memory-safety-patterns

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

Quality

48%

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/memory-safety-patterns/SKILL.md

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

Quality

Content

43%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 skill body is short and well-sectioned but largely generic, offering abstract instructions and pointing all concrete material to a referenced file that is missing from the bundle, which undercuts both actionability and disclosure.

Suggestions

Add concrete, executable guidance inline: minimal RAII/smart-pointer code snippets, a use-after-free diagnostic checklist, or specific commands rather than 'apply best practices'.

Create the referenced 'resources/implementation-playbook.md' (or fix the path) so the single detailed reference resolves; alternatively inline the key patterns and drop the dead reference.

Replace the abstract instruction bullets with an explicit workflow with validation checkpoints (e.g. identify ownership transfer -> apply RAII -> verify with sanitizer/leak check -> confirm no raw pointer escapes).

Dimension	Reasoning	Score
Conciseness	The body is lean and free of concept over-explanation, but the generic Instruction bullets ('Apply relevant best practices and validate outcomes') add little value, keeping it just below the fully token-efficient anchor.	4 / 5
Actionability	Instructions are high-level hints ('Clarify goals', 'Apply relevant best practices') with no concrete code, commands, or specific patterns; the only detailed material is deferred to a file that does not exist.	2 / 5
Workflow Clarity	A rough sequence is present via Use/Don't-use selection and generic Instruction bullets, but steps are poorly defined and there are no validation checkpoints for memory-safety operations that the rubric flags as needing feedback loops.	2 / 5
Progressive Disclosure	Sections are reasonably organized and a one-level reference is clearly signaled, but the referenced 'resources/implementation-playbook.md' does not exist in the bundle, so the disclosure path is broken rather than clean.	3 / 5
	Total	11 / 20 Passed

Description

53%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 clearly scopes a coherent niche and lists concrete technical concepts, but it omits any explicit trigger guidance and presents topics rather than performed actions, leaving it at the mid-band across most dimensions.

Suggestions

Add a 'Use when...' clause naming concrete triggers (e.g. 'Use when preventing use-after-free, double-free, or resource leaks, or when choosing between Rust/C++ ownership models').

Reframe the capability list as actions the skill performs (e.g. 'Apply RAII and smart-pointer patterns, diagnose use-after-free and leaks, choose ownership models across languages').

Include natural synonyms and file/feature terms users actually say ('memory leak', 'dangling pointer', 'move semantics', 'borrow checker').

Dimension	Reasoning	Score
Specificity	Names the memory-safety domain and lists several concrete concept terms ('RAII, ownership, smart pointers, and resource management'), but these are topic labels rather than actions the skill performs, so it stops short of comprehensive concrete-action coverage.	3 / 5
Completeness	Provides a clear 'what' but no 'when'; per the guideline a missing 'Use when...' clause caps completeness at 3, and the anchor 3 example matches this exactly.	3 / 5
Trigger Term Quality	Includes relevant technical terms users say (RAII, ownership, smart pointers, memory-safe) but misses common variations and synonyms such as 'use-after-free', 'leaks', or 'memory leak'.	3 / 5
Distinctiveness Conflict Risk	Targets a fairly distinct niche (cross-language memory-safety patterns with RAII/smart pointers) with only minor overlap risk against general systems-programming skills, fitting the 'mostly distinct' anchor above the midpoint.	4 / 5
	Total	13 / 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/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.