agent-native-reviewer

Reviews code to ensure agent-native parity -- any action a user can take, an agent can also take. Use after adding UI features, agent tools, or system prompts.

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

92%

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

A highly actionable, well-sequenced review methodology with concrete search strategies, code examples, and calibration guidance. The only notable weakness is that all reference material lives inline in one file with no progressive disclosure into bundle files.

Suggestions

Move the stack-specific search-strategies table and/or the Anti-Patterns Reference table into a references/ file (e.g., references/search-strategies.md) and link to it from SKILL.md to reduce the inline footprint.

Extract the Output Format template into a separate reference or asset so the main body stays a lean overview while preserving the copy-paste template.

Consider splitting the per-step detail (steps 2-6) into a referenced deeper file, keeping SKILL.md focused on triage and the capability-map workflow.

Dimension	Reasoning	Score
Conciseness	The body is dense and actionable throughout with no padding or explanations of concepts Claude already knows; the stack-specific search table, the anti-pattern vs. correct TypeScript snippets, and calibration guidance each earn their place. It is not score-2 because there is no unnecessary explanation to tighten.	3 / 3
Actionability	It gives concrete executable guidance: stack-specific grep patterns and tool locations, a copy-paste TypeScript anti-pattern vs. correct primitive example, a capability-map table template, and a full output-format template. This matches the fully-executable/specific-examples anchor.	3 / 3
Workflow Clarity	A clearly sequenced process (Triage then steps 1-6 including the Noun Test) with prioritization tiers, severity guidance, and a confidence-calibration checkpoint. As a read-only review skill it needs no destructive-operation validation, so the explicit-sequence-with-checklists anchor is met.	3 / 3
Progressive Disclosure	The skill is a single monolithic ~180-line file with no references/, scripts/, or assets/ bundle files; the stack-specific search table, anti-patterns reference, and output template are inline material that could be split into one-level-deep reference files. This fits the some-structure-but-content-should-be-separate anchor rather than the under-50-lines exception.	2 / 3
	Total	11 / 12 Passed

Description

85%

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, specific description in third person that clearly states both capability and trigger conditions. Its main weakness is a somewhat narrow trigger-term set that omits common developer phrasings around agent integration.

Suggestions

Broaden trigger terms to include natural developer phrasings like "agent integration", "agent-accessible", or "make this agent-accessible" so the skill surfaces for more varied requests.

Consider adding a negative-scope cue (e.g., 'not for general code review') to further reduce conflict risk with generic review skills.

Dimension	Reasoning	Score
Specificity	Names a concrete capability ("Reviews code to ensure agent-native parity") and defines that parity precisely ("any action a user can take, an agent can also take"), plus concrete trigger contexts (UI features, agent tools, system prompts). It is more comprehensive than the score-2 anchor and matches the multiple-specific-actions anchor.	3 / 3
Completeness	It explicitly answers both what ("Reviews code to ensure agent-native parity...") and when ("Use after adding UI features, agent tools, or system prompts") with an explicit trigger clause, matching the clearly-answers-both anchor.	3 / 3
Trigger Term Quality	The triggers "UI features, agent tools, or system prompts" are natural and relevant, but the set is narrow and misses common variations a developer might actually say (e.g., "agent integration", "agent-accessible", "agent can't do X"), fitting the some-keywords-but-missing-variations anchor rather than full coverage.	2 / 3
Distinctiveness Conflict Risk	"agent-native parity" is a clear niche with distinct change-based triggers, making it unlikely to fire for unrelated skills, matching the clear-niche-distinct-triggers anchor.	3 / 3
	Total	11 / 12 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: udecode/plate
Path: .agents/skills/agent-native-reviewer/SKILL.md
Commit: 45116fd

Reviewed: about 13 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.