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.

3.95x

Quality

—

Does it follow best practices?

Impact

83%

3.95x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Quality

Content

92%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-organized, highly actionable body with lean executable commands and clear navigation. The main weakness is progressive disclosure: the skill advertises advanced reference files that are not present in the bundle.

Suggestions

Create the referenced ./references/tokei-advanced.md and ./references/difft-advanced.md files (filtering, output formats, display modes, git integration) so the progressive-disclosure pointers resolve, or remove the pointers and inline only what is essential.

The 'Sample Output' block adds tokens Claude does not strictly need since tokei's output is self-evident when run; consider trimming it to tighten conciseness further.

If reference files are added, keep them strictly one level deep and ensure each covers a single clearly-titled topic to preserve the clean navigation already established.

Dimension	Reasoning	Score
Conciseness	The body is lean and command-focused — executable snippets, a compact quick-reference table, and a brief 'Why Semantic?' comparison; it assumes Claude's competence without padding concepts Claude already knows.	3 / 3
Actionability	Provides fully executable, copy-paste-ready commands for both tools (e.g. 'tokei --output json \| jq ".Total.code"', 'GIT_EXTERNAL_DIFF=difft git diff') plus a task-to-command reference table, matching the score-3 anchor.	3 / 3
Workflow Clarity	This is a simple single-purpose skill with unambiguous per-tool actions and a clear 'When to Use' guide; per the simple-skills note, that clarity earns a 3 without needing a multi-step validation workflow, and no destructive/batch operations require feedback loops.	3 / 3
Progressive Disclosure	The 'Additional Resources' section cleanly signals one-level-deep references, but the referenced files ('./references/tokei-advanced.md', './references/difft-advanced.md') do not exist in the bundle, so the disclosure structure is promised but not delivered.	2 / 3
	Total	11 / 12 Passed

Description

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.

A strong, concise description that names concrete capabilities, specific tools, and an explicit trigger clause covering natural user phrasings. Voice is appropriately third-person and it carves a clear niche with low conflict risk.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'fast line counts by language', 'semantic AST-aware diffs', and 'quick project overview without manual counting' — naming specific tools and what each does, matching the score-3 anchor.	3 / 3
Completeness	Clearly answers 'what' (analyze codebase with tokei/difft for line counts and semantic diffs) and 'when' via the explicit 'Triggers on:' clause, satisfying the score-3 anchor for both what AND when.	3 / 3
Trigger Term Quality	The 'Triggers on:' list gives natural phrases users would say — 'how big is codebase', 'count lines of code', 'what languages', 'show semantic diff', 'compare files', 'code statistics' — with good coverage of common variations.	3 / 3
Distinctiveness Conflict Risk	The tokei/difft tooling and AST-aware-diff niche are distinct from general code skills; the trigger list is specific to line counting and semantic diffing, making wrong-skill activation unlikely.	3 / 3
	Total	12 / 12 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: NeverSight/skills_feed
Commit: 26d37ce

Reviewed: about 20 hours ago

Table of Contents

Discovery Implementation Validation

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.