By oalders
A collection of useful Claude Code skills and commands for software development workflows
Fixes immediate PR feedback, defers remaining items as issues
Audit CLAUDE.md files for token efficiency, clarity, and accuracy against actual codebase
Splits big issues into reviewable chunks with tracking issue
Heavy code review - fans out to all applicable specialized reviewers (security, frontend, seo, geo, playwright) based on diff content
Codebase health check for AI optimization - token efficiency, discoverability, and code quality
Use when the user asks for an "adversarial review", "review this adversarially", or wants two reviewers competing to find serious issues in code or other work. Enforces scope discipline so findings count doesn't inflate across rounds.
Streamlined code review workflow - gets SHAs and invokes a general-purpose code reviewer without permission prompts
Use when the user asks to "implement the design handoff", "build this design", "apply the design handoff", or otherwise wire a design-system / component-export spec (often a set of `*.card.html` cards plus component source) into an app's real templates and CSS. Also use when the user asks to write a GitHub issue that points an implementing agent at a design to build later.
Triages plan complexity to avoid heavyweight execution for trivial changes
Use when reviewing or improving Perl code against project standards — reads changed .pm/.pl/.t files (or named paths) and flags violations of the rules in STANDARDS.md (quoting, core-module use, URL building, test hygiene, and more).
Based on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Everything but the kitchen sink

A grab bag of skills to automate the boring parts out of your hair and into your robot.
GitHub CLI: Several skills and commands use gh to interact with GitHub issues and pull requests. Install it and authenticate with gh auth login.
Superpowers plugin: Most skills and commands rely on obra/superpowers for workflows like brainstorming, verification, and subagent-driven development. Install it first:
claude plugin marketplace add obra/superpowers
Add from the Claude Code plugin marketplace:
claude plugin marketplace add oalders/kitchen-sink &&
claude plugin install kitchen-sink
| Command | Description |
|---|---|
| /fix-gh-issue | Point your robot at a GitHub issue and let it start beeping and booping |
| /fix-linter-warnings | Linter busywork in bite-sized chunks—your robot's idea of a good time, not yours |
| /git-rebase | Rebase without the cruel and unusual punishment of solving your own merge conflicts |
| /break-into-gh-issues | Maybe split big issues into smaller ones—so you get a code review and not an intervention |
| /address-gh-review | A robot that does the urgent repairs now and books appointments for the rest |
| /request-review | Get code review feedback without permission prompts stalling the workflow |
| /frontend-review | Frontend expert review catching accessibility gaps, responsive design issues, and CSS anti-patterns |
| /playwright-review | Playwright test review enforcing ARIA labels, detecting UI layout issues, and optimizing performance |
| /security-review | OWASP-based security review catching session fixation, PII logging, and timing attacks |
| /codebase-health | Systematic health check optimizing codebase for AI consumption—dead code, token waste, and discoverability |
| /audit-claude-md | Audit CLAUDE.md files for token efficiency, clarity, and accuracy against actual codebase |
| Skill | Description |
|---|---|
| code-review-flow | Streamlined code review workflow that avoids permission prompts |
| implement-design-handoff | Wires a design-system / component-export handoff into an app's real templates and CSS faithfully, forcing a property-by-property visual-parity check and protecting untouched surfaces |
| over-engineer-no-more | Prevents your robot from building a spaceship when you asked for a bicycle |
| perl-review | Flags Perl code that strays from your project standards — quoting, core-module use, URL building, test hygiene — reading a living rules doc you edit freely |
| tune-dependabot-config | Groups minor/patch Dependabot updates per ecosystem and adds a 7-day cooldown |
| tune-perl-ci | Six idempotent transforms to modernize Dist::Zilla-style Perl GitHub Actions CI |
| tune-precious | Migrates a Perl repo from Code::TidyAll to precious (or sets up precious from scratch) — config, .perltidyrc, dist.ini, CI lint job |
| working-with-dist-zilla | Stops your robot from committing 100 lines of regenerated META.json and other dzil faceplants |
| Hook | Description |
|---|---|
| suggest-review-after-commit | Smart PostToolUse hook that analyzes committed files and suggests relevant review commands (/frontend-review, /playwright-review, /security-review, or /request-review) based on file types and patterns |
Automates the workflow for fixing GitHub issues:
fix-978 -> 978)gh and applies "in progress" label/frontend-review/security-review/playwright-review/request-reviewverification-before-completionBatch approach to linter cleanup:
Rebases the current branch onto origin/main:
--rebase--force-with-lease for safe pushing (never --force)npx claudepluginhub oalders/kitchen-sink --plugin kitchen-sinkAudit content for shareability using Anil Dash's framework - ensure others can authentically talk about your work without you present
Analyzes and fixes GitHub issues using a structured approach with GitHub CLI for issue details, implementing necessary code changes, running tests, and creating proper commit messages.
This is a getty104's base tool set
Multi-language iterative PR review + autofix loop (built-in iteration engine + pr-review-toolkit + optional Codex)
Process and fix code review issues with risk assessment - decides FIX vs TECH_DEBT based on impact
Fix PR review comments automatically with context-aware patches
Code review and worktree workflow commands