Name: cpp-pro
Rating: 54.400000000000006 (1 reviews)
Author: administrakt0r

cpp-pro

Write idiomatic C++ code with modern features, RAII, smart pointers, and STL algorithms. Handles templates, move semantics, and performance optimization.

Quality

61%

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 ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/cpp-pro/SKILL.md

The canonical home for this skill is cpp-pro in administrakt0r/AI-Agents-Safe-Coding-Skills

Quality

Content

57%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 reasonably concise and well-sectioned but lacks executable code or concrete command sequences, leaving actionability and workflow clarity at mid-range. Progressive disclosure is hurt by a broken reference path that fails to connect to the well-organized reference bundle.

Suggestions

Add at least one copy-paste-ready code example (e.g., a RAII smart-pointer snippet or a STL-algorithm usage) to move actionability toward fully executable.

Fix the reference path from `resources/implementation-playbook.md` to the actual `references/` files and explicitly link the 5 topic files (modern-cpp.md, templates.md, concurrency.md, memory-performance.md, build-tooling.md) so progressive disclosure is clearly signaled.

Turn the Approach list into a concrete build/verify workflow with validation checkpoints (e.g., compile with -fsanitize=address, run tests, then benchmark) to add real workflow clarity.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean bullet and numbered lists with no padding about what C++ or libraries are, but a few lines ("You are a C++ programming expert...", "Follow C++ Core Guidelines") are generic filler that could be trimmed, so it is efficient with minor over-explanation rather than fully lean.	4 / 5
Actionability	It names concrete tools and practices (perf, VTune, Google Test, Catch2, Google Benchmark, "Prefer stack allocation and RAII") but provides no executable code or commands, so guidance is concrete in places yet incomplete for direct execution.	3 / 5
Workflow Clarity	The Approach section lists a numbered sequence, but the steps are general principles rather than a sequenced task workflow and there are no validation checkpoints, matching the anchor with sequence present but checkpoints missing.	3 / 5
Progressive Disclosure	A well-organized one-level-deep bundle of 5 topic files exists under references/, but the body points only at a non-existent path (resources/implementation-playbook.md) and never surfaces the 5 real files, so structure is present but references are not correctly signaled.	3 / 5
	Total	13 / 20 Passed

Description

66%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 specific and domain-distinctive, naming concrete C++ capabilities and natural trigger terms. Its main weakness is the complete absence of an explicit "when to use" clause, which leaves completeness at the cap of 3.

Suggestions

Append an explicit "Use when..." clause naming concrete trigger phrases (e.g., writing or reviewing modern C++, smart pointers, templates, move semantics, C++ performance work) to raise completeness.

Add natural synonyms and file extensions users might say ("modern C++", "C++11/14/17/20/23", ".cpp", "CMake") to broaden trigger-term coverage.

Sharpen "performance optimization" into a concrete action (e.g., "profile and optimize hot paths with perf/VTune") to push specificity toward the comprehensive anchor.

Dimension	Reasoning	Score
Specificity	Lists several concrete capabilities ("RAII, smart pointers, and STL algorithms", "templates, move semantics", "performance optimization") but phrases like "modern features" and "performance optimization" stay somewhat abstract, leaving minor gaps versus the comprehensive anchor.	4 / 5
Completeness	It gives a clear "what" (write idiomatic C++ with RAII, templates, etc.) but contains no "Use when..." clause or equivalent trigger guidance, which caps completeness at 3 per the judging guidelines.	3 / 5
Trigger Term Quality	Includes domain terms a C++ user would naturally say ("C++ code", "smart pointers", "templates", "move semantics") but misses common variations a user might utter ("modern C++", "C++11/17/20", ".cpp"), so a few natural terms are absent.	4 / 5
Distinctiveness Conflict Risk	C++ is a clear niche with distinct, low-overlap triggers; it is mostly distinct from other skills, though the absence of explicit "use when" phrasing leaves minor overlap risk versus the minimal-conflict anchor.	4 / 5
	Total	15 / 20 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: plugins/AI-Agents-Safe-Coding-Skills-claude/skills/cpp-pro/SKILL.md
Commit: 57c135b

Reviewed: 3 days 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.