CtrlK
BlogDocsLog inGet started
Tessl Logo

review

Reviews PR(s) using comprehensive review guidelines including security, correctness, clean code, TypeScript, React patterns, i18n/RTL, performance, and accessibility. Use when reviewing pull requests or code changes.

75

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

85%

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

A well-structured, concise review workflow with concrete commands and clear sequencing. Its main weakness is reliance on an external docs/REVIEW_PROMPT.md for the actual review criteria, which is not bundled with the skill.

Suggestions

Inline the key review criteria (or a condensed rubric) into SKILL.md, or include docs/REVIEW_PROMPT.md as a bundled reference file so the skill is self-contained and the criteria are verifiable.

Add a brief validation checkpoint after fetching PR data (e.g., confirm the diff/non-empty files were retrieved) so command failures are caught before review begins.

Reduce the slight redundancy between the 'Review Criteria' list and the 'Issue Categories' table by cross-referencing one from the other.

DimensionReasoningScore

Conciseness

The body is lean: numbered steps, concrete gh commands, a compact category table, and a defined output format, with no explanation of concepts Claude already knows and only minor redundancy between the criteria list and category table.

3 / 3

Actionability

Concrete executable gh commands ('gh pr view ... --json ...', 'gh pr diff ...') and a clear output structure are present, but the substantive review criteria are delegated to an external 'docs/REVIEW_PROMPT.md' that is not part of the skill bundle, leaving the actionable review guidance incomplete.

2 / 3

Workflow Clarity

A clearly sequenced per-PR workflow with an explicit checkpoint ('If files changed > 15, flag for potential split'), a re-review protocol that checks prior status, and a multi-PR loop with a final confirmation step provide good sequencing and feedback for a non-destructive task.

3 / 3

Progressive Disclosure

The body is organized into clearly labeled sections (Arguments, Steps, Re-review Protocol, Review Criteria, Issue Categories, Output Format, Multi-PR Workflow) with a single clearly-signaled one-level external reference and no nested reference chains.

3 / 3

Total

11

/

12

Passed

Description

100%

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, third-person description that concisely states a specific capability and an explicit use-when trigger covering natural terms. It is well-distinguishable and not padded with fluff.

DimensionReasoningScore

Specificity

It enumerates many concrete review domains — 'security, correctness, clean code, TypeScript, React patterns, i18n/RTL, performance, and accessibility' — rather than vague language, matching the anchor that lists multiple specific concrete capabilities.

3 / 3

Completeness

It states both what it does ('Reviews PR(s) using comprehensive review guidelines including...') and an explicit when trigger ('Use when reviewing pull requests or code changes.'), satisfying the what-AND-when anchor.

3 / 3

Trigger Term Quality

Natural user-facing terms appear — 'PR(s)', 'pull requests', 'code changes', 'reviewing' — which are the phrases a user would naturally say when requesting a review; only minor variations like 'diff' or 'code review' are absent.

3 / 3

Distinctiveness Conflict Risk

PR/pull-request review is a clear, distinct niche with dedicated triggers; the 'code changes' phrasing is slightly broad but the PR framing keeps it unlikely to conflict with unrelated skills.

3 / 3

Total

12

/

12

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
quran/quran.com-frontend-next
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.