code-reviewer

Elite code review expert specializing in modern AI-powered code

Quality

26%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/code-reviewer/SKILL.md

Quality

Content

17%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 body is a persona-style capability catalog rather than operational guidance: it pads the context window with lists of tools and concepts Claude already knows while providing no executable commands, code, or concrete review procedures. Its one progressive-disclosure pointer references a nonexistent file, so the skill offers neither lean inline guidance nor working external depth.

Suggestions

Replace the capability catalog with actionable artifacts: a concrete review checklist, executable commands (e.g., semgrep/CodeQL scan invocations), and at least one worked review example with severity-tagged findings.

Fix the dangling `resources/implementation-playbook.md` reference — either ship the file or remove the pointer — and move the tool/language-specific capability lists into reference files one level deep, leaving SKILL.md as a lean overview.

Cut the Behavioral Traits, Knowledge Base, and Example Interactions sections and rewrite the Response Approach with concrete, verifiable steps (e.g., 'run static analysis, triage findings by severity, verify fixes with tests') instead of abstract directions.

Dimension	Reasoning	Score
Conciseness	Eight capability sections (~155 lines) enumerate tools and concepts Claude already knows — "SonarQube, CodeQL, and Semgrep", "OWASP Top 10", "Clean Code principles and SOLID pattern adherence" — plus filler sections like Behavioral Traits and Knowledge Base. This is noticeably verbose with many padded sections; not 1 because it is enumeration rather than concept explanation and does have section structure, and not 3 because nearly every section could be cut without losing information Claude doesn't have.	2 / 5
Actionability	The body contains no executable code, commands, or concrete steps — the Instructions are meta-direction ("Provide actionable steps and verification") and the Response Approach steps are abstract ("Apply automated tools for initial analysis"). This matches anchor 1 ('Entirely vague or abstract; no concrete code or commands; only describes rather than instructs').	1 / 5
Workflow Clarity	The 10-step "Response Approach" provides a rough sequence but steps are poorly defined and validation is absent (e.g., "Analyze code context", "Conduct manual review") — matching anchor 2. Not 3 because the steps lack the specificity to function as checkpoints, and not 1 because a recognizable sequence does exist.	2 / 5
Progressive Disclosure	Long capability catalogs that clearly belong in separate reference files are inlined in SKILL.md, and the sole reference — "open `resources/implementation-playbook.md`" — points to a file that does not exist (no references/, scripts/, or assets/ directories ship with the bundle). This matches anchor 2 ('content that clearly belongs in separate files is inlined'); not 3 because the only external pointer is a dangling reference rather than a clearly signaled, working one.	2 / 5
	Total	7 / 20 Passed

Description

36%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 a buzzword-heavy persona label rather than a capability statement. It names the code review domain but provides no concrete actions, no natural trigger variants beyond 'code review', and no 'when to use' guidance, making it hard to select over similar review-oriented skills.

Suggestions

Add an explicit 'Use when...' clause with concrete trigger phrases (e.g., 'Use when reviewing pull requests, analyzing code quality, or hunting security vulnerabilities').

Replace buzzwords ('Elite', 'modern AI-powered') with 2-3 concrete actions, e.g., 'Reviews pull requests for bugs, security vulnerabilities (OWASP Top 10), and performance issues; runs static analysis with Semgrep/CodeQL'.

Include natural trigger variants users actually say — pull request, PR review, code quality, static analysis — to improve both trigger-term coverage and distinctiveness from generic review skills.

Dimension	Reasoning	Score
Specificity	The description "Elite code review expert specializing in modern AI-powered code" names the domain (code review) but lists no concrete actions, relying on buzzwords like "Elite" and "modern AI-powered". It matches the anchor 'Names the domain but actions are minimal or generic' — not 3, which requires 1-2 concrete actions, and not 1, since the domain is at least specifically named.	2 / 5
Completeness	It offers only a vague 'what' ("Elite code review expert") with no 'Use when...' clause or equivalent trigger guidance; the rubric guideline caps completeness at 3 for a missing 'when', and anchor 2 ('Has a vague what and no when') is the closest fit. Not 3 because 'when' is entirely absent rather than weakly implied.	2 / 5
Trigger Term Quality	"code review" is a natural phrase a user would say, but the description includes no common variations or synonyms such as pull request, PR, code quality, or review checklist. This matches 'Some relevant keywords but missing common variations or synonyms' — not 4, since coverage is limited to a single real trigger term.	3 / 5
Distinctiveness Conflict Risk	"code review expert" is somewhat specific but would overlap with general review, quality, and security skills; "specializing in modern AI-powered code" adds no distinguishing trigger. Matches 'Somewhat specific but could still overlap with similar skills' — not 4 because no distinct trigger phrases set it apart.	3 / 5
	Total	10 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: sickn33/agentic-awesome-skills
Path: skills/code-reviewer/SKILL.md
Commit: 7b534bc

Reviewed: 5 days ago

Table of Contents

Discovery Implementation Validation

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.