code-reviewer
Elite code review expert specializing in modern AI-powered code
22
3%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/code-reviewer/SKILL.mdQuality
Discovery
0%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 description is extremely weak across all dimensions. It reads as marketing copy ('Elite', 'AI-powered') rather than a functional skill description, provides no concrete actions, no trigger guidance, and no distinguishing details that would help Claude select it appropriately from a list of skills.
Suggestions
Replace vague language with specific concrete actions, e.g., 'Reviews code for bugs, security vulnerabilities, style issues, and performance problems. Analyzes pull requests and suggests improvements.'
Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when the user asks for a code review, PR feedback, code quality check, or wants suggestions on their code changes.'
Remove marketing fluff like 'Elite' and 'AI-powered' and instead describe the specific domain or languages/frameworks the skill covers to improve distinctiveness.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description uses vague, buzzword-heavy language ('Elite code review expert') without listing any concrete actions. It does not specify what the skill actually does (e.g., review pull requests, suggest refactors, check for bugs). | 1 / 3 |
Completeness | The description weakly addresses 'what' (code review) but provides no 'when' clause or explicit trigger guidance. Both dimensions are very weak, with no 'Use when...' or equivalent. | 1 / 3 |
Trigger Term Quality | 'Code review' is a relevant keyword, but 'elite' and 'AI-powered' are marketing fluff rather than natural user trigger terms. Missing common variations like 'PR review', 'pull request', 'code feedback', 'review changes'. | 1 / 3 |
Distinctiveness Conflict Risk | 'Code review' is extremely broad and could overlap with many coding-related skills. 'Modern AI-powered code' is vague and does not carve out a distinct niche. | 1 / 3 |
Total | 4 / 12 Passed |
Implementation
7%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill reads like a persona description or capability catalog rather than an actionable skill file. It extensively lists topics Claude already knows (OWASP, SOLID, static analysis tools, etc.) without providing any concrete code examples, specific commands, validation steps, or executable workflows. The content would need a fundamental restructuring to be useful—replacing descriptive capability lists with concrete review checklists, example code patterns, and specific tool invocation commands.
Suggestions
Replace the extensive capability lists with a concise code review checklist containing specific, actionable items (e.g., 'Check for N+1 queries by searching for ORM calls inside loops; suggest eager loading with `.prefetch_related()` or `.includes()`').
Add concrete, executable examples showing how to perform a code review—e.g., example input code with annotated review comments, specific tool commands like `semgrep --config=p/owasp-top-ten .`, or structured output formats for review findings.
Define a clear multi-step workflow with validation checkpoints, such as: run linter → check security scan results → review logic → verify test coverage → produce structured findings report, with specific commands and expected outputs at each step.
Remove the 'Capabilities', 'Behavioral Traits', and 'Knowledge Base' sections entirely—these describe what Claude already knows—and replace with a focused quick-start section and references to detailed playbooks for specific review types (security, performance, etc.).
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose with extensive lists of capabilities, tools, and concepts that Claude already knows. The bulk of the content is a taxonomy of code review topics (OWASP, SOLID, design patterns, etc.) that adds no actionable value beyond what Claude inherently understands. The 'Behavioral Traits' and 'Knowledge Base' sections describe general qualities rather than providing specific instructions. | 1 / 3 |
Actionability | No concrete code examples, commands, or executable guidance anywhere in the skill. The content is entirely descriptive—listing capabilities, behavioral traits, and example prompts—without providing any specific steps, code snippets, or tool invocations that Claude could actually execute during a code review. | 1 / 3 |
Workflow Clarity | The 'Response Approach' section lists 10 high-level steps but they are vague and lack validation checkpoints, concrete commands, or feedback loops. Steps like 'Apply automated tools' and 'Conduct manual review' provide no specifics on what tools to run, what to check, or how to verify results. No error recovery or validation steps are included. | 1 / 3 |
Progressive Disclosure | There is a single reference to 'resources/implementation-playbook.md' for detailed examples, which is a reasonable attempt at progressive disclosure. However, the main file itself is a monolithic wall of categorized lists that should be significantly trimmed or split into separate reference files. The structure uses headers but the content under each is just bullet-point lists without clear navigation. | 2 / 3 |
Total | 5 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- sickn33/antigravity-awesome-skills
- Commit
93c57b2
- 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.