CtrlK
BlogDocsLog inGet started
Tessl Logo

code-review-expert

Expert code review of current git changes with a senior engineer lens. Detects SOLID violations, security risks, and proposes actionable improvements.

85

0.97x
Quality

76%

Does it follow best practices?

Impact

88%

0.97x

Average score across 8 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./frontend/magic-web/.agents/skills/code-review-expert/SKILL.md
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.

The body is well-structured with concrete commands, a clear sequenced workflow, a safety confirmation gate, and clean progressive disclosure into real reference files. The only real weakness is inline checklist duplication that overlaps the bundled references.

Suggestions

Trim the inline SRID/security/quality bullet lists to a brief pointer per area, letting the loaded reference checklists carry the detail and reducing token redundancy.

DimensionReasoningScore

Conciseness

The body is largely lean and actionable, but the inline SRP/OCP/LSP/ISP/DIP, security, and quality bullet lists duplicate content already provided by the loaded reference checklists and could be tightened.

2 / 3

Actionability

Provides concrete executable commands (git status -sb, git diff --stat, git diff, rg/grep) plus a copy-paste output template and a specific inline-comment format, rather than abstract direction.

3 / 3

Workflow Clarity

Seven clearly sequenced steps with edge-case handling (no changes, large diff) and an explicit "Do NOT implement until user confirms" next-steps gate form a clear feedback loop.

3 / 3

Progressive Disclosure

A concise overview points to four well-signaled one-level-deep references, each loaded from its relevant section and mapped in a Resources table; all referenced files exist and are substantive.

3 / 3

Total

11

/

12

Passed

Description

67%

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 specific and distinctive, naming concrete review actions scoped to git changes. Its main weakness is the absence of an explicit "Use when..." trigger clause and incomplete coverage of natural trigger phrasings.

Suggestions

Add an explicit "Use when..." clause naming user triggers such as reviewing a PR, a git diff, or staged changes.

Broaden trigger terms to include common phrasings like "pull request", "PR review", or "review my diff/changes".

DimensionReasoningScore

Specificity

Lists several concrete actions ("Detects SOLID violations, security risks, and proposes actionable improvements") rather than vague language, matching the multi-action anchor.

3 / 3

Completeness

It clearly states what the skill does but lacks an explicit "Use when..." trigger clause, so the when is only implied; the rubric caps this at 2.

2 / 3

Trigger Term Quality

"code review", "git changes", "SOLID", and "security risks" are relevant, but common variations like "PR review", "pull request", or "review my diff" are missing.

2 / 3

Distinctiveness Conflict Risk

"Expert code review of current git changes" defines a clear niche tied to git-diff review, making it unlikely to fire for unrelated skills.

3 / 3

Total

10

/

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
dtyq/magic
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.