CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

cpp-coding-standards

基于C++核心指南(isocpp.github.io)的C++编码标准。在编写、审查或重构C++代码时使用,以强制实施现代、安全和惯用的实践。

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./docs/zh-CN/skills/cpp-coding-standards/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

71%Weight 40%Scale 1-5

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 executable examples, GOOD/BAD contrasts, and a useful completion checklist. Its weaknesses are token efficiency (much of the rule catalog restates what Claude already knows) and progressive disclosure: the full ~720-line reference lives in SKILL.md with no bundle files, where an overview plus per-area reference files would serve better.

Suggestions

Split the per-area rule catalogs (e.g. classes, concurrency, templates, naming) into references/ files such as references/classes.md and references/concurrency.md, keeping SKILL.md as a lean overview of cross-cutting principles, 'when to use', and links to each area — this moves ~500 lines out of the always-loaded context.

Trim rule-table entries that restate common knowledge (e.g. 'use nullptr not 0/NULL', 'avoid malloc/free') and keep only the rule ID plus non-obvious guidance, reserving space for the traps Claude is likelier to miss (C.82, F.53, CP.44, ES.100).

Add brief guidance on applying the standards: how to prioritize conflicting rules (e.g. Per.* performance exceptions vs. safety rules) and how to report findings (rule ID + fix) during code review.

DimensionReasoningScore

Conciseness

The body is dense and free of fluff (no 'what is C++' padding, terse rule tables), but large portions restate Core Guidelines knowledge Claude already has (e.g. "P.8 不要泄漏任何资源", "ES.47 使用 nullptr 而非 0 或 NULL") and full listings like the ~30-line five-rule Buffer class add bulk that could be tightened. This fits 'mostly efficient but includes some unnecessary explanation or could be tightened' — not 2 since there is no real padding, not 4 since a meaningful fraction restates known rules.

3 / 5

Actionability

Every section provides complete, executable, copy-paste-ready C++ covering the common cases: parameter passing, the zero/five-rule Buffer, a RAII FileHandle, scoped_lock for multiple mutexes, C++20 concepts, include guards, plus explicit GOOD/BAD contrasts and a final pre-completion checklist. This matches the anchor-5 example of fully executable code covering common cases.

5 / 5

Workflow Clarity

As a standards reference, the single action is unambiguous (consult rules when writing/reviewing; verify against the '快速参考检查清单' before marking work done), and that closing checklist is an explicit validation checkpoint. It falls short of 5 because there is no guidance on sequencing or prioritizing rules (e.g. how to weigh Per.* exceptions against safety rules) when applying them to real code.

4 / 5

Progressive Disclosure

No bundle files exist (no references/, scripts/, or assets/); the entire ~720-line standards reference is inlined in SKILL.md. Internal organization is good — clear section headers per guideline area (P/I, F, C, R, ES, ...) — which keeps it above anchor 2's header-less inline dump, but content that clearly belongs in separate reference files is inline with no one-level-deep references, matching anchor 3.

3 / 5

Total

15

/

20

Passed

Description

73%Weight 40%Scale 1-5

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 solid description that clearly identifies its niche (C++ standards derived from the Core Guidelines) and includes an explicit 'use when' trigger clause with natural keywords. Its main weakness is that the capability statement ('enforce modern, safe and idiomatic practices') is abstract rather than enumerating the concrete enforcement actions the skill performs.

Suggestions

Replace the generic capability phrase '强制实施现代、安全和惯用的实践' with 2-3 concrete actions, e.g. '审查C++代码是否符合核心准则、标记违规规则(如R.11裸new/delete)、建议符合准则的替代写法' (review code against Core Guidelines, flag violated rule IDs, suggest compliant alternatives).

Add common trigger variations such as ".cpp", "C++17/20/23", or "代码风格/代码审查" to broaden the natural keywords users might say.

DimensionReasoningScore

Specificity

The description names the domain clearly ("基于C++核心指南(isocpp.github.io)的C++编码标准") and ties use to concrete activities ("在编写、审查或重构C++代码时使用"), but the skill's own action is the generic phrase "强制实施现代、安全和惯用的实践" rather than a list of specific capabilities. It exceeds anchor 2 (domain named, actions minimal/generic) thanks to the concrete usage actions, but does not list the several specific actions required for anchor 4.

3 / 5

Completeness

Both parts are present: the what ("基于C++核心指南...的C++编码标准...以强制实施现代、安全和惯用的实践") and an explicit when clause ("在编写、审查或重构C++代码时使用") with concrete triggers. It is not anchor 5 because the 'what' states what the artifact is rather than enumerating concrete actions as in the top example.

4 / 5

Trigger Term Quality

It includes natural terms users would actually say — "C++", "编码标准", "编写", "审查", "重构", "C++核心指南" — giving good keyword coverage. It falls short of anchor 5 because common variations and file extensions like ".cpp", "C++17/20", or "code style" are missing.

4 / 5

Distinctiveness Conflict Risk

It occupies a clear niche — C++ coding standards with a named source (C++ Core Guidelines, isocpp.github.io) — and its triggers (writing, reviewing, refactoring C++ code) are distinct. Only negligible overlap with a general code-review skill; matches the anchor-5 example of a clear niche with minimal conflict risk.

5 / 5

Total

16

/

20

Passed

Validation

87%

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

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (724 lines); consider splitting into references/ and linking

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

14

/

16

Passed

Repository

xu-xiang/everything-claude-code-zh

Path

docs/zh-CN/skills/cpp-coding-standards/SKILL.md

Reviewed

Table of Contents

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.