CtrlK
BlogDocsLog inGet started
Tessl Logo

pr-review-expert

Use when the user asks to review pull requests, analyze code changes, check for security issues in PRs, or assess code quality of diffs.

68

Quality

81%

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

The canonical home for this skill is pr-review-expert in alirezarezvani/claude-skills

SKILL.md
Quality
Evals
Security

Quality

Content

75%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 thorough, highly actionable PR-review skill with executable commands for both GitHub and GitLab and a clear six-step workflow. Its main weaknesses are length/redundancy and a monolithic structure with limited error-recovery feedback loops.

Suggestions

Deduplicate the diff-fetching commands: the standalone "Fetching the Diff" section repeats what Step 1 already covers — consolidate into one place to trim tokens.

Add explicit validation/feedback loops (e.g. "if CI checks fail, report and stop"; "if coverage delta < threshold, re-run with --coverage and surface missing lines") to lift workflow clarity.

Consider moving the 30+ item checklist and the security/performance grep catalog into a references/ file linked from SKILL.md so the main file reads as an overview pointing to detailed materials.

DimensionReasoningScore

Conciseness

The body is information-dense and avoids explaining concepts Claude already knows, but at ~390 lines it includes redundancy — e.g. the "Fetching the Diff" section duplicates commands restated in "Step 1 — Fetch Context" — so it could be tightened; fits the "mostly efficient but includes some unnecessary explanation or could be tightened" anchor rather than a 4.

3 / 5

Actionability

Copy-paste-ready executable commands throughout — gh/glab CLI invocations and concrete grep patterns for SQL injection, secrets, XSS, N+1, etc. — cover the common review cases, matching the "fully executable; copy-paste ready" anchor.

5 / 5

Workflow Clarity

A clear six-step sequence (Fetch Context → Blast Radius → Security → Coverage → Breaking Changes → Performance) plus CI-status and coverage-rule checkpoints and a 30+ item checklist; not a 5 because explicit error-recovery feedback loops (validate → fix → retry) are largely absent beyond the coverage block rule.

4 / 5

Progressive Disclosure

Well-organized with clear section headers and logical navigation, and no bundle files exist so all content is appropriately inline; the gap keeping it from 5 is the monolithic ~390-line manual where the command catalog or checklist could be split into one-level-deep reference files.

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.

A strong, third-person description with an explicit "Use when…" trigger clause and several concrete actions tied to natural user phrasing. It clearly communicates both capability and activation conditions with low conflict risk.

DimensionReasoningScore

Specificity

Quotes "review pull requests, analyze code changes, check for security issues in PRs, or assess code quality of diffs" — four named concrete actions in the PR/diff domain, matching the "lists several specific actions; minor gaps" anchor; not a 5 because "assess code quality" is somewhat generic and coverage of capabilities (e.g. test coverage, breaking-change detection) shown in the body is absent from the description.

4 / 5

Completeness

Explicitly answers both: what ("review pull requests, analyze code changes, check for security issues… assess code quality of diffs") and when ("Use when the user asks to…") with concrete trigger phrases, matching the top anchor exactly.

5 / 5

Trigger Term Quality

Natural user phrases appear — "review pull requests", "PRs", "security issues", "code quality", "diffs" — with synonyms (pull requests/PRs, code changes/diffs); not a 5 because common variants like "code review" and "merge request / MR" are missing.

4 / 5

Distinctiveness Conflict Risk

PR/diff review is a clear niche with distinctive triggers ("pull requests", "PRs", "diffs") and minimal overlap risk with other skills; matches the "clear niche with distinct triggers; minimal conflict risk" anchor.

5 / 5

Total

18

/

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
alirezarezvani/claude-skills
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.