ios-memgraph-leaks

Capture and inspect iOS leaks and memgraphs. Use when debugging leaked objects, retain cycles, memory growth, or before/after leak evidence.

Quality

82%

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

Quality

Content

86%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.

A tightly written, highly actionable skill body with concrete commands, a sound workflow plus feedback loop, and clean one-level-deep file references. Only minor tightening of duplicated guidance and inline validation markers would push it higher.

Dimension	Reasoning	Score
Conciseness	Lean and assumes Claude's competence (no explainer prose on what leaks/retain cycles are), with substantive code and rules; held at 4 rather than 5 because the 'do not claim a fix from count alone' guidance is restated across Core Workflow and Root Cause Rules.	4 / 5
Actionability	Fully executable, copy-paste-ready bash invocations with real script paths and real flags (--udid, --bundle-id, --out-dir, --trace-limit) plus concrete leaks subcommands for traceTree and groupByType, covering the common capture/summarize/trace cases.	5 / 5
Workflow Clarity	A clear 6-step Core Workflow with a recapture feedback loop and a separate Root Cause Rules checklist; held at 4 rather than 5 because validation checkpoints live in a separate section rather than being bolded inline in the step sequence (as in the top anchor).	4 / 5
Progressive Disclosure	Well-organized sections with clearly signaled, one-level-deep references to the two real bundle scripts (scripts/capture_sim_memgraph.sh, scripts/summarize_memgraph_leaks.py) and the sibling ../ios-debugger-agent/SKILL.md; no nested or buried references.	5 / 5
	Total	18 / 20 Passed

Description

78%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.

A strong, third-person description that explicitly pairs a concrete capability statement with natural trigger phrases. The main gap is modest action breadth and a few missing synonyms rather than any structural weakness.

Dimension	Reasoning	Score
Specificity	Names the iOS-leak domain and two concrete actions ("Capture and inspect iOS leaks and memgraphs"), matching the 1-2 concrete actions anchor; not comprehensive enough for a 4 since it lists only capture/inspect rather than several distinct operations.	3 / 5
Completeness	Explicitly answers both what ("Capture and inspect iOS leaks and memgraphs") and when with concrete trigger phrases ("Use when debugging leaked objects, retain cycles, memory growth, or before/after leak evidence"), matching the top anchor; the explicit 'Use when' clause removes the cap at 3.	5 / 5
Trigger Term Quality	Good natural keyword coverage ("leaked objects, retain cycles, memory growth, before/after leak evidence") plus "iOS leaks" and "memgraphs"; falls short of 5 because common synonyms like "memory leak", "Instruments", or the ".memgraph" extension are absent.	4 / 5
Distinctiveness Conflict Risk	Clear leak/memgraph niche with distinct triggers and low conflict risk, but it shares the iOS-debugging space with the sibling ios-debugger-agent skill it explicitly pairs with, so it is not quite the minimal-conflict 5.	4 / 5
	Total	16 / 20 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: openai/plugins
Path: plugins/build-ios-apps/skills/ios-memgraph-leaks/SKILL.md
Commit: d416fd5

Reviewed: 4 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.