See which page ranks for each query with the Search Console API.
Search Console exports separate queries from pages, hiding which URL Google shows for each term. The API joins them. Here is the fifteen-minute setup.
Codex vs Claude Code: two agents on one codebase
I run Claude Code and Codex daily, sometimes on the same repository. My session logs show the context cost, while the working tree shows the coordination cost.
What using Claude Code actually looks like
Using Claude Code is a loop: ask, change, check, decide. Here is what a normal session looks like, six commands worth learning first, and how to recover when it goes wrong.
Claude Code skills: building a workflow that runs itself
The control layer of my work system is markdown and small scripts. How a workflow combines Claude Code skills, rules, model routing, and parallel sub-agents.
Most of my AI pipeline isn't AI
By volume, most of my AI pipeline is plain Python. The model is a small, expensive part I call as little as possible. The script-first split, and why it wins.
The Claude Code plugins I built and run
I put the Claude Code tools I reuse across projects into one public toolshed: generators, workflow commands, anti-slop checks, search visibility, rule packs, and prompts.
My AI was smart. It just couldn't see my job.
My work context was scattered across email, meetings, documents, and notes. So I wired it into a private Obsidian vault Claude Code can read.
Four calendar days, one person, one full redesign
A full site redesign in four calendar days, from design system to admin stack. The real question is what product teams should do with the time AI gives back.
A safe way to edit database content with AI coding tools
AI coding tools edit files. Your content lives in a database. This is the pull, diff, push workflow that connects the two without hand-writing SQL against production.
How I built this site with Claude Code.
Three weeks, end to end: PHP backend, vanilla JS, a CSS design system I built by hand, the lot. Claude did most of the typing. The speed is the obvious story. The one worth telling is which decisions I'd still own and which I'd hand back.
Claude Code and the context window on bigger projects
My website is close to a thousand files. I keep Claude Code useful by giving each session one task, naming the files involved, and keeping the project instructions current.
Fixing bugs with Claude Code (without losing your mind)
Something broke. Describe what you expected, show what happened, let Claude investigate, then test the proposed fix.
Claude Code permissions: what to allow and what to block
Claude Code can change real files and run commands. Check the permission mode, protect secrets, review the diff, test the result, and keep a restore path.
What is vibe coding, and when should you use it?
Vibe coding is useful for disposable experiments where failure is cheap. Software you intend to keep needs review, tests, version control, and an owner.
Keeping your Claude Code project organized
Give each file an obvious home, document the stable rules, and test what your deployment actually includes.
Teaching Claude Code your standards with rule files
Use CLAUDE.md for project-wide facts and rule files for detailed standards, including rules that load only for matching paths.
Creating reusable Claude Code skills
If you keep pasting the same prompt, save it as a small Claude Code skill. You can run it with a short command and add templates or scripts later.
The CLAUDE.md file: what to put in it, and what to leave out.
Each Claude Code session starts with fresh context. CLAUDE.md loads the project facts and instructions you want available, while auto memory stores patterns Claude learns.
How to undo Claude Code changes with rewind and Git
Claude Code will sometimes make the wrong change. Inspect the diff, use rewind for recent mistakes, and keep Git for a durable restore point.
Set up Claude Code so you can review changes as they happen
Keep Claude Code and the result visible at the same time so you can review each change before asking for the next one.
How to use Claude Code subagents for parallel work
Use Claude Code subagents when a focused task can stand alone. Split independent checks, ask for one combined result, and keep dependent work with one owner.
Giving Claude Code better instructions
Give Claude Code the problem, relevant context, and the result you expect. A specific instruction reduces guessing, but you still need to review the result.
How Claude Code sees your files
The folder where you start Claude Code is its main working directory. Keep one project in scope, then add other directories only when the task needs them.
Your first conversation with Claude Code
Create a separate practice folder, then use three prompts to inspect it, create a file, and edit that file while reviewing each action.
Installing Claude Code without the old Node.js setup
Install Claude Code with Anthropic's current native installer on Windows, macOS, or Linux. No Node.js, no npm, and the fixes for when the command is not found.
Opening the terminal for the first time
You need four terminal actions to start Claude Code: open it, run a command, move to the project folder, and close it when you are done.
Meet your AI assistant that actually does things
Claude Code can inspect a project, use development tools, and apply approved changes. Your job is to decide what should happen and check the result.
/a-rules-optimizer
Rules go stale quietly: a renamed directory, a deleted helper, a CLAUDE.md nobody trimmed. This checks them against the code and fixes what drifted.
/a-self-learner
The same review finding keeps coming back because nobody wrote it down. This reads your review history and proposes the rule change that would stop it.
/a-seo-gsc
Search Console gives you thousands of rows and no priority. This reads your export and hands back a ranked list of what is actually costing you traffic, with the evidence attached.
/a-geo-optimizer
More and more people ask an assistant instead of visiting your page. This checks whether an assistant can reach yours, understand it, and find something in it worth quoting.
/a-review-optimizer
A review skill written for someone else flags what your project settled years ago. This reads your codebase and writes the review for it, or sharpens the one you already have.
/a-unslop-ui
The advice on making a site look less AI-generated produced its own AI-generated look. This flags both defaults, and prescribes neither.
/a-unslop-code
Swallowed errors, a method the library never had, a left-in "rest of your code" stub. This finds the AI tells in your source that actually break things, and puts the cosmetic ones last.
/a-unslop-text
Someone tells you a draft reads like ChatGPT and you cannot see what they saw. This names the exact words and rhythms doing it, then helps you sound like yourself rather than merely clean.
search-visibility
Search Console tells you something is wrong but not what to do. This pulls your own data and hands back a ranked fix list, plus a second skill that checks whether AI assistants can use your site.
flutter-rules
A .claude/rules pack for Flutter and Dart: null-safety and idiom standards, state management with Riverpod, and router-agnostic navigation discipline (GoRouter).
react-ts-rules
A .claude/rules pack for React and TypeScript: strict-TS standards, component and variant patterns, and server-state data-fetching discipline (React Query, forms, auth).
generic-rules
A .claude/rules baseline for any stack: security, code quality, architecture discipline, and a token-first CSS rule. The standards Claude should be holding to anyway.
php-rules
A .claude/rules pack for PHP 8.2+: strict-types and idiom standards, migration-and-query database discipline, and the security calls the generic baseline leaves to the language.
python-rules
A .claude/rules pack for Python 3.10+: type-hint and logging standards, plus a security file weighted to the subprocess, deserialization, and SSRF surfaces real pipelines hit.
dev-loop
Review, commit, ship: the end of every change, done by hand every time. dev-loop makes each one a command that works the same in any codebase.
sanitize-public
The check to run before anything goes public. sanitize-public scans a repo or bundle for the secrets, internal hostnames, and private paths that leak by accident, and catches them first.
dev-workflow-forge
Generic review tools don't know your codebase. dev-workflow-forge reads yours and writes a review skill, a rules set, and a learning loop fitted to your actual stack.
unslop
You used AI. Now it reads like AI. unslop catches the tells in your writing, code, and UI (the em dash, the generic phrasing, the stock look) so it reads like you, not a model.
role lenses
Six senior-review lenses for Claude Code that argue back instead of agreeing.
a-make-prompt
One job: turn a rough request into a finished, paste-ready prompt. Not a cure-all for prompting.