skill-init (AI Career Skill Inventory Onboarding)
A 5-minute onboarding skill that profiles your transferable skills, assigns a starting tier (S0–S3), and saves it to .skill-state.json for later job-scan and study-plan steps.
EducationBeginner★ 170⑂ 13AI score 9/10Last updated: Jun 27, 2026
What it does
- Fires as the entry point whenever someone says they want to find or plan an AI-era job and no
.skill-state.jsonexists yet. - Opens with expectation setting and an anti-scam pledge (no course-funnel "Top 10 AI jobs" lists, hard rejection of training loans, guaranteed-placement and paid-referral offers).
- Asks 7 questions in one pass: current skills/role, how related the target direction is, education and years of experience, weekly study hours and months of stamina, self-learning ability, location and target salary, urgency of the switch. "Not sure" is allowed and stored as null.
- Extracts transferable skills, then classifies you into S0/S1/S2/S3 using the bundled role-tiers reference, explains the reasoning, and rounds down when uncertain.
- Writes
.skill-state.jsonfrom a template, reading local time and IANA timezone from your machine instead of hardcoding a city. - Ends with a next-step menu:
skill-scanfor real job listings,skill-planfor a learning roadmap.
Who it's for
- Career switchers who want an AI-adjacent role but don't know where to start.
- People who prefer a personalized readiness assessment over generic high-salary job lists.
- Users of the cheat-on-skill suite who want the full inventory → scan → plan pipeline.
Examples
- Say "I want a high-paying AI-era job" → 7 questions, an S1 verdict with rationale, and a fresh
.skill-state.json. - A backend developer answers that they already code → tiered as S2, with programming logged as the transferable base for scan-time gap analysis.
- Run it again when the state file exists → it offers to update your profile or routes straight to
skill-scan.
· · · Install guide · · ·
Try it now, no install
Paste this into Claude to use the skill without installing anything.
Read the instructions in this file and follow them to help me: https://raw.githubusercontent.com/XBuilderLAB/cheat-on-skill/HEAD/skills/skill-init/SKILL.md What I want: (describe your task here)
If Claude can't open the link, open it yourself and paste the contents instead.
↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.
Install in the Claude app (no terminal)
- Download the ZIP with the button below.
- In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
- Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
Install in Claude Code
Let Claude do it — paste this into Claude Code
Install the skill I found on Claude Skill Mart. Copy the skills/skill-init folder from the GitHub repo XBuilderLAB/cheat-on-skill into my ~/.claude/skills/skill-init/. When it's done, tell me in one line what this skill can do.
Install with a command instead
git clone https://github.com/XBuilderLAB/cheat-on-skill.git && mkdir -p ~/.claude/skills && cp -r cheat-on-skill/skills/* ~/.claude/skills/⚠ This is a third-party skill. Check the source repository before installing.
- Open a terminal.
- Clone the repo:
git clone https://github.com/XBuilderLAB/cheat-on-skill.git - Create the skills directory:
mkdir -p ~/.claude/skills - Copy the skills over (copy all of them so skill-scan and skill-plan are available too):
cp -r cheat-on-skill/skills/* ~/.claude/skills/ - Make sure the repo's
shared-references/andtemplates/folders keep their relative layout — this skill loadsrole-tiers.mdandskill-state.template.jsonby relative path. - Restart Claude Code, cd into the working folder you want the profile stored in, and type "skill init" or "help me inventory my skills".
- Answer the 7 questions;
.skill-state.jsonappears in that folder. It holds personal data, so add it to.gitignore.
Note: salary and demand signals downstream come from Chinese hiring data (BOSS Zhipin); adjust expectations for your own market.
View source on GitHub ↗License: MIT