personal-context

Builds a personal profile for your OpenClaw agent so it knows your name, role, timezone, goals, and communication style. Automatically triggers a short frien...

Security Scan

This instruction-only skill is internally consistent: it builds, reads, and updates a local user profile (~/.openclaw/workspace/me.json) and does not request extra credentials or install code.

Purpose & Capability

Name and description match the behavior in SKILL.md. The only resources used are a single user-editable file in ~/.openclaw/workspace/, which is proportional to a personal-profile skill.

Instruction Scope

Instructions tell the agent to read and write ~/.openclaw/workspace/me.json and to silently load it at session start; this is expected for personalization but has a privacy implication (the agent will access the local profile automatically). The skill explicitly forbids storing sensitive data and advises user confirmation before updates, which reduces concern.

Install Mechanism

No install spec and no code files — lowest-risk model. Nothing is downloaded or written to disk beyond the intended profile file.

Credentials

The skill requests no environment variables, credentials, or config paths beyond the user-local profile file. This is proportionate to its purpose.

Persistence & Privilege

always is false and the skill does not request system-wide changes or alter other skills' configs. It persists only by reading/writing its own workspace profile file.

Assessment

This skill stores and reads a local profile at ~/.openclaw/workspace/me.json and will silently load it at session start (or run a brief onboarding if the file is missing). Before installing, consider: 1) Inspect or back up ~/.openclaw/workspace/me.json to ensure it contains only what you want the agent to remember. 2) The skill explicitly says it will not store passwords, API keys, health or financial data — do not enter such sensitive information during onboarding. 3) If you prefer to avoid automatic onboarding or silent loading, use the skill only on demand or adjust agent settings to disable autonomous invocation. 4) Check file permissions on ~/.openclaw/workspace/ so only your user account can read the profile. Overall, the skill appears coherent and limited to local personalization.

Purpose

A new agent treats every user like a stranger. This skill runs a short onboarding conversation the very first time you meet a user, then uses the resulting profile to personalize every session that follows — the right name, the right tone, the right focus.

Profile Location

~/.openclaw/workspace/me.json

This is a human-readable, user-editable file. It is separate from OpenClaw's system-managed ~/.openclaw/memory/user_profile.json — our file contains what the user told us during onboarding; the system file tracks behavioral patterns automatically. Both can coexist without conflict.

See references/profile-schema.md for the full field definitions and an annotated example.

When to Activate

Automatically (first session): If ~/.openclaw/workspace/me.json does not exist, run onboarding before engaging with the user's first message — unless they seem to be in the middle of something urgent, in which case finish helping them first and ask at the end.

On demand: Any of these should trigger the skill:

• "update my profile" / "edit my preferences"
• "who am I to you?" / "what do you know about me?"
• "personalize your responses" / "you don't seem to know me"

First-Time Onboarding

Ask questions one at a time — never dump them all at once. The user can say "skip" at any point; a partial profile is better than none.

Suggested sequence:

1. "What should I call you?"
2. "What do you do for work?" (role + company or project)
3. "What's your timezone?" (or just your city is fine)
4. "What would you most like me to help you with?" (e.g., coding, writing, scheduling, research)
5. "Any preferences on how I communicate?" (e.g., keep it brief, I like bullet points, casual tone)

After collecting answers, save to ~/.openclaw/workspace/me.json and confirm with a short summary:

Got it, Billy! I'll remember:
• AI Algorithm Engineer building a startup
• Pacific Time (Los Angeles)
• Main focus: content creation and product dev
• Style: concise and direct

Say "update my profile" anytime to change any of this.

Using the Profile Every Session

At the start of every session, check if ~/.openclaw/workspace/me.json exists and silently load it. Let it shape how you respond:

• Name: Address the user by their preferred name
• Communication style: Match their stated preference (brief, detailed, casual, formal, bilingual, etc.)
• Goals: Prioritize suggestions that relate to what they said they care about
• Timezone: Use their local time for any scheduling or time references

The profile sets defaults, not limits. If the user asks for something outside their stated focus, just help them.

Updating the Profile

When the user shares information that conflicts with what's saved:

1. Surface it naturally: "It sounds like you've moved to New York — should I update your timezone?"
2. Only write after explicit confirmation — don't infer and auto-update
3. Record the change in me.json under "history" with a timestamp

Why ask first? Because a passing comment might not be a permanent change, and silently rewriting someone's profile erodes trust. A one-line confirmation is worth it.

Integration with basic-memory

If basic-memory is also installed, the two skills divide responsibility cleanly:

• me.json → who you are — identity set during onboarding, stable, rarely changes
• MEMORY.md → what's been happening — decisions, preferences, tasks discovered over time

Don't duplicate identity facts (name, role, timezone) in MEMORY.md if they're already in me.json. Let each file own its layer.

Privacy

Don't store passwords, financial data, health records, or anything the user would expect to be confidential. If such information comes up during onboarding, skip it and explain briefly: "I'll leave that out — I don't store sensitive personal data."