user-onboarding
Skill1 starsChanged 11 days agoMITView on GitHub
Capture user preferences once, persist across projects. Creates a user profile for personalization across skills. Triggers: first session, setup preferences. Do NOT use for project-specific config.
We split this skill into the rules it gives an agent
4 rules. 0 are common, 3 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 6 edited versions we read keep these.
3
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 71
Ask once. Store permanently.
- Distinctive: line 72
Never include secrets, API keys, or sensitive data.
- Very specific: line 73
Update updated_at on any change.
- Distinctive: line 192
Before any skill runs discovery:
“Common” is measured: kept by at least 6 in 10 of the 6 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
User Onboarding
Ask once. Remember forever.
Captures user preferences, constraints, context. Eliminates repetitive discovery. Subsequent projects read user-profile.json and adapt defaults, suggestions, questions.
When to Use
AUTO-DETECTED — User never needs to ask.
Runs automatically when:
- Any skill starts and no
~/.config/opencode/user-profile.json user-profile.json> 90 days old- User says "setup preferences", "remember stack", "configure defaults"
When NOT to Use
- Profile exists and < 90 days old (Quick Verify instead)
- User says "skip" and profile exists
- Turbo Mode active with existing profile
Output Contract
| Artifact | Format | Location | Quality Criteria |
| User profile | JSON file with 7 sections (identity, preferences, design, workflow, constraints, session defaults) | ~/.config/opencode/user-profile.json | Profile saved after full onboarding (27 questions across 7 sections), versioned schema with created_at/updated_at, no secrets or API keys stored, profile <90 days old or update offered, Quick Verify on subsequent sessions |
How it works:
User: "Crea una landing page"
Agent: [checks profile] → NOT FOUND
Agent: "Primera vez. Preguntas rápidas para personalizar ayuda."
→ Runs user-onboarding → Saves profile → Resumes original requestCore Process
Phase 0 — Detect Profile
- Check
~/.config/opencode/user-profile.json:- <90 days → Read, skip to Phase 3 (Quick Verify)
90 days → Read, ask "Update profile?"
- Missing → Full onboarding
- Check stale preferences: Mentioned technologies outdated (e.g., Next.js 14 when current is 16)? Suggest update.
Phase 1 — Discovery Interview (Full Onboarding)
→ See guides/ONBOARDING-QUESTIONS-GUIDE.md for complete 30-question interview (7 sections: Identity, Technical, Design, Workflow, Commit, Constraints, Session Purpose).
Summary: 27 questions covering identity, technical preferences (platform, framework, stack), design taste, workflow style, constraints.
Rules:
- Ask once. Store permanently.
- Never include secrets, API keys, or sensitive data.
- Update
updated_aton any change. - Version schema for backward compatibility.
Phase 2 — Persist & Lock
Save to ~/.config/opencode/user-profile.json:
{
"version": "1.0",
"created_at": "2026-05-24",
"updated_at": "2026-05-24",
"identity": {
"name": "Juan",
"role": "developer",
"industry": "fintech",
"experience_years": "3-5",
"team_size": "solo",
"github_username": "juandelossantos",
"author_name": "Juan de los Santos"
},
"preferences": {
"language": "es",
"primary_platform": "web",
"web_framework": "react",
"mobile_approach": null,
"desktop_framework": null,
"backend_stack": "nodejs",
"styling_approach": "tailwind",
"database": "postgresql",
"deployment": "vercel"
},
"design": {
"aesthetic": "minimalist",
"color_preference": "dark",
"typography_care": "high",
"animation_level": "moderate"
},
"workflow": {
"communication_style": "detailed",
"decision_style": "propose_options",
"commit_review": "auto_review_with_approval",
"context_persistence": true,
"documentation_level": "comprehensive",
"commit_approval": "manual"
},
"constraints": {
"budget_context": "startup",
"time_pressure": "moderate",
"open_source": false,
"accessibility_priority": "important"
},
"session_defaults": {
"default_purpose": "development",
"purpose_skills_map": {
"brainstorming": ["idea-refine", "architecture-analysis"],
"development": ["spec-driven-development", "test-driven-development", "incremental-implementation"],
"code_review": ["project-health-check", "code-review-and-quality"],
"pr_review": ["git-workflow-and-versioning", "code-review-and-quality"],
"debugging": ["debugging-and-error-recovery", "test-driven-development"],
"custom": []
}
}
}Phase 3 — Quick Verify (if profile exists)
PROFILE DETECTED:
Name: Juan | Role: Developer | Industry: Fintech
Platform: Web (React) + Node.js + PostgreSQL + Vercel
Design: Minimalist, dark mode, moderate animation
Communication: Detailed, proposes options
Default purpose: Development
→ Still correct? (yes/sí)
→ Update anything? (reply with section number)How Other Skills Use This Profile
→ See guides/USAGE-EXAMPLES-GUIDE.md for 5 skill-specific examples and preference update workflow.
