CtrlK
BlogDocsLog inGet started
Tessl Logo

cpp-core-review

Load when reviewing, refactoring, modernizing, debugging, or designing non-trivial C++ code where ownership, lifetime, RAII, concurrency, templates, interfaces, exceptions, or Core Guidelines compliance may affect correctness, safety, maintainability, or performance.

68

Quality

82%

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

The canonical home for this skill is cpp-core-review in zhxc372/cpp-ai-constitution

SKILL.md
Quality
Evals
Security

Quality

Content

72%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, token-efficient review constitution with concrete tooling and classification guidance. Its main weaknesses are missing validation feedback loops in the workflow and dangling references to bundle files that are not actually provided.

Suggestions

Add an explicit validation step to the workflow (e.g., 'Re-run clang-tidy/sanitizers to confirm each proposed fix actually resolves the finding before reporting it').

Either ship the referenced files (references/concurrency.md, references/error-handling.md, references/templates.md, references/performance.md, references/lifetime.md, references/rule-map.md, GOTCHAS.md, templates/phase0-starter.md) or remove the dangling references from the body.

Provide concrete clang-tidy invocation examples (e.g., a sample command with relevant checks) rather than only naming the tool.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence: tight ordered lists, no textbook explanations of C++ concepts, and every section earns its place. Only minor editorializing ("not from textbooks") keeps it from feeling padded.

5 / 5

Actionability

Concrete, executable guidance is present throughout (ordered review priority, specific tooling like compile_commands.json and clang-tidy, an ownership classification scheme, and severity-bucketed output), but tool invocations lack specific flags/commands.

4 / 5

Workflow Clarity

Sequenced steps exist (Review Priority 1-8, Tool First discovery, Modernization Discipline ordering), but there are no explicit validation checkpoints or validate-fix-retry feedback loops for confirming findings are correct before reporting.

3 / 5

Progressive Disclosure

Structure and condition-signaled one-level references are well designed ("If project has concurrency → read references/concurrency.md"), but the referenced files (references/*.md, GOTCHAS.md, templates/phase0-starter.md) do not exist in the bundle, so the navigation is broken in practice.

3 / 5

Total

15

/

20

Passed

Description

92%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 strong, third-person description with an explicit "Load when" trigger, concrete actions, and a well-scoped C++ review niche. Keyword coverage is comprehensive but a few natural synonyms (e.g. "code review") are missing.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions ("reviewing, refactoring, modernizing, debugging, or designing") across a comprehensive set of C++ concern areas (ownership, lifetime, RAII, concurrency, templates, interfaces, exceptions, Core Guidelines), matching the comprehensive-coverage anchor.

5 / 5

Completeness

It explicitly answers both what (review/refactor/modernize/debug/design non-trivial C++ code) and when via the concrete "Load when ... where ... may affect correctness, safety, maintainability, or performance" trigger clause.

5 / 5

Trigger Term Quality

Natural trigger phrases like "reviewing, refactoring, modernizing, debugging" plus concern keywords (RAII, concurrency, lifetime) cover what a C++ user would say, but common variations like "code review", "code audit", or "C++ codebase" are absent.

4 / 5

Distinctiveness Conflict Risk

The niche is sharply defined ("non-trivial C++ code", "Core Guidelines compliance") with concern-specific triggers, making overlap with unrelated skills minimal.

5 / 5

Total

19

/

20

Passed

Validation

93%

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

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

referenced_paths_exist

Referenced path issues: 6 missing

Warning

Total

15

/

16

Passed

Repository
zhxc372/cpp-ai-constitution
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.