skills/create-profile/SKILL.md
Creates or updates a personal developer profile at ~/.claude/PROFILE.md. Run this once to tell Claude about your role, experience, and preferences so that explanations and other skills can tailor their output to you.
npx skillsauth add rolemodel/rolemodel-skills create-profileInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
This skill interviews the user and writes ~/.claude/PROFILE.md. Other skills read this file to tailor their output without re-asking these questions.
If ~/.claude/PROFILE.md already exists, read it first so you can show current values and let the user update rather than start fresh.
Ask these questions one at a time using AskUserQuestion, waiting for each answer before continuing. Tailor follow-up questions based on what you learn — the goal is a profile that feels like it was written by the person, not a form they filled out.
Header: "What's your role?"
Options (allow free-form "Other"):
Header: "What frameworks and languages are you most familiar with? And how long have you been using them?"
DO NOT USE AskUserQuestion options for this — let them answer in their own words.
Header: "Which of these domains are you most familiar with?"
DO NOT USE AskUserQuestion options for this — let them answer in their own words.
Header: "What tools and editors do you use day-to-day?"
DO NOT USE AskUserQuestion options for this — let them answer in their own words. (e.g. VS Code, Neovim, GitHub, Linear, Figma, etc.)
Header: "How do you prefer explanations?"
Options (allow free-form, allow multi-select):
Ask as plain text: "Anything else you'd like me to know? For example: areas you're focused on, things you find confusing, topics you want me to go deeper on, or anything I should avoid."
Wait for the response. If the user says "no" or "nothing", that's fine — skip it in the profile.
After collecting answers, write ~/.claude/PROFILE.md with this structure (adapt the content to what the user actually said — do not copy options verbatim if their free-form answer is more expressive):
# Developer Profile
## Role
<their role, in their words or the selected option>
## Primary Stack
<their experience level and any context they gave>
## Domain Experience
<domains they selected or described, as a short prose sentence or bullet list>
## Tools
<their day-to-day tools, as they described them>
## Working Style
<their stated preferences — rewrite as natural prose if they gave multiple options>
## Additional Preferences
<their open-ended answer, or omit this section entirely if they had nothing to add>
After writing the file, confirm to the user: "Your profile has been saved. Skills like /explain will now use it to tailor output to you. You can run /create-profile again any time to update it."
testing
Verify what Ruby versions actually exist and install a specific Ruby via rbenv. Use BEFORE asserting that any Ruby version does or doesn't exist (e.g., "Ruby 4.0 isn't out yet", "the latest Ruby is 3.x", "Ruby X.Y.Z doesn't exist"). Also use when the user asks "what's the latest Ruby", "is Ruby X out", "does Ruby X.Y exist", "install Ruby", "switch to Ruby X", "what Ruby is installed", or mentions a specific Ruby version you're unsure about. Claude's training data may be out of date — run `check.sh` first.
development
Trace code through the stack — upward to entry points, downward to data, or laterally across boundaries. Use when the user asks "where does this get called from", "what calls this method", "trace this through the stack", "how does this request flow", "where does this data come from", "follow this through the code", or pastes/selects a piece of code and wants to understand where it fits in the larger system.
tools
Pick the single highest-priority unresolved Sentry issue and hand it off to a fixer skill. Use when triaging Sentry errors, running automated issue triage, or when asked to fix the top Sentry issue in a project.
tools
Find and fix issues from Sentry using MCP. Use when asked to fix Sentry errors, debug production issues, investigate exceptions, or resolve bugs reported in Sentry. Methodically analyzes stack traces, breadcrumbs, traces, and context to identify root causes.