memory-safety

Run AddressSanitizer and UndefinedBehaviorSanitizer on the Z3 test suite to detect memory errors, undefined behavior, and leaks. Logs each finding to z3agent.db.

Quality

76%

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

Quality

Content

85%

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

The content is a strong, well-structured workflow with executable commands, explicit outcome-based validation checkpoints, and appropriate externalization of implementation into the bundled script. The only mild weakness is conciseness, where the bug-class enumeration and repeated Action/Expectation/Result scaffold could be trimmed.

Dimension	Reasoning	Score
Conciseness	The body avoids concept-explanation fluff, but the intro parenthetically enumerates every bug class each sanitizer catches and the Action/Expectation/Result scaffold repeats across all three steps — mildly redundant and could be tightened.	2 / 3
Actionability	Provides fully executable, copy-paste-ready bash commands for each sanitizer mode and reuse case, SQL query examples, and a complete Parameters table documenting every flag.	3 / 3
Workflow Clarity	Three clearly sequenced steps (build, run/collect, interpret) each carry explicit Action/Expectation/Result with distinct outcome states (clean/findings/timeout/error) and recovery guidance, functioning as validation checkpoints with error-recovery feedback.	3 / 3
Progressive Disclosure	SKILL.md is a well-organized overview split into steps and a Parameters table, with implementation appropriately externalized to one real bundle script (scripts/memory_safety.py) at a single level of depth and no nested references.	3 / 3
	Total	11 / 12 Passed

Description

67%

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 concrete and distinctive, clearly stating the capability and target, but it lacks an explicit use-when trigger and omits common shorthand terms (ASan/UBSan) that users would naturally say. Adding trigger guidance and natural variations would lift the weakest dimensions.

Suggestions

Add an explicit 'Use when...' trigger clause (e.g., 'Use when investigating memory safety, undefined behavior, or leaks in Z3, or when reproducing a sanitizer-reported crash') to answer the 'when' half of completeness.

Include natural trigger variations users actually say — ASan, UBSan, sanitizer, memory leak, buffer overflow, use-after-free — alongside the formal AddressSanitizer/UndefinedBehaviorSanitizer names.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions — "Run AddressSanitizer and UndefinedBehaviorSanitizer", "detect memory errors, undefined behavior, and leaks", "Logs each finding to z3agent.db" — matching the anchor for listing several specific actions.	3 / 3
Completeness	Clearly states what the skill does, but there is no "Use when..." or equivalent trigger clause answering when Claude should invoke it, which caps completeness at 2 per the guidelines.	2 / 3
Trigger Term Quality	Includes relevant keywords (AddressSanitizer, UndefinedBehaviorSanitizer, memory errors, leaks) but omits common natural variations users actually say — ASan, UBSan, sanitizer, memory leak, buffer overflow, use-after-free.	2 / 3
Distinctiveness Conflict Risk	The niche is sharply specific — sanitizer instrumentation on the Z3 test suite — making it clearly distinguishable and unlikely to trigger for an unrelated skill.	3 / 3
	Total	10 / 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: Z3Prover/z3
Path: .github/skills/memory-safety/SKILL.md
Commit: 1c89937

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.