memory-safety-patterns

Implement memory-safe programming with RAII, ownership, smart pointers, and resource management across Rust, C++, and C. Use when writing safe systems code, managing resources, or preventing memory bugs.

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 ./skills/memory-safety-patterns/SKILL.md

Quality

Content

37%Weight 40%Scale 1-3

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

The body is concise and well-sectioned but lacks substance: the Instructions are generic and non-actionable, there is no concrete workflow or validation, and the single referenced resource file is missing. It reads as a template rather than executable guidance.

Suggestions

Replace generic directives with concrete, executable guidance: example RAII/smart-pointer snippets in Rust and C++, specific ownership patterns, and named tools or linters (e.g. valgrind, AddressSanitizer, cargo Miri).

Add a sequenced workflow for diagnosing memory bugs (reproduce -> run sanitizer -> inspect report -> fix -> re-verify) with explicit validation checkpoints.

Create the referenced 'resources/implementation-playbook.md' or remove the dangling reference, so progressive disclosure points to a real file.

Dimension	Reasoning	Score
Conciseness	The body is lean with no padding or explanation of concepts Claude already knows; every line is brief and purposeful.	3 / 3
Actionability	Instructions are abstract platitudes ('Apply relevant best practices and validate outcomes') with no concrete code, commands, or specific memory-safety patterns, matching the score-1 anchor of describing rather than instructing.	1 / 3
Workflow Clarity	The Instructions are an unordered list of generic directives with no sequence, no multi-step process, and no validation checkpoints for risky operations like resource handling.	1 / 3
Progressive Disclosure	A single one-level-deep reference is signaled, but it points to 'resources/implementation-playbook.md' which does not exist as a bundle file, so the reference is broken and navigation fails.	2 / 3
	Total	7 / 12 Passed

Description

85%Weight 40%Scale 1-3

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 strong: it is concrete, third-person, covers multiple specific mechanisms and languages, and includes an explicit 'Use when' trigger clause. Its main weakness is trigger-term coverage, which lacks several common phrasings a user might naturally say.

Suggestions

Broaden trigger terms to include natural phrases users say, e.g. 'use-after-free', 'memory leaks', 'buffer overflow', 'dangling pointers', or 'memory-safe code'.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete mechanisms and languages ('RAII, ownership, smart pointers, and resource management across Rust, C++, and C') with correct third-person voice, matching the score-3 anchor.	3 / 3
Completeness	Explicitly states both what it does ('Implement memory-safe programming...') and when to use it via an explicit 'Use when...' clause.	3 / 3
Trigger Term Quality	Includes natural phrasings like 'writing safe systems code' and 'preventing memory bugs' but omits common variations users would say such as 'use-after-free', 'memory leak', or 'buffer overflow'.	2 / 3
Distinctiveness Conflict Risk	Scoped to a clear niche (RAII, ownership, smart pointers across Rust/C++/C) with distinct triggers unlikely to conflict with unrelated skills.	3 / 3
	Total	11 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: rmyndharis/antigravity-skills
Path: skills/memory-safety-patterns/SKILL.md
Commit: e63f7dd

Reviewed: 13 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.