Onboarding
First-run user onboarding. Asks 6 quick questions, detects the project, writes USER_PROFILE.json, and recommends the right setup tier. Auto-activates on first use or when the user says 'set me up', 'I'm new', or runs /onboard.
Install
$ agentstack add skill-shivae372-claude-bootstrap-onboarding ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Links to your public security report.[](https://agentstack.voostack.com/security/report/skill-shivae372-claude-bootstrap-onboarding) Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Purpose
Collect just enough about the person and their project to tailor the Claude Code setup, then write USER_PROFILE.json and route to the right tier (developer / hybrid / non-dev).
When To Use This
- The user runs
/onboard, says they're new, or asks to be set up - No
USER_PROFILE.jsonexists yet and the user wants/bootstrap
Steps
1. Greet briefly
> "I'll ask 6 quick questions so Claude Code fits how YOU work — about 2 minutes, once."
2. Ask the 6 questions ONE AT A TIME (wait for each answer)
- Role — developer, founder, designer, PM, data, student, other?
- Comfort with code/terminal (1–5) — 1 = avoid the terminal … 5 = senior engineer.
- Team — solo / small (2–5) / larger?
- Domain — software / design / ops / marketing / research / other?
- Top 1–3 goals — e.g. "ship faster", "automate reports", "learn to code".
- Success in 30 days — one sentence.
3. Detect the project (no interaction)
python3 .claude/skills/onboarding/scripts/detect-project.py --target . --output /tmp/detected.jsonIf it fails, treat detection as {"has_project": false}.
4. Write the profile
echo '' | python3 .claude/skills/onboarding/scripts/write-profile.py \
--detected /tmp/detected.json --output USER_PROFILE.json` keys: roletype, techlevel (int 1–5), teamsize (solo|small|large), domain, primarygoals (array), successin30_days`.
5. Recommend the tier
Read generation_tier from USER_PROFILE.json and tell the user which tier fits, then point them to /bootstrap (or to bash install.sh --tier if they prefer the deterministic path).
Output
Writes USER_PROFILE.json and prints a short summary (role, tech level, tier, detected stack).
Notes
- If a profile already exists, ask whether to update or keep it — never silently overwrite.
- If an answer is ambiguous, ask one quick follow-up rather than guessing.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: shivae372
- Source: shivae372/claude-bootstrap
- License: Apache-2.0
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.