CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

ios-memgraph-leaks

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

72

Quality

91%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

96%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.

An excellent instruction-oriented skill body: lean, executable commands whose interfaces match the bundled scripts, a well-sequenced workflow with explicit verification rules and error-recovery branches, and appropriate delegation of mechanics to scripts. The only notable gap is the dangling sibling-skill reference.

DimensionReasoningScore

Conciseness

The ~75-line body is lean throughout: it never explains what memgraphs or retain cycles are, and every section (Capture, Summarize, Root Cause Rules, Report) adds non-obvious judgment calls like "Do not derive SKILL_DIR from the target app repo's pwd". Not a 4 because there is no padded or over-explained passage to trim.

5 / 5

Actionability

Both command blocks are copy-paste ready and their flags match the actual bundle scripts (capture_sim_memgraph.sh takes --udid/--bundle-id/--out-dir; summarize_memgraph_leaks.py takes --trace-limit/--out), and concrete fallbacks like `xcrun simctl spawn "$SIM" launchctl list` and `leaks --groupByType <file.memgraph>` are given. Placeholders like <simulator-udid> are environment values, not pseudocode, so it sits fully at the top anchor.

5 / 5

Workflow Clarity

The six-step Core Workflow is clearly sequenced and heavily validation-centric: explicit before/after recapture of the same flow, "Do not claim a leak fix from a smaller memgraph alone", "prove the specific type or path disappeared", and an error-recovery branch when the process cannot be found. Not a 4 because validation checkpoints are explicit and repeated, not implicit.

5 / 5

Progressive Disclosure

The bundle is well structured: mechanical detail is correctly delegated to the two existing, clearly referenced scripts, and the body stays an overview with organized sections. Not a 5 because the sibling-skill pointer `../ios-debugger-agent/SKILL.md` is not resolvable from this bundle, a minor navigation gap alongside a plain-text (non-link) reference style.

4 / 5

Total

19

/

20

Passed

Description

82%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 description with an explicit what and when, concrete trigger phrases, and a clearly distinct iOS-memgraph niche. Its only weakness is that it advertises just two actions (capture, inspect) while the skill also summarizes leaks and drives root-cause analysis, and it lacks a few natural synonyms.

Suggestions

Add 1-2 more concrete actions to the description, e.g. "...summarize leaked types and ownership paths" or "generate before/after leak evidence", to raise specificity.

Include common synonyms users would naturally say, such as "memory leaks", "heap growth", or ".memgraph files", to broaden trigger-term coverage.

DimensionReasoningScore

Specificity

"Capture and inspect iOS leaks and memgraphs" names the domain plus two concrete actions (capture, inspect), matching the '1-2 concrete actions, but not comprehensive' anchor; the summarizing/root-cause/reporting work the skill actually performs is not reflected in the description. It is not a 4 because no further specific actions are listed beyond the two.

3 / 5

Completeness

Both parts are explicit: the what ("Capture and inspect iOS leaks and memgraphs") and a concrete when ("Use when debugging leaked objects, retain cycles, memory growth, or before/after leak evidence"), matching the anchor with concrete trigger phrases. Not below 5 since neither half is vague or merely implied.

5 / 5

Trigger Term Quality

"leaked objects, retain cycles, memory growth, before/after leak evidence" are natural phrases a developer debugging memory would say. Not a 5 because common variations are missing: "memory leak(s)", "heap growth", ".memgraph", or "Xcode memory graph".

4 / 5

Distinctiveness Conflict Risk

A clear niche (iOS memgraph-based leak debugging) with distinct triggers (retain cycles, memgraphs, before/after leak evidence) that would not plausibly route to a generic memory or debugging skill. Not a 4 because no meaningful overlap risk with closely related skills is evident from the description alone.

5 / 5

Total

17

/

20

Passed

Validation

100%

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

Reviewed

Table of Contents

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.