code-reviewer
Elite code review expert specializing in modern AI-powered code
17
3%
Does it follow best practices?
Impact
—
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 more like a marketing tagline than a functional skill description, using vague superlatives ('elite,' 'AI-powered') without specifying concrete actions, trigger conditions, or a clear niche. It would be nearly impossible for Claude to reliably select this skill from a pool of coding-related skills.
Suggestions
Replace vague language with specific actions, e.g., 'Reviews code for bugs, security vulnerabilities, performance issues, and style violations. Analyzes diffs 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, diff analysis, or wants code quality suggestions.'
Remove marketing fluff like 'Elite' and 'AI-powered' and instead clarify what distinguishes this skill from general coding assistance (e.g., specific languages, frameworks, or review methodologies supported).
| 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 barely addresses 'what' (code review, vaguely) and completely omits 'when' — there is no 'Use when...' clause or any explicit trigger guidance. | 1 / 3 |
Trigger Term Quality | The only potentially useful trigger term is 'code review,' but 'elite' and 'AI-powered' are marketing fluff rather than natural user keywords. Missing terms like 'PR review,' 'pull request,' 'diff,' 'review changes,' etc. | 1 / 3 |
Distinctiveness Conflict Risk | 'Code review' is extremely broad and could overlap with linting skills, testing skills, refactoring skills, or general coding assistance skills. 'AI-powered code' adds confusion rather than clarity about the 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 is essentially a persona description and capability catalog rather than an actionable skill. It lists dozens of topics Claude already knows about (OWASP, SOLID, static analysis tools, etc.) without providing any concrete review checklists, executable commands, code examples, or specific workflows. The content would need a fundamental restructuring to be useful—replacing abstract descriptions with concrete, copy-paste-ready review procedures and tool-specific commands.
Suggestions
Replace the abstract 'Capabilities' and 'Knowledge Base' bullet lists with a concrete code review checklist containing specific items to check (e.g., 'Check for N+1 queries by searching for ORM calls inside loops').
Add executable code examples showing how to run specific tools (e.g., `semgrep --config=p/owasp-top-ten .` or `npx eslint --ext .ts src/`) and how to interpret their output.
Define a concrete workflow with validation checkpoints, e.g., '1. Run static analysis → 2. Check for security issues using [specific checklist] → 3. Verify test coverage meets threshold → 4. Review architecture against [specific patterns]' with explicit pass/fail criteria.
Remove the 'Behavioral Traits', 'Knowledge Base', 'Example Interactions', and 'Limitations' boilerplate sections—these consume tokens without adding actionable guidance Claude doesn't already possess.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose and padded with information Claude already knows. The massive 'Capabilities' section reads like a marketing brochure listing every possible code review topic (OWASP, SOLID, PEP 8, etc.) without adding actionable value. The 'Knowledge Base', 'Behavioral Traits', and 'Limitations' sections restate obvious concepts. Most of this content is wasted tokens. | 1 / 3 |
Actionability | No concrete code examples, commands, or executable guidance anywhere. The entire skill is abstract descriptions and bullet-point lists of topics. Instructions like 'Apply relevant best practices and validate outcomes' and 'Analyze code context and identify review scope' are vague directives with no specifics on how to actually perform a code review. | 1 / 3 |
Workflow Clarity | The 'Response Approach' section lists 10 steps but they are generic and lack validation checkpoints, concrete tool commands, or feedback loops. Steps like 'Apply automated tools' and 'Conduct manual review' provide no specifics on what tools, what commands, or how to verify results. No error recovery or validation gates are defined. | 1 / 3 |
Progressive Disclosure | There is one reference to 'resources/implementation-playbook.md' for detailed examples, which is a reasonable attempt at progressive disclosure. However, no bundle files exist to support this reference, and the massive inline content (capabilities, knowledge base, behavioral traits) should have been split into separate reference files rather than dumped into the main skill body. | 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
79d9c42
- 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.