comprehensive-review-full-review
Use when working with comprehensive review full review
Install with Tessl CLI
npx tessl i github:sickn33/antigravity-awesome-skills --skill comprehensive-review-full-review43
Quality
17%
Does it follow best practices?
Impact
85%
1.13xAverage score across 3 eval scenarios
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/comprehensive-review-full-review/SKILL.mdDiscovery
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 severely deficient across all dimensions. It appears to be malformed or incomplete, containing redundant phrasing ('review full review') and no actual description of capabilities. The description provides no useful information for Claude to determine when to select this skill.
Suggestions
Define what type of review this skill performs (e.g., 'code review', 'document review', 'PR review') and list 2-3 specific actions it can take.
Add domain-specific trigger terms that users would naturally say, such as file types, tool names, or specific review contexts (e.g., 'pull request', 'merge request', '.diff files').
Rewrite the 'Use when' clause with meaningful conditions, such as 'Use when the user asks for code review, wants feedback on a pull request, or mentions reviewing changes.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description contains no concrete actions whatsoever. 'Comprehensive review full review' is abstract and redundant language that doesn't describe what the skill actually does. | 1 / 3 |
Completeness | The description fails to answer 'what does this do' entirely. While it has a 'Use when' clause, the trigger condition ('working with comprehensive review full review') is nonsensical and provides no meaningful guidance. | 1 / 3 |
Trigger Term Quality | The only keyword is 'review' repeated twice, which is extremely generic. No natural variations, domain-specific terms, or file types are mentioned that users would naturally say. | 1 / 3 |
Distinctiveness Conflict Risk | The term 'review' is extremely generic and would conflict with any skill involving code review, document review, PR review, performance review, etc. There is no clear niche or distinguishing characteristic. | 1 / 3 |
Total | 4 / 12 Passed |
Implementation
35%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill attempts to orchestrate a comprehensive code review workflow but suffers from excessive verbosity and lack of concrete executable examples. While the phased structure is logical and tool references are specific, the content explains concepts Claude already understands and provides template prompts rather than actionable commands. The workflow would benefit from condensing to essential steps with explicit validation checkpoints and splitting detailed content into referenced files.
Suggestions
Reduce content by 60-70% by removing explanatory text about what security scanning, performance profiling, and CI/CD are - focus only on the specific commands and tool invocations needed
Add concrete executable examples showing actual tool commands (e.g., `snyk test --severity-threshold=high`) rather than descriptive prompts
Add explicit validation checkpoints after each phase with clear pass/fail criteria and error recovery steps (e.g., 'If security scan finds CVSS > 7.0: STOP and escalate before proceeding')
Split detailed phase content into separate reference files (SECURITY-REVIEW.md, PERFORMANCE-REVIEW.md, etc.) and keep SKILL.md as a concise orchestration overview
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose with extensive explanations Claude already knows (what security scanning is, what CI/CD means, etc.). The extended thinking block and detailed phase descriptions add significant token overhead without proportional value. Much of this could be condensed to essential commands and checkpoints. | 1 / 3 |
Actionability | Provides structured guidance with specific tool names (SonarQube, Snyk, GitLeaks) and subagent types, but lacks executable code examples. The prompts are templates with placeholders rather than copy-paste ready commands. No concrete code snippets showing how to actually invoke these tools. | 2 / 3 |
Workflow Clarity | Clear 4-phase sequential structure with dependencies noted between phases, but lacks explicit validation checkpoints. No feedback loops for error recovery - if Phase 2 security scan fails, there's no guidance on how to handle it. Success criteria are listed but not integrated as verification steps within the workflow. | 2 / 3 |
Progressive Disclosure | References one external file (resources/implementation-playbook.md) but the main content is a monolithic wall of text. The detailed phase descriptions, configuration options, and priority classifications could be split into separate reference files. The skill tries to be comprehensive inline rather than providing an overview with links to details. | 2 / 3 |
Total | 7 / 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 | |
- 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.