memory-safety-patterns

Cross-language patterns for memory-safe programming including RAII, ownership, smart pointers, and resource management.

Quality

30%

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/memory-safety-patterns/SKILL.md

The canonical home for this skill is memory-safety-patterns in rmyndharis/antigravity-skills

Quality

Content

18%Scale 1-5

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

This skill is essentially a stub with no actionable content. It claims to cover cross-language memory safety patterns (RAII, ownership, smart pointers) but provides zero concrete examples, code, or specific guidance. The instructions are generic boilerplate that could apply to any skill, and the entire substantive content is deferred to a bundle file that doesn't exist.

Suggestions

Add concrete, executable code examples for at least the core patterns (RAII in C++, ownership in Rust, smart pointers) directly in the SKILL.md as a quick-start overview.

Replace the generic instruction bullets ('Clarify goals,' 'Apply relevant best practices') with specific, actionable steps for implementing memory safety patterns, such as a decision tree for choosing the right pattern.

Provide the referenced `resources/implementation-playbook.md` bundle file, or inline the essential content if the bundle is unavailable.

Add a concrete workflow with validation steps, e.g., how to audit code for memory safety issues, with specific tools or checks to run (valgrind, AddressSanitizer, cargo clippy).

Dimension	Reasoning	Score
Conciseness	The skill is relatively short, but the 'Use this skill when' and 'Do not use this skill when' sections add little value since Claude can infer applicability. The instructions section is generic boilerplate ('Clarify goals, constraints, and required inputs') rather than domain-specific content.	3 / 5
Actionability	The skill provides zero concrete code, commands, or specific patterns. Instructions like 'Apply relevant best practices and validate outcomes' are entirely vague. For a skill about memory safety patterns (RAII, ownership, smart pointers), there are no actual patterns, code examples, or executable guidance whatsoever.	1 / 5
Workflow Clarity	There is no meaningful workflow defined. The four bullet points in Instructions are generic platitudes ('Clarify goals,' 'Apply relevant best practices') with no sequencing, no validation checkpoints, and no concrete steps for implementing memory safety patterns.	1 / 5
Progressive Disclosure	The skill references `resources/implementation-playbook.md` for detailed patterns, which is a reasonable structure, but no bundle files are provided so the reference is unverifiable. The SKILL.md itself contains essentially no substantive content to serve as an overview — it's an empty shell pointing to a file that may not exist.	2 / 5
	Total	7 / 20 Passed

Description

41%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 identifies a clear technical domain and lists relevant concepts, but reads more like a topic heading than an actionable skill description. It lacks concrete actions (what does the skill do — teach, refactor, review?) and entirely omits 'when to use' guidance, making it difficult for Claude to reliably select this skill from a large pool.

Suggestions

Add a 'Use when...' clause with trigger phrases like 'Use when the user asks about memory safety, fixing memory leaks, RAII patterns, ownership semantics, or smart pointer usage in C++, Rust, or other languages.'

Replace the topic listing with concrete actions, e.g., 'Guides refactoring code to use RAII and smart pointers, identifies memory safety issues like use-after-free and dangling pointers, and translates ownership patterns across languages.'

Include natural user terms and language names such as 'memory leak', 'dangling pointer', 'use-after-free', 'C++', 'Rust', 'unique_ptr', 'shared_ptr' to improve trigger term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain (memory-safe programming) and lists several concepts (RAII, ownership, smart pointers, resource management), but these are topic areas rather than concrete actions. It doesn't describe what the skill actually does — e.g., 'refactors code to use RAII patterns' or 'identifies memory leaks'.	3 / 5
Completeness	Provides a partial 'what' (cross-language patterns for memory-safe programming) but has no 'when' clause at all. There is no 'Use when...' guidance, which per the rubric should cap completeness at 3, and the 'what' itself is more of a topic listing than a clear capability statement, placing it at 2.	2 / 5
Trigger Term Quality	Includes relevant technical keywords like 'RAII', 'ownership', 'smart pointers', and 'resource management' that users might mention. However, it misses natural user phrases like 'memory leak', 'dangling pointer', 'use-after-free', 'Rust', 'C++', or specific language names that would be common trigger terms.	3 / 5
Distinctiveness Conflict Risk	The focus on memory safety and specific patterns like RAII and ownership provides some distinctiveness, but 'cross-language patterns' and 'resource management' are broad enough to overlap with general programming best practices skills or language-specific skills for Rust or C++.	3 / 5
	Total	11 / 20 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	10 / 11 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: plugins/AI-Agents-Safe-Coding-Skills/skills/memory-safety-patterns/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.