CtrlK
BlogDocsLog inGet started
Tessl Logo

code-review

Perform thorough code reviews focusing on correctness, readability, and security.

60

Quality

70%

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

Fix and improve this skill with Tessl

tessl review fix ./code-review/SKILL.md
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 content is a tight, well-structured instruction skill: a concise checklist, clear feedback directives, and concrete examples, with no padding and no unnecessary external references. Its only weakness is mild: as an instruction-only skill it lacks executable tooling/commands and an explicit ordered workflow with checkpoints.

DimensionReasoningScore

Conciseness

The body is lean and efficient: a terse checklist, a short feedback-style list, and two brief illustrative quotes, with no over-explanation of what code review is or basic concepts Claude already knows, matching anchor 5 (every token earns its place); it is not 4 because there is no padding or unnecessary explanation to trim.

5 / 5

Actionability

Concrete, specific guidance is present — security items name real risks ("No injection, no leaked secrets, no unsafe deserialization"), feedback style directs referencing line numbers and suggesting alternatives, and examples show actual review comments — matching anchor 4 (mostly executable guidance with minor gaps); not 5 because, being instruction-only, it lacks fully copy-paste-ready tooling/commands, and not 3 because the guidance and examples are concrete rather than pseudocode or vague.

4 / 5

Workflow Clarity

The numbered checklist (1-5) provides a clear review sequence and the feedback-style section defines how to respond, giving a clear, well-organized process for a simple non-destructive skill, matching anchor 4; not 5 because there is no explicit end-to-end sequence or validation checkpoints, and not 3 because the checklist supplies a real ordered sequence rather than loosely defined steps.

4 / 5

Progressive Disclosure

The skill is under 50 lines with no bundle files and no need for external references, yet is cleanly organized into well-signaled sections (Review Checklist, Feedback Style, Examples), meeting the simple-skill exception for anchor 5; not 4 because the structure is clean and navigation is trivial with no inline bloat or buried references.

5 / 5

Total

18

/

20

Passed

Description

53%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 clear and appropriately concise, naming the domain and three review focus areas, but it lacks any explicit "Use when..." trigger guidance and offers only thin keyword coverage. Adding a trigger clause with natural terms like "PR" or "pull request review" would lift completeness and trigger-term quality.

Suggestions

Append a 'Use when...' clause, e.g. 'Use when reviewing a pull request, PR, or diff for correctness, readability, and security issues.'

Include natural trigger synonyms users say, such as 'code review', 'PR review', 'pull request', or 'diff review', to broaden keyword coverage.

Optionally enumerate concrete review actions (e.g. 'check edge cases, flag security risks, suggest readability improvements') to push specificity toward 4-5.

DimensionReasoningScore

Specificity

"Perform thorough code reviews focusing on correctness, readability, and security" names the domain and one main action plus three review dimensions, matching anchor 3 (1-2 concrete actions, not comprehensive); it is above anchor 2 because the three named focus areas add concrete substance beyond a single generic action, but below 4 since "perform code reviews" is essentially one action without enumerating concrete review activities.

3 / 5

Completeness

It clearly states what ("Perform thorough code reviews focusing on correctness, readability, and security") but has no "Use when..." or equivalent trigger clause, so per the missing-trigger-guidance cap it lands at anchor 3; not 4 because no explicit "when" guidance is present, not 2 because the "what" is clear rather than vague.

3 / 5

Trigger Term Quality

"code reviews" is a strong natural keyword users would say, but the description omits common variations/synonyms like "PR", "pull request", or "diff review", matching anchor 3 (some relevant keywords, missing common variations); it is below 4 due to limited keyword coverage and above 2 because "code reviews" is a genuinely natural trigger term rather than generic jargon.

3 / 5

Distinctiveness Conflict Risk

"code reviews" is a mostly distinct niche with only minor overlap risk against general coding skills, matching anchor 4; it is below 5 because the description lacks explicit distinct trigger phrases, and above 3 because code review is clearly more specific than broadly "works with code".

4 / 5

Total

13

/

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
neil-tessl/skill-index-evals-dev
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.