slop

Invoke only when the user explicitly asks to review code through the "single level of abstraction / layered error handling" lens — a function does only its own layer's business logic while errors are handled above or below. The agent reports detections, raw-count measurements, and move directions. Apply only when the user explicitly requests this lens.

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Quality

Content

73%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 delivers concrete, well-sequenced review guidance with a feedback loop and a tight output contract, but it would benefit from tightening the repeated severity-grade rationale and from a worked example to reach full actionability.

Suggestions

Consolidate the duplicated severity-grade rationale (it appears in both 'Scope of this skill' and 'Severity grading belongs downstream') into one section to improve conciseness.

Add one short worked example applying the five checks to a sample function, so the procedure is demonstrated end-to-end and reaches fully copy-ready actionability.

Tighten verbose phrasing such as 'compress a continuous quantity into an uncalibrated three-point scale and are the main source of review-to-review variance' to reduce token cost without losing meaning.

Dimension	Reasoning	Score
Conciseness	The body is substantive and lens-specific without padding Claude-already-knows basics, but the severity-grade rationale is repeated across sections and several passages could be tightened, so it is mostly efficient with some unnecessary length.	3 / 5
Actionability	Concrete executable guidance is provided (classification tags core/down/up/cross-cutting, the no-'and' explanation test, file:line evidence format, output contract items 1-5), but no worked end-to-end example function demonstrates the procedure, keeping it just below fully copy-ready 5.	4 / 5
Workflow Clarity	A clear top-down numbered sequence (name the level, classify, decide down/up, extract, signal, re-read) is given with an explicit feedback loop ('repeat from step 1') and a defined output contract.	5 / 5
Progressive Disclosure	The single self-contained file is well organized with clear section headers and no nested references, though the roughly 130-line body and the duplicated severity rationale show minor organization gaps versus an ideal split.	4 / 5
	Total	16 / 20 Passed

Description

87%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 strong: it clearly scopes a niche lens, provides an explicit invocation gate with natural trigger phrases, and states concrete outputs. Minor gap is the absence of a few synonyms, but both what and when are concretely answered.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ('reports detections, raw-count measurements, and move directions') and names the lens behavior, but the actions are somewhat abstract rather than fully concrete tool-level operations, so it sits below the comprehensive 5 anchor.	4 / 5
Completeness	Explicitly answers both what (reports detections, raw-count measurements, move directions) and when (Invoke only when the user explicitly asks to review code through this lens) with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural trigger phrases ('check whether this function does too much', 'errors should be handled above/below', a Chinese example) and the lens name, but lacks some synonyms (e.g. 'SLAP', 'separation of concerns'), placing it just below exhaustive 5.	4 / 5
Distinctiveness Conflict Risk	A clearly defined niche (single level of abstraction / layered error handling lens) with an explicit gate ('Invoke only when the user explicitly asks') minimizing conflict with other review skills.	5 / 5
	Total	18 / 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: MoonshotAI/kimi-code
Path: .agents/skills/agent-core-review/slop/SKILL.md
Commit: d4e0ad4

Reviewed: 1 day 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.