one-on-ones
About
This Claude Skill provides structured guidance for conducting effective one-on-one meetings, including agenda frameworks, question banks, and handling difficult conversations. It's designed for developers in leadership roles to build trust, develop team members, and proactively address issues. Use it when setting up new 1:1s, resetting unproductive meetings, or preparing for performance and career development discussions.
Quick Install
Claude Code
Recommendednpx skills add guia-matthieu/clawfu-skills -a claude-code/plugin add https://github.com/guia-matthieu/clawfu-skillsgit clone https://github.com/guia-matthieu/clawfu-skills.git ~/.claude/skills/one-on-onesCopy and paste this command in Claude Code to install this skill
Documentation
One-on-Ones
Design and run effective 1:1 meetings that build trust, develop people, and surface problems before they become crises.
When to Use This Skill
- New manager setting up 1:1s for the first time
- Resetting unproductive 1:1s that became status updates
- Onboarding a new direct report with structured first conversations
- Preparing for a difficult conversation (performance, conflict, change)
- Career development coaching in 1:1 context
- Scaling management as team grows
Methodology Foundation
| Aspect | Details |
|---|---|
| Sources | Andy Grove (High Output Management), Kim Scott (Radical Candor), Michael Lopp (Managing Humans) |
| Core Principle | The 1:1 is the direct report's meeting, not the manager's — their time to surface what matters to them |
| Key Ratio | Manager talks 10-30% of the time; listens 70-90% |
What Claude Does vs What You Decide
| Claude Does | You Decide |
|---|---|
| Designs 1:1 cadence and structure for your team size | Personal relationship-building approach |
| Generates conversation frameworks and question banks | Which questions fit each person |
| Creates agenda templates and running-notes docs | How to adapt for individual personalities |
| Prepares scripts for difficult conversations | Final wording and tone for sensitive topics |
| Suggests development discussion frameworks | Career advice based on your knowledge of the person |
Instructions
Step 1: Set Up the Mechanics
Cadence by maturity:
| Task-Relevant Maturity | Frequency | Duration |
|---|---|---|
| New or struggling | 2x/week | 30-45 min |
| Developing | Weekly | 30-45 min |
| Senior / independent | Bi-weekly | 45-60 min |
Rules: Same time each week. Rarely cancel. They own the agenda (shared doc, they add topics first). Private space for sensitive topics.
30-minute structure:
| Time | Activity |
|---|---|
| 0-5 min | Check-in: "How are you, really?" |
| 5-20 min | Their agenda items |
| 20-25 min | Your topics (feedback, context) |
| 25-30 min | Commitments and close |
Step 2: Master the Conversation
Opening — Understand where they're at: "What's on your mind this week?" / "How's your energy level?"
Middle (their agenda) — Coach, don't solve:
- "Tell me more about that."
- "What have you tried?"
- "What do you think you should do?"
- "How can I help?"
Resist the urge to fix immediately. Ask → Listen → Ask more → Let them reach conclusions.
Middle (your topics) — Keep secondary. Feedback, context, observations.
Closing — Capture commitments: "What are you committing to? What am I committing to?" Document and review next time.
Step 3: Handle Different Conversation Types
Career Development (monthly/quarterly):
- "Where do you want to be in 2-3 years?"
- "What skills do you want to develop?"
- "What would make this the best job you've ever had?"
Feedback:
- Context → 2. Specific observation → 3. Impact → 4. Their perspective → 5. What should change
Performance concern:
- State the pattern with specific examples
- Ask: "Help me understand — what's happening?"
- Explain the impact
- Agree on path forward with clear expectations and timeline
- Document
Validation checkpoint: After a performance conversation, check in at the next 1:1. If no improvement after 2-3 follow-ups, escalate to formal process.
Trust-building (new relationship):
- "Tell me about your path to here."
- "How do you like to receive feedback?"
- "What do you need from me to do your best work?"
Step 4: Troubleshoot Common Problems
| Problem | Likely Cause | Fix |
|---|---|---|
| "Everything is fine" every week | Lack of trust or wrong questions | Wait in silence longer; share your own challenges first; ask "What would you change if you could?" |
| Turns into status update | Habit, no agenda ownership | "I can read status — what do you need from me?"; use shared doc for status, meeting for discussion |
| Same complaints, no action | Venting without ownership | "We've discussed this for weeks. Are you ready to address it?" |
| Surface-level only | Trust not established yet | Walk-and-talks, share about yourself, be patient |
| Too busy to hold 1:1s | Too many reports or not delegating | 1:1s are core management work, not optional — restructure |
Examples
Example: Onboarding a New Report
Week 1 (60 min): Getting to know each other — their story, working preferences, how they like feedback, your context and priorities.
Weeks 2-4 (30 min, 2x/week): Frequent check-ins — "What's surprising? What's confusing? What do you need?"
Week 4+: Transition to weekly cadence with shared running doc. Add development topics monthly.
90-day check-in: "How's it going overall? What's working? What's not? What do you want to focus on next quarter?"
Example: Resetting Stale 1:1s
The reset conversation: "I've noticed our 1:1s have become mostly status updates. I want to use this time for things you can't get elsewhere — challenges, development, feedback. What would make these more valuable for you?"
Then: implement shared agenda doc, change opening from "What's your update?" to "What's on your mind?", add 10 minutes for development each week, experiment with format (walks, coffee).
See QUESTIONS.md for a complete question bank organized by category (opening, work, development, relationship, closing).
Skill Boundaries
What This Skill Does Well
- Designing 1:1 systems and cadence for different team sizes
- Generating conversation frameworks and question banks
- Preparing scripts for difficult management conversations
- Diagnosing and fixing unproductive 1:1 patterns
What This Skill Cannot Do
- Replace real human judgment about individual personalities
- Handle legally sensitive HR situations (consult HR/legal)
- Know your team members — you provide the context
- Substitute for building genuine relationships over time
References
- Grove, Andy. High Output Management — 1:1 fundamentals
- Scott, Kim. Radical Candor — Caring personally + challenging directly
- Lopp, Michael. Managing Humans — Practical 1:1 advice
- Horowitz, Ben. The Hard Thing About Hard Things — Difficult conversations
Related Skills
- high-output-management — Grove's full management system
- radical-candor — Feedback framework for 1:1s
GitHub Repository
Related Skills
content-collections
MetaThis skill provides a production-tested setup for Content Collections, a TypeScript-first tool that transforms Markdown/MDX files into type-safe data collections with Zod validation. Use it when building blogs, documentation sites, or content-heavy Vite + React applications to ensure type safety and automatic content validation. It covers everything from Vite plugin configuration and MDX compilation to deployment optimization and schema validation.
polymarket
MetaThis skill enables developers to build applications with the Polymarket prediction markets platform, including API integration for trading and market data. It also provides real-time data streaming via WebSocket to monitor live trades and market activity. Use it for implementing trading strategies or creating tools that process live market updates.
creating-opencode-plugins
MetaThis skill helps developers create OpenCode plugins that hook into 25+ event types like commands, files, and LSP operations. It provides the plugin structure, event API specifications, and implementation patterns for JavaScript/TypeScript modules. Use it when you need to intercept, monitor, or extend the OpenCode AI assistant's lifecycle with custom event-driven logic.
sglang
MetaSGLang is a high-performance LLM serving framework that specializes in fast, structured generation for JSON, regex, and agentic workflows using its RadixAttention prefix caching. It delivers significantly faster inference, especially for tasks with repeated prefixes, making it ideal for complex, structured outputs and multi-turn conversations. Choose SGLang over alternatives like vLLM when you need constrained decoding or are building applications with extensive prefix sharing.
