CtrlK
BlogDocsLog inGet started
Tessl Logo

frontend-code-review

Use only when the user explicitly requests a review or audit of frontend code under `web/` or `packages/dify-ui/`. Supports pending-change, file-focused, and pasted-diff reviews. Do not use for implementation-only requests, diagnosis without review intent, or backend-only code.

72

Quality

89%

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

86%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, well-structured review instruction sheet with excellent progressive disclosure into real reference packs and clear severity/output guidance. The main gap is the absence of concrete example findings that would lift actionability and workflow explicitness to the top anchor.

Suggestions

Add one or two short example findings (file:line, observed failure, fix direction) under 'Severity And Output' to make the expected output format concrete and copy-paste ready.

Insert an explicit verification checkpoint in 'Evidence First' (e.g., 'confirm the cited contract/rule actually applies before reporting') to surface a clear validate-then-report loop.

Consider a one-line note clarifying when to stop reading reference packs (e.g., 'read only the packs matched; do not preload all references') to further tighten actionability.

DimensionReasoningScore

Conciseness

Lean and efficient throughout — it assumes Claude's competence, explains no basic concepts, and every section (Evidence First, Rule Routing, Severity And Output) earns its place with no padding.

5 / 5

Actionability

Provides concrete routing rules keyed to diff characteristics, explicit P0–P3 severity definitions, and a defined output structure, but as an instruction-style review skill it lacks concrete finding examples that would make guidance fully copy-paste ready.

4 / 5

Workflow Clarity

The numbered 'Evidence First' sequence and diff-matched 'Rule Routing' give a clear sequence with implicit checkpoints (scope -> read -> trace -> report), but there is no explicit validate/retry loop, which is acceptable for a read-only review skill though not a 5.

4 / 5

Progressive Disclosure

SKILL.md is a clear overview routing to eight real, one-level-deep reference packs (all confirmed present in ./references/), each linked inline by topic and enumerated in a reference link list, making navigation easy.

5 / 5

Total

18

/

20

Passed

Description

92%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 well-scoped, concrete, and answers both what and when explicitly, with strong path-based triggers and clear exclusions that reduce conflict risk. Trigger term coverage is strong but leaves a few natural synonyms on the table.

DimensionReasoningScore

Specificity

Names the domain (frontend code review/audit) plus concrete review modes — 'pending-change, file-focused, and pasted-diff reviews' — giving comprehensive, specific action coverage rather than generic language.

5 / 5

Completeness

Explicitly answers both what (review/audit frontend code across three review modes) and when ('Use only when the user explicitly requests a review or audit of frontend code under web/ or packages/dify-ui/'), with concrete trigger and exclusion phrases.

5 / 5

Trigger Term Quality

Includes natural terms users would say ('review', 'audit', 'frontend code') plus useful negative triggers ('implementation-only', 'diagnosis', 'backend-only'), though a few common synonyms or phrasings are absent.

4 / 5

Distinctiveness Conflict Risk

Scoped to specific paths and modes with explicit exclusions ('Do not use for implementation-only requests, diagnosis without review intent, or backend-only code'), giving a clear niche with minimal conflict risk.

5 / 5

Total

19

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
langgenius/dify
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.