Without profile: "React or Vue? What stack?"
With profile: "I see you prefer React + Tailwind. Confirm for this project?"
Common Rationalizations
| Excuse | Response |
| "Ask every time." | Repetitive questions waste time. Saved profile makes every interaction faster. |
| "User might change mind." | Quick Verify and easy updates exist. Profile is default, not prison. |
| "Multiple people, same machine." | Support multiple profiles: user-profile-juan.json, user-profile-maria.json. |
| "Just bureaucracy." | 3 minutes onboarding saves 10+ minutes repeated questions per project. |
Red Flags
- Asks "React or Vue?" when profile already specifies.
- Ignores user preference, defaults to agent's own.
- Profile contains secrets or API keys.
- Profile never updated even after user changes preferences.
Verification
Before any skill runs discovery:
- Checked
~/.config/opencode/user-profile.json - If exists: Used to personalize and skip redundant questions
- If missing: Ran full onboarding
- If outdated: Offered update
- Never stored secrets in profile
Other versions8 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 8
- Starchild-ai-agent/official-skills★ 29same name
- CodeAlive-AI/ceo-ai-os★ 9same name
- Bappoz/My-Claude-Skills★ 1same name
- certivpaul/claude-skills★ 1same name
- Layneformalized225/ai-cofounder★ 1same name
- pooriaarab/skills★ 1same name
- TGPSKI/flow-indicator★ 1same name
- 2867203296/hermes-agent★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository59 other files it gives its agents.
- AGENTS.mdAGENTS.md
- templates/CLAUDE.mdCLAUDE.md
- adapt-skillSkill
- api-and-interface-designSkill
- architecture-analysisSkill
- audit-skillSkill
- backend-api-masterySkill
- browser-testing-with-devtoolsSkill
- ci-cd-and-automationSkill
- clarify-skillSkill
- cli-toolsSkill
- code-review-and-qualitySkill
- code-simplificationSkill
- context-engineeringSkill
- critique-skillSkill
- customize-opencodeSkill
- debugging-and-error-recoverySkill
- debugging-three-strikesSkill
- delight-skillSkill
- deprecation-and-migrationSkill
- dev-environment-auditSkill
- documentation-and-adrsSkill
- doubt-driven-developmentSkill
- engineering-fundamentalsSkill
- frontend-desktopSkill
- frontend-mobileSkill
- frontend-pwaSkill
- frontend-ui-engineeringSkill
- frontend-webSkill
- fullstack-shippingSkill
- gateSkill
- git-init-and-versioningSkill
- git-workflow-and-versioningSkill
- hard-skillSkill
- idea-refineSkill
- incremental-implementationSkill
- industrial-brutalist-uiSkill
- interview-meSkill
- minimalist-uiSkill
- multi-agent-orchestrationSkill
- observability-and-instrumentationSkill
- optimize-skillSkill
- output-skillSkill
- performance-optimizationSkill
- planning-and-task-breakdownSkill
- polish-skillSkill
- project-health-checkSkill
- project-metricsSkill
- redesign-skillSkill
- security-and-hardeningSkill
- self-improvementSkill
- shipping-and-launchSkill
- skill-creatorSkill
- skill-improverSkill
- soft-premium-uiSkill
- source-driven-developmentSkill
- spec-driven-developmentSkill
- test-driven-developmentSkill
- typeset-skillSkill
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

