CtrlK
BlogDocsLog inGet started
Tessl Logo

1k-code-review-pr

Review OneKey PRs and diffs for security, correctness, concurrency, React/RN pitfalls, and repository-specific regressions. Use for code review or 审查 PR.

74

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

92%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.

A well-structured, highly actionable code-review skill with clear workflows, validation checkpoints, and effective use of one-level reference files. The only weakness is length-driven redundancy across the confidence, priority, and emphasis sections.

Suggestions

Consolidate the confidence-level (emoji tags), priority (P0-P2), and cross-validation rules into a single section; they are currently repeated across Confidence Levels, Auto-Fix Patches, and Cross-Validation Rules.

Trim repeated "MANDATORY" / "CRITICAL" emphasis lines — the rules are clear once; repeated bold caps add tokens without adding information.

Consider moving the full Unified Report Format template and Scoring System anchors into a reference file (e.g. references/report-format.md) to shorten SKILL.md, keeping only the section list inline.

DimensionReasoningScore

Conciseness

The body is mostly lean with concrete commands and no filler explaining concepts Claude already knows, but at ~382 lines it repeats confidence/priority rules across several sections and overuses MANDATORY emphasis that could be consolidated.

4 / 5

Actionability

Fully executable guidance throughout — copy-paste git/gh commands with jq filters, an Agent dispatch snippet, an inline-comment gh api template, and exact scoring deduction rules cover the common cases.

5 / 5

Workflow Clarity

A clear 10-step numbered workflow plus sequenced sub-workflows, with explicit checkpoints (triage, confidence tagging, mandatory scoring/reporting) and feedback loops (cross-validate→promote, refuted→noise section) and guardrails on the batch action of auto-posting comments.

5 / 5

Progressive Disclosure

SKILL.md acts as an overview pointing to four real one-level-deep reference files via a Reference Files section and inline triage-table links, keeping bulk detail in references while retaining only the report template and scoring system inline.

5 / 5

Total

19

/

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.

A strong, specific description that names concrete review dimensions, includes an explicit Use-when trigger, and is tightly scoped to the OneKey repository. Only minor improvement possible by adding synonyms like "pull request" / "diff review".

DimensionReasoningScore

Specificity

Lists multiple concrete review dimensions — "security, correctness, concurrency, React/RN pitfalls, and repository-specific regressions" — giving comprehensive coverage of the skill's actions.

5 / 5

Completeness

Explicitly answers both what ("Review OneKey PRs and diffs for...") and when ("Use for code review or 审查 PR") with a concrete trigger phrase.

5 / 5

Trigger Term Quality

"Use for code review or 审查 PR" provides good natural keyword coverage including a Chinese synonym, but omits common variations like "pull request" or "diff review".

4 / 5

Distinctiveness Conflict Risk

"OneKey PRs and diffs" plus "repository-specific regressions" carve a clear niche with distinct triggers and minimal overlap risk with generic review skills.

5 / 5

Total

19

/

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

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

Total

15

/

16

Passed

Repository
OneKeyHQ/app-monorepo
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.