My Claude Code setup & Skills.
This repository also configures its own agents. See what dotclaude tells them →
Skill Claude CodeCodex
Writing style for markdown files. Strips filler, writes telegraphic and content-only — docs are for AI agents, not prose. Trigger whenever creating or editing ANY .md file (skills, rules, CLAUDE.md, feature specs, design notes, guides, etc.), for the new/edited content you produce. Do NOT trigger for README.md, and do…
Skill Claude CodeCodex
Merge one branch (usually the default branch) into the current branch while preserving local unstaged changes, resolving conflicts by understanding both sides, and catching silent semantic conflicts with the repo's own checks. Trigger on explicit /git-merge, or when the user asks to merge a branch or the default…
Skill Claude Code
Static landing pages — single/few-file HTML/CSS/JS for project sites, GitHub Pages, product one-pagers. Build, redesign, or review. Layers on frontend-design; not for app UIs, dashboards, or framework SPAs.
Skill Claude CodeCodex
Remove AI writing patterns from prose. Use when drafting, editing, or reviewing text to eliminate predictable AI tells.
Skill Claude Code
Build a higher-level map of an unfamiliar code area. Use when you need to understand how modules, callers, data flow, boundaries, and project concepts fit together before changing code.
Skill Claude Code
Use when the user wants to hand off, continue in a new session, or pass the current work to another agent. Compacts the conversation into a handoff document.
Skill Claude Code
Write one stuck problem into a standalone markdown brief so a fresh session in any coding agent can attack it without inheriting the dead ends. Use when the user says they want to offload a problem, take it to a new chat or another agent, or asks for a prompt/doc explaining a problem they need help with.
Skill Claude Code
Review a PR, branch, commit, or uncommitted changes for correctness bugs, structural regressions, security and performance problems. Reports findings grouped by severity with file:line and a concrete fix. Use when asked to review a PR / branch / diff / "my changes" before merge.
Skill Claude Code
Ask the user clarifying questions before acting, instead of filling gaps with guesses. Use when starting to implement a feature, fix a bug, write or change tests, refactor, or plan any change where intent, scope, expected behavior, values, or done-criteria aren't fully stated. Also use mid-task when a new unknown…
Skill Claude Code
Use when reviewing, auditing, or tightening an existing Claude Code skill. Handles SKILL.md, references, and description fixes. Not for writing new skills → anthropic-skills:skill-creator.
Skill Claude Code
Use when a CI pipeline failed on something unrelated to the code and the PR is blocked — pushes an empty commit to re-trigger CI on the current branch.
Skill Claude CodeCodex
Use when the user asks to create, enter/switch to, or remove a git worktree on Windows — makes it under .claude/worktrees/ and provisions a shared nodemodules (junction) and local .env so it runs without a reinstall. Windows + PowerShell only. Trigger on /git-worktree.
Skill Claude CodeCodex
README writing and restyling — scaffold a new README, restyle an existing one, or add/refresh its badges (shieldcn.dev or shields.io), header, admonitions, collapsibles, and GitHub markdown patterns.
Skill Claude Code
Explain a concept, feature, problem, flow, or piece of code as a visual HTML page — diagrams, charts, tables, interactive or animated sections. Claude artifact when available, otherwise a standalone HTML file.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: