comprehensive-review-full-review
Use when working with comprehensive review full review
24
13%
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/comprehensive-review-full-review/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 is an extremely poor skill description that fails on every dimension. It provides no concrete actions, no meaningful trigger terms, and is essentially incoherent with the redundant phrase 'comprehensive review full review.' It would be nearly impossible for Claude to correctly select this skill from a list of available skills.
Suggestions
Define what the skill actually does by listing specific concrete actions (e.g., 'Conducts code reviews by analyzing diffs, checking for bugs, and suggesting improvements').
Clarify the domain and type of review (e.g., code review, document review, performance review) to make the description distinctive and reduce conflict risk.
Add a proper 'Use when...' clause with natural trigger terms users would actually say (e.g., 'Use when the user asks for a code review, PR feedback, or wants to review changes before merging').
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description contains no concrete actions whatsoever. 'Working with comprehensive review full review' is vague and abstract with no indication of what the skill actually does. | 1 / 3 |
Completeness | The 'what' is entirely missing — there is no description of what the skill does. While there is a 'Use when' clause, it provides no meaningful trigger guidance since 'working with comprehensive review full review' is incoherent. | 1 / 3 |
Trigger Term Quality | The only keyword is 'review,' which is extremely generic and could apply to code reviews, document reviews, performance reviews, etc. 'Comprehensive review full review' is redundant and not a natural phrase users would say. | 1 / 3 |
Distinctiveness Conflict Risk | The term 'review' is extremely generic and would conflict with any skill related to reviews of any kind — code reviews, document reviews, peer reviews, etc. There is nothing distinctive here. | 1 / 3 |
Total | 4 / 12 Passed |
Implementation
27%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is an overly verbose, template-heavy document that reads more like a project planning document than an actionable skill for Claude. It suffers from excessive token usage explaining concepts Claude already knows, relies on pseudo-instructions with placeholder variables rather than executable guidance, and dumps everything into a single monolithic file. The phased structure shows some organizational thought but lacks the validation checkpoints and concrete examples needed for reliable execution.
Suggestions
Reduce content by 70%+ by removing explanations of well-known concepts (OWASP, SOLID, CI/CD) and trimming subagent prompt templates to essential parameters only.
Add concrete, executable examples showing actual Task tool invocations with real inputs and expected output formats rather than template placeholders.
Add explicit validation checkpoints between phases (e.g., 'Verify Phase 1 output contains at minimum: quality score, code smell count, and refactoring list before proceeding to Phase 2').
Split detailed subagent prompts, priority classification criteria, and success metrics into separate referenced files to improve progressive disclosure and reduce the main skill's token footprint.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose with extensive explanations Claude doesn't need. The extended thinking block, detailed prompt templates for subagents, and exhaustive enumeration of tools (SonarQube, CodeQL, Semgrep, Snyk, Trivy, GitLeaks) add massive token overhead. The content reads like a design document rather than a concise skill. Many sections explain obvious concepts (what OWASP Top 10 is, what CI/CD means) that Claude already knows. | 1 / 3 |
Actionability | The skill provides structured phases and specific tool references, but relies on pseudo-instructions like 'Use Task tool with subagent_type="code-reviewer"' without executable code or real commands. The prompts are templates with placeholder variables ($ARGUMENTS, {phase1_context}) but no concrete examples of actual inputs/outputs. It describes what to do at a high level but lacks copy-paste ready commands. | 2 / 3 |
Workflow Clarity | The four-phase sequential structure is clear and logically ordered with dependencies between phases noted. However, there are no explicit validation checkpoints or feedback loops — no 'if this fails, do X' guidance. The workflow describes what each phase should produce but doesn't specify how to verify phase outputs before proceeding, which is critical for a multi-phase review process. | 2 / 3 |
Progressive Disclosure | The skill is a monolithic wall of text with no bundle files to support it. It references 'resources/implementation-playbook.md' but no such file exists in the bundle. All content is inlined in a single massive file with no meaningful separation of concerns. The detailed subagent prompts, configuration options, priority classifications, and success criteria could all be split into separate referenced files. | 1 / 3 |
Total | 6 / 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
f5dc9e3
- 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.