Help us improve
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
By ckorhonen
8 Claude Code skills that run on a cadence to fight code entropy — method brevity, naming clarity, duplication detection, broken windows. See cdd.dev/skills/hone.
npx claudepluginhub ckorhonen/hone-skillsFinds manual processes that could be automated: manual deploy steps in READMEs, setup instructions that could be scripts, repetitive git workflows, manual testing procedures, and undocumented tribal knowledge. Also checks for artifacts not in source control. Use monthly to surface automation ROI. Do NOT use for code quality or style audits.
Detects entropy signals in a codebase: stale TODOs, disabled tests, lint suppressions, commented-out code, dead imports, empty catch blocks, and deprecated API usage. Designed for daily runs to catch quality erosion early. Do NOT use for feature work, refactoring planning, or security audits.
Finds duplicated code patterns across the codebase including exact copies and structural duplication (same logic with different variable names). Ranks by frequency and suggests extraction candidates. Designed for weekly runs. Do NOT use for method length, naming, or style concerns.
Finds code that obscures its intent: unclear variable names, nested ternaries, boolean parameters without names, overly clever one-liners, and comments that restate code instead of explaining why. Focuses on recently changed files. Do NOT use for method length, duplication, or test naming concerns.
Surfaces magic numbers, unexplained string literals, hardcoded URLs, configuration values buried in code, and other "magical" values that should be named constants or config entries. Use when you want a weekly sweep for unnamed literals. Do NOT use for style or formatting audits.
Share bugs, ideas, or general feedback.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Develop, test, build, and deploy Godot 4.x games with Claude Code. Includes GdUnit4 testing, web/desktop exports, CI/CD pipelines, and deployment to Vercel/GitHub Pages/itch.io.
Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review
Comprehensive PR review agents specializing in comments, tests, error handling, type design, code quality, and code simplification
Design fluency for frontend development. 1 skill with 23 commands (/impeccable polish, /impeccable audit, /impeccable critique, etc.) and curated anti-pattern detection.
UI/UX design intelligence. 67 styles, 161 palettes, 57 font pairings, 25 charts, 15 stacks (React, Next.js, Vue, Svelte, Astro, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui, Nuxt, Jetpack Compose). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, flat design. Topics: color palette, accessibility, animation, layout, typography, font pairing, spacing, hover, shadow, gradient.
A broad collection of 45+ Claude Code skills spanning development, design, marketing, AI, security, and infrastructure. See cdd.dev/skills.
17 agent skills for engineering analysis and judgment — PR risk review, repo introspection, audits, ownership maps, refactor opportunities. See https://cdd.dev/skill/.
Sharpen the things that dull.
8 AI skills that enforce timeless software engineering practices — the kind that outlast every framework, language, and tool. Derived from 25 proven practices that emphasize code clarity, disciplined process, and proactive maintenance.
These skills are designed to run on a schedule (daily, weekly, monthly, or per-PR), turning your AI coding assistant into a persistent quality guardian.
npx skills add ckorhonen/hone-skills
Works with Claude Code, Cursor, Codex, Gemini CLI, GitHub Copilot, and any agent that supports the Agent Skills standard.
| Skill | What it does | Schedule |
|---|---|---|
hone:method-brevity-audit | Finds methods that have grown too long | Weekly |
hone:intent-clarity-audit | Spots code that hides its intent | Weekly |
hone:test-naming-audit | Checks test names read as sentences | Every PR |
hone:duplication-hunt | Finds duplicated patterns worth extracting | Weekly |
hone:magic-number-hunt | Surfaces magic numbers and unexplained literals | Weekly |
hone:naming-specificity-audit | Flags vague names like Manager, Handler, Utils | Weekly |
hone:broken-windows-hunt | Detects entropy: TODOs, dead code, lint ignores | Daily |
hone:automation-opportunities | Finds manual processes ripe for automation | Monthly |
"Practices change much slower than tools and are typically a better investment."
These skills codify engineering judgment that has survived decades of framework churn. Each one runs a bounded, evidence-led audit against your actual codebase — no generic advice, only concrete findings with file paths and line numbers.
Hone is what runs in the background. It's quiet guardianship rather than expert advice — noticing what a careful practitioner would have noticed if they had the time, on a cadence you choose.
Published alongside this pack at cdd.dev/skills:
swe:
skills for on-demand engineering work: PR risk review, repo introspection,
audits, incident follow-up, ownership maps. Invoked in conversation when you
need them.bun install
bun run evals:check # validate all skills + eval suites
bun run lint:md # check markdown
bun run lint:md:fix # auto-fix markdown
skills/<slug>/SKILL.md — skill definition
evals/<slug>/README.md — what the eval covers
evals/<slug>/rubric.md — pass/fail conditions
evals/<slug>/cases.json — test scenarios
evals/shared/criteria.json — shared review criteria
scripts/validate-evals.mjs — structural validation
site/ — landing page source