memory-load-check

Review PRs and diffs for unbounded memory loading, concurrency explosions, oversized payload materialization, and missing pagination or byte caps. Use when reviewing cleanup jobs, background jobs, data imports/exports, file parsing, API fan-out, workflow execution payloads, large arrays/files, or any change that reads many rows, files, responses, logs, or external API pages into process memory.

Quality

88%

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

77%

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

A dense, highly actionable review guide with a clear sequenced workflow, but it carries verbose inline reference catalogs (helpers, connector handling) that overlap and could be externalized for better token efficiency and progressive disclosure.

Suggestions

Tighten the 'KB Connector File Size Handling' section to the litmus test plus the three required calls; the helper roster is already covered in 'Sim Helpers'.

Move the detailed 'Sim Helpers' and 'KB Connector' catalogs into a references/ file (e.g. references/helpers.md) and keep SKILL.md as an overview pointing to them, improving progressive disclosure.

Trim the 'References' URL list to the two most decision-relevant links to reduce token cost.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and operational with no conceptual filler, but the 'KB Connector File Size Handling' section (~18 lines) restates helpers already listed in 'Sim Helpers' and elaborates beyond what each token earns.	2 / 3
Actionability	Concrete and copy-ready: named helpers with file paths, exact calls like readBodyWithLimit(resp, CONNECTOR_MAX_FILE_BYTES), and precise SQL shapes like 'WHERE id > afterId ORDER BY id LIMIT N'.	3 / 3
Workflow Clarity	The 7-step 'Review Workflow' is a clearly sequenced check process with explicit pass/fail criteria ('If the code does not enforce one, it is unbounded') and a 'Confirm failure behavior' verification step.	3 / 3
Progressive Disclosure	Well-sectioned with clear headers and one-level external URL references, but the large 'Sim Helpers' and 'KB Connector' catalogs are inline reference material that could be split into a references/ file rather than living in SKILL.md.	2 / 3
	Total	10 / 12 Passed

Description

100%

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 states concrete capabilities, gives explicit and natural 'Use when...' triggers, and occupies a clear niche. It answers both what and when without padding.

Dimension	Reasoning	Score
Specificity	Names multiple concrete review checks — 'unbounded memory loading, concurrency explosions, oversized payload materialization, and missing pagination or byte caps' — rather than vague actions.	3 / 3
Completeness	Explicitly answers both what ('Review PRs and diffs for...') and when ('Use when reviewing...'), with an explicit trigger clause present.	3 / 3
Trigger Term Quality	The 'Use when...' clause covers natural terms a reviewer would say: cleanup jobs, background jobs, data imports/exports, file parsing, API fan-out, large arrays/files, and reads of many rows/files/responses/logs.	3 / 3
Distinctiveness Conflict Risk	The bounded-memory / unbounded-load niche with specific triggers is clearly distinguishable from general code-review skills and unlikely to fire for the wrong skill.	3 / 3
	Total	12 / 12 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
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	15 / 16 Passed

Repository: simstudioai/sim
Path: .agents/skills/memory-load-check/SKILL.md
Commit: 6f514c1

Reviewed: about 16 hours 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.