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.

65

Quality

79%

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 ./.claude/skills/cpp-core-review/SKILL.md

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

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-structured, lean review skill with clear sequencing and concrete tooling guidance. Its main defect is progressive disclosure: the body points to several reference and template files that are not present in the bundle, leaving dead-end navigation.

Suggestions

Ship the referenced bundle files (references/concurrency.md, error-handling.md, templates.md, performance.md, lifetime.md, rule-map.md, GOTCHAS.md, templates/phase0-starter.md) so the conditional-loading pointers resolve to real content.

Add an explicit validate→fix→retry feedback loop for the review output (e.g., re-run clang-tidy/sanitizers after applying a safety fix) to strengthen workflow_clarity for destructive changes.

Trim the self-referential Constitution rules (e.g. 'This Skill is not a C++ textbook', 'Root SKILL.md stays short') or move them to a separate meta file to tighten conciseness.

DimensionReasoningScore

Conciseness

The body is lean and punchy — short ordered lists and imperative lines like 'Run clang-tidy before eyeballing code' assume Claude's competence — but the self-referential Constitution section ('This Skill is not a C++ textbook', 'Root SKILL.md stays short') is mildly meta and could be trimmed.

4 / 5

Actionability

Concrete guidance is present — named tools (clang-tidy, compile_commands.json, .clang-tidy), an explicit review-priority order, and a severity taxonomy — with only minor gaps; for an instruction-only review skill the direction is actionable rather than abstract.

4 / 5

Workflow Clarity

Multi-step processes are clearly sequenced (Review Priority 1–8, Tool First 1–6, Modernization Discipline ordering) with implicit checkpoints like 'Never mix safety-critical changes with style rewrites', though no explicit validate→fix→retry feedback loop is spelled out.

4 / 5

Progressive Disclosure

The conditional-loading pattern ('If project has concurrency → read references/concurrency.md') is exemplary one-level-deep signaling, but the referenced files (references/*.md, GOTCHAS.md, templates/phase0-starter.md) do not exist in the bundle, so navigation is broken in practice.

3 / 5

Total

15

/

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.

A strong, well-targeted description that names concrete actions, an explicit load trigger, and a clearly distinct C++ core-review niche. Its only weakness is that the action verbs are somewhat generic, leaving minor specificity gaps.

DimensionReasoningScore

Specificity

Lists several concrete actions ('reviewing, refactoring, modernizing, debugging, or designing') tied to a specific C++ domain, but the verbs are somewhat generic rather than fine-grained operations, leaving minor coverage gaps versus a comprehensive 5.

4 / 5

Completeness

It explicitly answers 'what' (review/refactor/modernize/debug/design non-trivial C++ code) and 'when' via a concrete 'Load when ...' trigger clause enumerating specific conditions, satisfying both halves clearly.

5 / 5

Trigger Term Quality

Natural user-facing terms like 'reviewing', 'refactoring', 'debugging', and 'C++ code' with an explicit 'Load when' trigger give good keyword coverage, though a few common synonyms or file/extension cues are missing.

4 / 5

Distinctiveness Conflict Risk

The niche is sharply defined — non-trivial C++ with ownership, RAII, concurrency, templates, Core Guidelines — giving it distinct triggers and minimal overlap risk with other 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.