code-stats
Analyze codebase with tokei (fast line counts by language) and difft (semantic AST-aware diffs). Get quick project overview without manual counting. Triggers on: how big is codebase, count lines of code, what languages, show semantic diff, compare files, code statistics.
96
100%
Does it follow best practices?
Impact
83%
3.95xAverage score across 3 eval scenarios
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 a strong skill description that clearly identifies specific tools (tokei, difft), concrete actions (line counts, semantic diffs, project overview), and includes an explicit trigger clause with natural user phrasings. It uses proper third-person voice and is concise without being vague. The description effectively distinguishes itself from generic code analysis skills through tool-specific terminology.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: analyze codebase with tokei for line counts by language, difft for semantic AST-aware diffs, get project overview. Names specific tools and their purposes. | 3 / 3 |
Completeness | Clearly answers both 'what' (analyze codebase with tokei and difft for line counts and semantic diffs) and 'when' (explicit 'Triggers on:' clause with multiple natural trigger phrases). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would say: 'how big is codebase', 'count lines of code', 'what languages', 'show semantic diff', 'compare files', 'code statistics'. These are natural phrasings a user would actually use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive by naming specific tools (tokei, difft) and specific capabilities (line counts by language, AST-aware diffs). Unlikely to conflict with generic code analysis or diff skills due to the tool-specific focus. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
100%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-crafted skill that exemplifies good content design. It's concise, fully actionable with executable commands, well-structured with a quick reference table, and appropriately delegates advanced content to reference files. The only minor quibble is the 'When to Use' section which tells Claude things it could infer, but it's brief enough to not meaningfully impact quality.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient. No unnecessary explanations of what tokei or difft are conceptually—it jumps straight to executable commands. The comparison table for semantic diffs is compact and informative. The 'When to Use' section is borderline unnecessary but brief enough not to be a real issue. | 3 / 3 |
Actionability | Every section provides concrete, copy-paste ready commands with real flags and options. The sample output helps Claude understand expected results. The quick reference table is immediately usable. | 3 / 3 |
Workflow Clarity | This is a simple, non-destructive skill (read-only analysis tools) so no validation checkpoints are needed. The commands are clearly organized by tool and purpose, and the progression from basic to advanced usage is logical. | 3 / 3 |
Progressive Disclosure | The main file provides a concise overview with all essential commands, then clearly points to one-level-deep references for advanced patterns (tokei-advanced.md and difft-advanced.md). Navigation is well-signaled. | 3 / 3 |
Total | 12 / 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
- NeverSight/skills_feed
- Commit
f772de4
- 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.