code-standards
Enforces project-specific coding conventions by loading language standards before writing code. Use when about to write, edit, modify, or generate Go, Rust, Python, or Tailwind CSS files. Loads once per language per session and overrides default style with project conventions. DO NOT TRIGGER for languages other than Go, Rust, Python, or Tailwind CSS.
89
86%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
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 an excellent skill description that clearly communicates what it does (enforces project coding conventions by loading language standards), when to use it (writing/editing Go, Rust, Python, or Tailwind CSS files), and when NOT to use it (other languages). The explicit negative trigger boundary is a strong differentiator that reduces conflict risk. The description is concise, uses third person voice, and includes natural trigger terms.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple concrete actions: 'loading language standards before writing code', 'overrides default style with project conventions', 'loads once per language per session'. Specifies exact languages supported (Go, Rust, Python, Tailwind CSS). | 3 / 3 |
Completeness | Clearly answers both 'what' (enforces project-specific coding conventions by loading language standards) and 'when' (explicit 'Use when about to write, edit, modify, or generate Go, Rust, Python, or Tailwind CSS files'). Also includes negative scoping. | 3 / 3 |
Trigger Term Quality | Includes natural trigger terms users and Claude would encounter: 'write', 'edit', 'modify', 'generate', and specific language names 'Go', 'Rust', 'Python', 'Tailwind CSS'. Also includes a negative trigger boundary ('DO NOT TRIGGER for languages other than...'). | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche: project-specific coding conventions for exactly four named languages. The explicit negative boundary ('DO NOT TRIGGER for languages other than...') further reduces conflict risk with other coding skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
72%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, concise skill that clearly defines its scope and uses a clean lookup table for language detection. Its main weaknesses are the lack of a concrete example of the Read tool invocation and the absence of error handling for cases where standards files might not exist. The workflow is implicit rather than explicitly sequenced.
Suggestions
Add a concrete example of the Read tool invocation (e.g., `Read file: ../../code-standards/go/CLAUDE.md`) to make the loading step fully actionable.
Add a brief error handling note for when a standards file is missing or unreadable (e.g., 'If the standards file does not exist, proceed with default conventions and note the missing file').
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is lean and efficient. Every section serves a clear purpose—language detection table, loading instruction, and application rule. No unnecessary explanations of what coding standards are or how Claude works. | 3 / 3 |
Actionability | The skill provides a clear lookup table and specifies using the Read tool, but lacks a concrete example of the invocation (e.g., an actual Read tool call). The 'Applying Standards' section is vague—'follow these standards' without showing how to reconcile conflicts with defaults or what 'override' looks like in practice. | 2 / 3 |
Workflow Clarity | The sequence is implicit (detect → load → apply) but not explicitly numbered or structured as a workflow. There's no validation step—e.g., confirming the file was successfully read or handling the case where the standards file doesn't exist. For a simple skill this is mostly adequate but the missing error handling for file reads keeps it at 2. | 2 / 3 |
Progressive Disclosure | The skill is appropriately structured as a concise overview that points to external standards files (one level deep). The table clearly signals where detailed content lives, and the skill itself stays short and navigable. | 3 / 3 |
Total | 10 / 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
- shousper/claude-kit
- Commit
a01bac9
- 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.