CtrlK
BlogDocsLog inGet started
Tessl Logo

code-review-assistant

Performs structured code review on a diff or file set, producing inline comments with severity levels and a summary. Checks correctness, error handling, security, and maintainability — in that priority order. Use when reviewing a pull request, when the user asks for a code review, when preparing code for merge, or when a second opinion is needed on a change.

72

Quality

88%

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

77%

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

This is a high-quality, expert-level code review skill that provides genuinely actionable guidance a senior engineer would recognize as valuable. Its greatest strengths are the clear priority-ordered workflow, specific and concrete checks at each step, well-defined severity levels, and an excellent worked example. The main weakness is length — at ~200 lines it's on the verbose side for a single SKILL.md, though most content earns its place.

Suggestions

Consider extracting the worked example and/or the edge-case input table into a separate reference file (e.g., EXAMPLES.md) to reduce the main skill's token footprint while preserving the valuable content.

DimensionReasoningScore

Conciseness

The skill is well-written and mostly efficient, but it's quite long (~200 lines). Some sections like the edge-case table and the security checklist are valuable, but the worked example, while excellent for teaching, adds significant length. The 'Do not' section restates some points already implied. Overall it earns most of its tokens but could be tightened in places.

2 / 3

Actionability

Extremely actionable — provides specific checks to perform at each step (e.g., 'expand De Morgan's in your head', 'Missing await on a promise-returning call'), concrete severity definitions with clear obligations, a complete output format example, and a worked example showing exactly how to apply the methodology to a real diff. Copy-paste ready output template.

3 / 3

Workflow Clarity

The workflow is clearly sequenced (Steps 1-5) with an explicit priority ordering and a stopping rule ('Stop after any tier that produces a Blocking finding'). Each step has specific checks to perform. The severity table acts as a decision framework, and the output format provides a clear checkpoint for structuring results. The instruction to ask for a PR description when missing is a validation checkpoint.

3 / 3

Progressive Disclosure

The content is well-organized with clear headers and sections, but it's a monolithic document with no references to external files. Given the length (~200 lines), the worked example and the detailed edge-case tables could potentially be split into separate reference files. However, for a standalone skill with no bundle, keeping everything inline is reasonable — it just pushes the boundary of what should be in a single file.

2 / 3

Total

10

/

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.

This is an excellent skill description that clearly articulates what the skill does (structured code review with inline comments, severity levels, and prioritized checks) and when to use it (pull requests, code reviews, merge preparation). It uses natural trigger terms, is concise without being vague, and occupies a distinct niche that minimizes conflict with other skills.

DimensionReasoningScore

Specificity

Lists multiple specific concrete actions: 'structured code review on a diff or file set', 'producing inline comments with severity levels and a summary', and specifies the priority order of checks (correctness, error handling, security, maintainability).

3 / 3

Completeness

Clearly answers both 'what' (structured code review producing inline comments with severity levels, checking correctness/error handling/security/maintainability) and 'when' (explicit 'Use when...' clause covering pull requests, code review requests, merge preparation, and second opinions).

3 / 3

Trigger Term Quality

Includes strong natural trigger terms users would say: 'pull request', 'code review', 'merge', 'diff', 'second opinion on a change'. These cover common variations of how users request code reviews.

3 / 3

Distinctiveness Conflict Risk

Clearly scoped to code review with distinct triggers like 'pull request', 'diff', 'merge', 'inline comments with severity levels'. Unlikely to conflict with general coding skills or documentation skills due to the specific review-oriented language.

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.

Validation11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository
santosomar/general-secure-coding-agent-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.