CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

73

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

82%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 body is a lean, highly actionable review checklist with concrete helpers, SQL shapes, and a sequenced workflow including validation checkpoints. Minor redundancy between sections and the long inline KB section prevent a perfect score on conciseness and progressive disclosure.

Suggestions

De-duplicate Red Flags and Preferred Fixes by cross-referencing (e.g., list each flag once with its fix inline) to tighten the body and lift conciseness toward 5.

Extract the detailed KB Connector File Size Handling section into a references/ file (e.g. KB_CONNECTOR_BYTES.md) and summarize the three-rule litmus test inline, improving progressive disclosure.

Add an explicit fix-and-revalidate feedback loop to the Review Workflow (e.g., 'after raising a finding, re-confirm the changed source now has explicit bounds') to reach the top workflow_clarity anchor.

DimensionReasoningScore

Conciseness

Dense and competence-assuming — no padding about what Map/Set or Promise.all are — but the Red Flags and Preferred Fixes sections mirror each other and the KB Connector section restates its three requirements twice (list + litmus test), so minor trimming is possible.

4 / 5

Actionability

Names concrete helpers and files (chunkedBatchDelete, readBodyWithLimit, selectRowsByIdChunks, apps/sim/connectors/utils.ts), specific SQL shapes (WHERE id > afterId ORDER BY id LIMIT N), and anti-patterns (Promise.all(items.map(...))), with a copy-ready Findings Format template covering common cases.

5 / 5

Workflow Clarity

The 7-step Review Workflow is clearly sequenced with per-step checkpoints (step 2 enforcement check, step 7 failure-behavior confirmation, and a "good to go" gate), but there is no explicit fix-then-revalidate feedback loop, leaving it just below the top anchor.

4 / 5

Progressive Disclosure

Well-organized into clear sections with one-level-deep external references (Node.js docs, pagination blog posts) clearly signaled; no bundle files exist, and the lengthy inline KB Connector section could plausibly live in a separate reference file, keeping it at 4 rather than 5.

4 / 5

Total

17

/

20

Passed

Description

100%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 is third-person, concise, and fully specifies both capability and trigger conditions. It lists concrete actions and natural trigger terms with strong distinctiveness.

DimensionReasoningScore

Specificity

Lists multiple concrete review actions — "unbounded memory loading, concurrency explosions, oversized payload materialization, and missing pagination or byte caps" — giving comprehensive, specific coverage rather than vague abstraction.

5 / 5

Completeness

Explicitly answers both what ("Review PRs and diffs for ...") and when ("Use when reviewing ...") with concrete trigger phrases, satisfying the top anchor.

5 / 5

Trigger Term Quality

Covers natural trigger terms a reviewer would say — "cleanup jobs, background jobs, data imports/exports, file parsing, API fan-out, workflow execution payloads, large arrays/files" — plus synonyms (rows, files, responses, logs, pages) with no common variant missing.

5 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (memory-load boundedness in PR/diff review) with distinct triggers unlikely to fire for unrelated skills; minimal conflict risk.

5 / 5

Total

20

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

referenced_paths_exist

Referenced path issues: 1 missing

Warning

Total

15

/

16

Passed

Repository
simstudioai/sim
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.