule-of-Five could be tightened or moved. It is mostly efficient but could be trimmed, matching the score-2 anchor.	2 / 3
Actionability	It provides numerous complete, compilable C++ examples (Buffer Rule-of-Five, FileHandle RAII, ThreadSafeQueue, concepts, constexpr factorial) plus concrete DO/DON'T and Anti-Pattern lists that are copy-paste ready and specific.	3 / 3
Workflow Clarity	Though a reference rather than a multi-step workflow, it closes with an explicit "Quick Reference Checklist" of validation checkpoints ("Before marking C++ work complete"), which the score-3 anchor credits, and no destructive/batch feedback-loop cap applies.	3 / 3
Progressive Disclosure	No bundle files exist and the entire 725-line reference is inline in SKILL.md with no overview-to-detail split or one-level-deep references; content that should be separate (detailed rule tables and full code examples) is inline, matching the score-2 anchor. It is well-structured so not score 1.	2 / 3
	Total	10 / 12 Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, third-person description that names concrete actions, includes an explicit "Use when" trigger, and carves out a distinct C++ niche. It answers both what the skill does and when to use it without verbosity or over-claiming.

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete actions — "writing, reviewing, or refactoring C++ code" — matching the score-3 anchor that enumerates several specific operations; it is more than naming a domain and a couple of actions.	3 / 3
Completeness	It states what ("C++ coding standards … to enforce modern, safe, and idiomatic practices") and an explicit "Use when writing, reviewing, or refactoring C++ code" trigger, so both what and when are answered with no cap applied.	3 / 3
Trigger Term Quality	"writing, reviewing, refactoring C++ code" and "C++ Core Guidelines" are exactly the natural terms a user would say to invoke this skill, giving good coverage rather than only some relevant keywords.	3 / 3
Distinctiveness Conflict Risk	The scope is clearly C++-specific and anchored to the C++ Core Guidelines, a distinct niche unlikely to trigger for non-C++ or generic code-review skills.	3 / 3
	Total	12 / 12 Passed

Validation

87%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (725 lines); consider splitting into references/ and linking	Warning
metadata_version	'metadata.version' is missing	Warning

	Total	14 / 16 Passed

Repository: affaan-m/everything-claude-code
Commit: 4130457

Reviewed: 4 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.