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.
Install with Tessl CLI
npx tessl i github:santosomar/general-secure-coding-agent-skills --skill code-review-assistant100
Quality
100%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Discovery
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 hits all the marks. It provides specific capabilities (structured review, inline comments, severity levels, priority-ordered checks), uses natural trigger terms users would actually say, includes an explicit 'Use when...' clause with multiple scenarios, and carves out a distinct niche that won't conflict with general coding skills.
| Dimension | Reasoning | Score |
|---|---|---|
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 explicitly names the review dimensions (correctness, error handling, security, maintainability) with priority order. | 3 / 3 |
Completeness | Clearly answers both what (structured code review with inline comments, severity levels, summary, checking specific dimensions) AND when (explicit 'Use when...' clause with four distinct trigger scenarios). | 3 / 3 |
Trigger Term Quality | Includes natural keywords 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 | Clear niche focused specifically on code review with distinct triggers like 'pull request', 'code review', 'preparing code for merge'. The structured output format (inline comments, severity levels) further distinguishes it from general coding assistance skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
100%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is an excellent skill document that demonstrates expert-level code review guidance. It's dense with actionable, specific patterns (off-by-one checks, async/await pitfalls, catch block scrutiny) while maintaining clear structure through the priority-ordered workflow. The worked example and output format make the expected behavior unambiguous.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Every section earns its place. No explanation of what code review is or why it matters—jumps straight to actionable guidance. The tables, examples, and checklists are dense with information Claude wouldn't already know (specific patterns, priority ordering, severity definitions). | 3 / 3 |
Actionability | Highly concrete throughout: specific code patterns to check (off-by-one, De Morgan's, missing await), exact input shapes to test against, real diff example with worked review, and copy-paste-ready output format. The worked example demonstrates exactly how to apply the guidance. | 3 / 3 |
Workflow Clarity | Clear 5-step sequence with explicit stopping condition ('Stop after any tier that produces a Blocking finding'). Each step has specific checks. The priority ordering is explicit and justified. The 'understand before you judge' step establishes a validation checkpoint before reviewing. | 3 / 3 |
Progressive Disclosure | Well-organized single document appropriate for its scope. Uses tables, headers, and the worked example to break up content logically. No need for external references given the self-contained nature of code review guidance. Content flows from principles → steps → output format → example → anti-patterns. | 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.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- 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.