vibe-check
Judgment linter for vibe-coded output — reads the energy of the code, not just correctness. Use when the user says "vibe check", "check this vibe code", "does this hold up", "sanity check this AI code", or after a fast generation session before committing.
90
Quality
87%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
89%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 a strong skill description with excellent trigger terms and clear when/what guidance. The main weakness is the somewhat abstract 'reads the energy' phrasing which could be more concrete about what specific checks or evaluations are performed. The distinctive focus on vibe-coded/AI-generated output creates a clear niche.
Suggestions
Replace 'reads the energy of the code' with more concrete actions like 'checks for common AI code pitfalls, reviews structure coherence, validates naming consistency'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain ('vibe-coded output', 'code') and describes the action ('reads the energy of the code'), but 'reads the energy' is somewhat abstract. It mentions what it checks against ('not just correctness') but doesn't list concrete specific actions like 'checks for code smells, reviews structure, validates patterns'. | 2 / 3 |
Completeness | Clearly answers both what ('Judgment linter for vibe-coded output — reads the energy of the code, not just correctness') and when ('Use when the user says...' with explicit trigger phrases and situational context 'after a fast generation session before committing'). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would actually say: 'vibe check', 'check this vibe code', 'does this hold up', 'sanity check this AI code', 'before committing'. These are realistic phrases users would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Very distinct niche targeting AI-generated/vibe-coded output specifically, with unique trigger terms like 'vibe check' and 'vibe code' that wouldn't overlap with standard code review or linting skills. The 'energy' framing further distinguishes it. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured skill with excellent actionability and workflow clarity. The assertion categories table with specific examples and the language-aware judgment section provide concrete guidance. Minor verbosity in the overview and some philosophical framing could be trimmed to improve token efficiency.
Suggestions
Trim the overview section - remove the philosophical framing ('what's the energy like right now?') and the comparison to static linters/code review, as Claude understands these concepts
Consider condensing the 'The vibe' column in the assertion categories table into the 'What it catches' column to reduce redundancy
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient but includes some unnecessary philosophical framing ('what's the energy like right now?') and explanatory text that could be trimmed. The overview section explains the concept more than necessary for Claude. | 2 / 3 |
Actionability | Provides concrete assertion categories with specific examples, clear output format with file:line references, and explicit workflow steps. The language-specific footguns list and example findings are copy-paste ready patterns. | 3 / 3 |
Workflow Clarity | Clear 5-step workflow with explicit sequence (Gather → Read → Report → Summarize → Escalate). Includes escalation criteria (8+ findings or 4+ categories) and clear output format expectations at each step. | 3 / 3 |
Progressive Disclosure | Well-organized with clear sections, appropriate use of tables for categories and severity levels, and a 'See Also' section pointing to related skills. Content is appropriately scoped for a single skill file. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- tslateman/duet
- Commit
96a72fa
- 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.