Name: cpp-pro
Rating: 48.8 (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

52%

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/skills/cpp-pro/SKILL.md

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

Quality

Content

38%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 well-sectioned and not bloated, but it offers no executable C++ examples and its file navigation is broken: it references a missing resources/ path while ignoring the five real references/ files. Workflow guidance stays at the principle level without concrete checkpoints.

Suggestions

Fix the broken reference and link the actual bundle, e.g. "For deep dives, open references/modern-cpp.md, references/templates.md, references/concurrency.md, references/memory-performance.md, references/build-tooling.md" instead of the non-existent resources/implementation-playbook.md.

Add at least one copy-paste-ready C++ snippet (e.g. a unique_ptr/RAII idiom or a STL-algorithm-over-raw-loop example) to lift actionability above high-level hints.

Turn the "Approach" principles into a concrete sequenced workflow with explicit validation checkpoints (e.g. compile with -Wall -Werror, run under AddressSanitizer, then benchmark).

Dimension	Reasoning	Score
Conciseness	Mostly efficient and it lists rather than explains known C++ concepts, but the templated "Use this skill when/Do not use this skill when" sections and the redundant "You are a C++ programming expert" line add boilerplate tokens that could be tightened.	3 / 5
Actionability	For a C++ coding skill it provides only high-level hints and principle lists with no executable code or concrete commands; tool names (perf, VTune, Google Test) are mentioned but the specific steps to execute are missing.	2 / 5
Workflow Clarity	A rough sequence exists in "Instructions" and a numbered "Approach", and validation is mentioned abstractly ("validate outcomes", "verification"), but there are no concrete validation checkpoints and the numbered list is principles rather than a true workflow.	3 / 5
Progressive Disclosure	Five reference files exist in references/ but the body never links them, and the one body reference points to a non-existent resources/implementation-playbook.md (wrong directory and filename), leaving the real bundle orphaned and unnavigable.	2 / 5
	Total	10 / 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 distinct, listing concrete C++ capabilities and natural trigger terms. Its main weakness is the absence of any explicit "Use when..." trigger guidance, which caps completeness at 3.

Suggestions

Append an explicit trigger clause, e.g. "Use when writing, refactoring, or optimizing C++ code, or when the user mentions C++, RAII, smart pointers, templates, or STL."

Add file-extension and version synonyms (.cpp/.cc, C++17/C++20) to broaden natural keyword coverage toward a 5.

Replace the vague verb "Handles" with concrete actions (e.g. "Optimizes", "Refactors") to match the specificity of "Write".

Dimension	Reasoning	Score
Specificity	Names several concrete capabilities ("RAII, smart pointers, and STL algorithms", "templates, move semantics, and performance optimization") beyond just the domain, with minor gaps since the second verb ("Handles") is less action-concrete than "Write".	4 / 5
Completeness	Has a clear "what" (writing idiomatic modern C++) but no "Use when..." clause or equivalent explicit trigger guidance; per the rubric, a missing when-clause caps completeness at 3.	3 / 5
Trigger Term Quality	Good natural keyword coverage ("C++ code", "RAII", "smart pointers", "templates", "move semantics", "STL", "performance optimization") that users would say, but missing synonyms and file extensions like .cpp/.cc and standard-version phrasing.	4 / 5
Distinctiveness Conflict Risk	The C++-specific triggers (RAII, smart pointers, STL, templates, move semantics) carve a mostly distinct niche with only minor overlap risk against generic coding or C skills.	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/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.