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

83%

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

SKILL.md
Quality
Evals
Security

Quality

Content

78%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.

The body is concise, well-structured, and actionable, with strong review-priority and classification guidance. Its main weakness is progressive disclosure: the skill signals detailed references in references/, templates/, and standalone files, but none of those bundle files actually exist, leaving the referenced material unreachable.

Suggestions

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

Add at least one concrete example of a categorized finding (e.g. an Ownership-severity comment with a fix) to lift actionability from directive guidance to copy-paste-ready.

Add an explicit review feedback loop (e.g. run clang-tidy/sanitizers → triage by severity → re-run to confirm a fix) to give workflow_clarity a validation checkpoint.

DimensionReasoningScore

Conciseness

The body is lean throughout — short bulleted lists and directives with no explanation of C++ concepts Claude already knows, e.g. 'Do not mechanically replace raw pointers. Classify first.' Every section earns its tokens.

5 / 5

Actionability

Provides concrete, actionable guidance — a review priority order, a tooling discovery list (compile_commands.json, .clang-tidy), 'Run clang-tidy before eyeballing code', an ownership classification taxonomy, and a severity-tagged output format — but few copy-paste commands or example findings beyond clang-tidy.

4 / 5

Workflow Clarity

Clear sequences exist (Review Priority order, Tool First, Modernization Discipline safety→refactor→style→perf) with a checkpoint rule ('Never mix safety-critical changes with style rewrites'), but there is no explicit validate→fix→retry feedback loop for the review process.

4 / 5

Progressive Disclosure

The Condition Loading section is well-designed one-level-deep progressive disclosure, but every referenced file (references/concurrency.md, references/lifetime.md, GOTCHAS.md, templates/phase0-starter.md, PROJECT_CONSTITUTION.md, ADAPTER_POLICY.md) is absent from the bundle, so navigation is broken.

3 / 5

Total

16

/

20

Passed

Description

87%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.

The description is strong: it uses an explicit 'Load when...' trigger, names concrete review activities, and carves out a distinct C++ safety niche. Minor gaps in action-verb concreteness and missing synonyms/file extensions keep specificity and trigger_term_quality just below full marks.

DimensionReasoningScore

Specificity

Lists several concrete actions (reviewing, refactoring, modernizing, debugging, designing) plus a comprehensive concern list (ownership, lifetime, RAII, concurrency, templates, interfaces, exceptions, Core Guidelines), but the action verbs are somewhat abstract relative to the PDF-style 5-anchor example.

4 / 5

Completeness

The 'Load when...' clause explicitly answers when to use it, and the enumerated review activities plus concern areas clearly answer what it does, satisfying the explicit-trigger requirement.

5 / 5

Trigger Term Quality

Strong natural phrases (reviewing, refactoring, modernizing, debugging C++ code) and relevant technical keywords (RAII, lifetime, concurrency, Core Guidelines) that users would say, but missing synonyms and file extensions like .cpp or headers.

4 / 5

Distinctiveness Conflict Risk

The C++ Core Guidelines / RAII / ownership niche is sharply scoped with distinct triggers, giving minimal overlap risk with non-C++ review skills.

5 / 5

Total

18

/

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.