fuck-u-code-analysis

Use when code changes are complete and ready for quality review, before committing or creating PRs. Triggers after implementing features, fixing bugs, or refactoring code. Also use when user asks to check code quality, analyze technical debt, review code smell, or mentions "fuck-u-code", "code quality", "shit mountain", "code review", "static analysis". Covers all 14 supported languages (Go, JS, TS, Python, Java, C, C++, Rust, C#, Lua, PHP, Ruby, Swift, Shell).

Quality

84%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

68%Weight 40%Scale 1-5

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

The body is highly actionable and well-structured, but it over-explains concepts Claude already knows and lacks an explicit validation checkpoint for its batch analysis workflow. Tightening redundant explanations and adding a verify/re-run step would lift the weakest dimensions.

Suggestions

Trim restatements of well-known concepts (e.g. definitions of cyclomatic/cognitive complexity) and move the 14-language naming-convention table to references/naming.md, keeping only a pointer inline.

Add a verification step to the workflow, e.g. 'Re-run fuck-u-code analyze after applying fixes and confirm the targeted file score rose above 60' before finalizing the report.

Consider extracting the 11-metric reference into references/metrics.md with a concise summary + thresholds table inline in SKILL.md to reduce inlined bulk.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and earned detail (commands, thresholds, templates), but re-explains concepts Claude already knows (e.g. 'Measures the number of independent execution paths', 'Measures how difficult code is to understand') and inlines a 14-language naming-convention table that is common knowledge, so it is not lean.	3 / 5
Actionability	Fully executable guidance throughout: copy-paste analyze commands with flags, concrete per-metric threshold tables, and specific remediation templates anchored to line numbers and function names covering the common cases.	5 / 5
Workflow Clarity	A clear 4-step sequence with a diagram exists, but this batch analysis operation has no explicit validation/verification checkpoint (e.g. confirm report locations reference real entries, or re-run after fixes to confirm improvement), and the scoring_notes batch cap holds workflow_clarity at 3.	3 / 5
Progressive Disclosure	Good structure with a real one-level-deep reference (references/thresholds.md, verified present) that correctly keeps the per-language threshold table out of SKILL.md, though the inlined 11-metric reference and naming-convention table could arguably live in separate files.	4 / 5
	Total	15 / 20 Passed

Description

100%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is strong: it states concrete capabilities, an explicit 'Use when' trigger with multiple natural phrasings and synonyms, a clear tool-specific niche, and a bounded language scope. It cleanly matches the top anchor on all four dimensions.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete capabilities ('check code quality, analyze technical debt, review code smell, ... static analysis') plus an enumerated set of 14 supported languages, giving comprehensive coverage of concrete actions rather than vague language.	5 / 5
Completeness	Explicitly answers both 'what' (quality review, technical-debt analysis, code-smell review, static analysis across 14 languages) and 'when' with concrete trigger clauses ('Use when code changes are complete...', 'Triggers after implementing features, fixing bugs, or refactoring code', 'Also use when user asks...').	5 / 5
Trigger Term Quality	Comprehensive natural trigger terms including common user phrases ('code quality', 'code review', 'static analysis', 'analyze technical debt', 'review code smell') plus distinctive synonyms ('shit mountain') and the tool name 'fuck-u-code'.	5 / 5
Distinctiveness Conflict Risk	The tool-specific trigger surface ('fuck-u-code', 'shit mountain') carves a clear niche that is unlikely to fire for unrelated review skills, and the explicit 14-language scope bounds it against generic linter skills.	5 / 5
	Total	20 / 20 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: Done-0/fuck-u-code
Path: skills/fuck-u-code-analysis/SKILL.md
Commit: 420c6e8

Reviewed: 20 days 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.