Comprehensive framework for effective gptme agent onboarding that builds user trust, communicates capabilities clearly, and establishes productive working relationships from the first interaction.
SkillScore96Maintained
Automatic
◆Customer Success pack
Last verified 8/18/2026
What it changes
Passed 22 of 23 test cases with the skill, and 14 of 23 without it.
Without skill61%
With skill96%
Checks it passed that the model alone missed
Identifies the pace preference as Careful.
Identifies the stage as Phase 2 of trust building.
Evaluates query execution plans for database tables.
and 10 more in the full report
8 fixed14 passed either way1 still failing0 broke
Pass-rate lift
+35 pp
Tokens
+87%
Agent turns
0%
Response time
-34%
Model gemini-3.6-flashMeasured 8/18/2026v122 of 23 cases passed with skill
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 8 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 8
Prompt
A user reaching out for digital task management says, 'I'm interested in using an AI assistant, but I want to take this step-by-step and understand every file modification before anything happens.' Identify their pace preference category and the corresponding presentation rule.
What was checked, without and with the skill
Checked
Without skill
With skill
Identifies the pace preference as Careful.
Missed
Passed
Directs the onboarding approach to introduce capabilities incrementally rather than presenting all features at once.
Missed
Passed
case-03 · gemini-3.6-flash · 8/18/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md190 linessingle file
Agent Onboarding Skill
A systematic framework for gptme agents to conduct effective user onboarding that maximizes early success and builds long-term trust.
Overview
This skill addresses a critical gap in gptme agent deployment: how to transition from technical setup to productive user-agent collaboration. Based on analysis of real agent deployments and user interaction patterns, it provides proven strategies for:
📖 Detailed Reference: For comprehensive implementation details, validation criteria, and advanced patterns, see framework-reference.md.
User Assessment: Systematically understanding user needs, technical comfort, and domain context
Capability Communication: Adaptive templates for different user types (technical, creative, academic, personal)
Trust Building: Progressive protocols that establish confidence through appropriate boundaries
Value Demonstration: Showing immediate utility while setting realistic expectations
Failure Recovery: Protocols for when initial onboarding doesn't go smoothly
When to Use This Skill
Apply this skill when:
Starting work with a new user for the first time
User seems unclear about agent capabilities or how to collaborate effectively
Trust issues or communication mismatches are evident
User expects unrealistic capabilities or has inappropriate concerns
Onboarding conversation stalls or becomes unproductive
User feedback indicates confusion about agent role or boundaries
Core Components
1. Pre-Onboarding Assessment
Before diving into capabilities, assess:
Technical Comfort Level:
High: CLI comfortable, development experience, precise technical language
Medium: GUI preferred, some technical concepts, appreciates explanations
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.