cpp-pro

Write idiomatic C++ code with modern features, RAII, smart pointers, and STL algorithms. Handles templates, move semantics, and performance optimization. Use PROACTIVELY for C++ refactoring, memory safety, or complex C++ patterns.

Quality

71%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/cpp-pro/SKILL.md

Quality

Content

57%

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

A reasonably organized, concise C++ reference skill with good sectioning, but it stays at the level of principles and tool names without executable examples or a real validated workflow. The generic boilerplate sections dilute its specificity.

Suggestions

Add at least one concrete, copy-paste code example (e.g. a RAII/smart-pointer snippet) and an executable CMakeLists.txt stanza with the required C++ standard to lift actionability.

Replace the generic "Instructions" and templated "Use this skill when/Do not use" boilerplate with C++-specific guidance, or remove it to improve conciseness.

For risky areas like concurrency and memory, add an explicit validate-fix-retry loop (e.g. run AddressSanitizer/ThreadSanitizer, fix, re-run) to turn the "Approach" list into a genuine workflow.

Dimension	Reasoning	Score
Conciseness	The C++-specific sections (Focus Areas, Approach, Output) are lean, but the generic "Instructions" boilerplate ("Clarify goals, constraints, and required inputs... validate outcomes") and templated "Use this skill when/Do not use" sections add non-specific padding that could be tightened.	2 / 3
Actionability	Names concrete rules and tools (Rule of Zero/Three/Five, perf, VTune, Google Test, Catch2, Google Benchmark) but provides no executable code, commands, or copy-paste examples, leaving guidance instructive yet incomplete for a coding skill.	2 / 3
Workflow Clarity	The numbered "Approach" list gives a loose priority sequence but it is principles, not a true workflow, and lacks any validation checkpoints despite the body mentioning "validate outcomes."	2 / 3
Progressive Disclosure	The body is under 50 lines, self-contained, and organized into clearly labeled sections with no external references needed, satisfying the simple-skill allowance for a top score.	3 / 3
	Total	9 / 12 Passed

Description

85%

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, specific description that answers both what the skill does and when to use it, with a clear C++ niche. Its main weakness is moderate trigger-term coverage that omits several natural variations a user might say.

Suggestions

Broaden the trigger clause to include natural variations users actually say, e.g. "Use PROACTIVELY for modern C++, smart pointers, templates, move semantics, C++ refactoring, or memory safety."

Consider surfacing concrete deliverable triggers (e.g. CMakeLists, Google Test, Google Benchmark) to strengthen distinctiveness against generic coding skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete capabilities — "Write idiomatic C++ code with modern features, RAII, smart pointers, and STL algorithms. Handles templates, move semantics, and performance optimization" — matching the multi-action anchor.	3 / 3
Completeness	Clearly answers what (write idiomatic modern C++ with RAII/smart pointers/STL) and when via an explicit "Use PROACTIVELY for..." trigger clause, matching the both-what-and-when anchor.	3 / 3
Trigger Term Quality	Trigger guidance "C++ refactoring, memory safety, or complex C++ patterns" offers some natural terms but omits common variations users would say (e.g. "modern C++", "smart pointers", "templates", "C++ optimization"), matching the missing-common-variations anchor.	2 / 3
Distinctiveness Conflict Risk	Targets a clear C++ niche with C++-specific triggers (RAII, templates, move semantics, C++ refactoring), making triggering for the wrong skill unlikely.	3 / 3
	Total	11 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: rmyndharis/antigravity-skills
Path: skills/cpp-pro/SKILL.md
Commit: e63f7dd

Reviewed: about 4 hours 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.