lisp-validator
Validate Lisp code (Clojure, Racket, Scheme, Common Lisp) for syntax errors, parenthesis balance, and semantic issues. This skill should be used when validating Lisp code files, checking for syntax errors before execution, or validating LLM-generated Lisp code including incomplete or partial expressions. Provides structured JSON output optimized for automated workflows.
67
81%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Quality
Discovery
100%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 that clearly defines its scope (Lisp code validation across multiple dialects), lists specific capabilities (syntax errors, parenthesis balance, semantic issues), and provides explicit trigger guidance with a 'should be used when' clause. The inclusion of specific Lisp dialects and mention of LLM-generated code validation adds useful distinctiveness and trigger coverage.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: validate for syntax errors, parenthesis balance, and semantic issues. Also specifies structured JSON output and mentions multiple Lisp dialects (Clojure, Racket, Scheme, Common Lisp). | 3 / 3 |
Completeness | Clearly answers both 'what' (validate Lisp code for syntax errors, parenthesis balance, semantic issues with JSON output) and 'when' (explicit 'should be used when' clause covering validating Lisp files, checking syntax before execution, validating LLM-generated code). | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'Lisp code', 'Clojure', 'Racket', 'Scheme', 'Common Lisp', 'syntax errors', 'parenthesis balance', 'validate', 'LLM-generated Lisp code'. Good coverage of dialect names and validation-related terms. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche targeting Lisp-family languages specifically for validation/syntax checking. Unlikely to conflict with general code linting or other language-specific skills due to the explicit Lisp dialect enumeration and validation focus. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
62%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill is highly actionable with excellent executable examples, clear workflow sequencing, and good decision-tree routing across Lisp dialects. However, it is severely bloated with extensive redundancy — the same commands and concepts appear in 3-4 different sections, and content that should live in referenced files (dialect details, troubleshooting, CI examples) is duplicated inline. Trimming redundancy and moving detailed content to the referenced files would dramatically improve this skill.
Suggestions
Eliminate redundancy by consolidating repeated content: Quick Start, Quick Reference, Examples, Dialect-Specific, and Using Validation Scripts sections all repeat the same commands. Keep one authoritative location for each command.
Move dialect-specific validation details, troubleshooting, and CI/CD examples into the referenced files (tool_comparison.md, error_patterns.md, integration_strategies.md) rather than inlining them in SKILL.md.
Remove explanations of concepts Claude already knows, such as what exit codes are, how to use jq, what JSON parsing means, and how grep/wc work.
Cut the skill to under 150 lines by keeping only the decision tree, quick reference table, one representative example, and pointers to reference docs for everything else.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at 500+ lines with massive redundancy. The same commands and concepts are repeated across Quick Start, Quick Reference, Examples, Dialect-Specific Validation, Validation Workflows, and Using Validation Scripts sections. Installation guidance, exit codes, and tool checking are each explained multiple times. Much content explains things Claude already knows (what exit codes mean, how to use jq, what JSON is). | 1 / 3 |
Actionability | The skill provides fully executable commands throughout, with concrete bash commands, Python scripts, CI/CD YAML configurations, and specific tool invocations. Output examples with JSON schemas are provided, and commands are copy-paste ready with clear flags and options. | 3 / 3 |
Workflow Clarity | The progressive validation workflow is clearly sequenced (tree-sitter → comprehensive → auto-format) with explicit validation checkpoints. The decision tree at the top clearly routes to appropriate tools. Exit codes provide clear pass/fail signals, and error recovery paths are documented (e.g., fix and re-validate loops, cross-referencing tools for false positives). | 3 / 3 |
Progressive Disclosure | The skill references three detailed reference documents (tool_comparison.md, error_patterns.md, integration_strategies.md) with clear descriptions of when to load them. However, no bundle files are provided to verify these exist, and the SKILL.md itself is monolithic — much of the dialect-specific detail, troubleshooting, and examples should be in those reference files rather than inline, creating a wall of text. | 2 / 3 |
Total | 9 / 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 |
|---|---|---|
skill_md_line_count | SKILL.md is long (830 lines); consider splitting into references/ and linking | Warning |
Total | 10 / 11 Passed | |
- Repository
- waddie/lisp-validator-skill
- Commit
7d2d2f2
- 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.