Agent skill
1on1-prep
Prepare for 1on1 meetings using a Psychological Safety x Responsibility framework. Use when preparing for a 1on1, noticing behavioral changes, or planning a difficult conversation with a report.
Install this agent skill to your Project
npx add-skill https://github.com/hairihou/dotfiles/tree/main/src/.config/claude/skills/1on1-prep
SKILL.md
1on1 Prep
Structured 1on1 preparation using the Psychological Safety x Responsibility 4-zone framework.
Core principle: 1on1 is a diagnostic tool — assess the zone first, then adapt your approach accordingly.
Scope: One member at a time. Not for team-wide assessment.
Framework details: ${CLAUDE_SKILL_DIR}/references/framework.md
Process
Step 1: Gather Observations
Ask the manager (via AskUserQuestion) about recent observations:
- "How has their communication style changed recently?" (tone in reviews, meetings, Slack)
- "What's their current workload like? Any deadline pressure?"
- "Are they taking on new challenges or staying in familiar territory?"
- "How do they respond to feedback or ambiguity?"
- "Have they expressed frustration, boredom, or disengagement?"
Supplement with objective data sources from the framework reference when available.
Step 2: Zone Assessment
Read the framework reference and map observations to a zone using the assessment decision flow.
Handling mixed signals: Use the dominant signal rule:
- Identify which axis (Safety or Responsibility) has clearer evidence
- Prioritize the zone with higher risk (Anxiety > Apathy > Comfort > Learning)
When genuinely ambiguous, start the 1on1 with open-ended questions from both candidate zones.
Step 3: Zone-Specific Strategy
Read the framework reference and apply the strategy, key questions, and 1on1 approach for the assessed zone.
Step 4: Generate Agenda
Output a structured 1on1 agenda:
## 1on1 Agenda: <member-name> — <date>
**Assessed zone:** <zone-name> (<Safety level> x <Responsibility level>)
**Basis:** <2-3 specific observations that led to this assessment>
### Opening (5 min)
- "<zone-appropriate opening question>"
### Core Discussion (15 min)
- "<question 1 from zone strategy>"
- "<question 2 from zone strategy>"
- "<question 3, optional>"
### Action Items
- [ ] **Manager:** <concrete action with deadline>
- [ ] **Manager:** <concrete action with deadline>
- [ ] **<member-name>:** <concrete action with deadline>
### Follow-up
- <next check-in type and timing>
- <next full 1on1 timing — shorter for Anxiety/Apathy>
Example output: see ${CLAUDE_SKILL_DIR}/references/framework.md (bottom section).
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
retrospect
Guided personal reflection that separates fact, interpretation, and emotion through structured inquiry. Use when "something feels off", "need to process this", "had a conflict", or decisions feel unclear. Not for technical decision analysis — use devils-advocate for that.
bonsai
Maintain and groom config files in the current repository. Use when "bonsai", "tidy up", "prune configs", "clean up", "spring cleaning", or reviewing config health. Not for code quality review — use code-critic for that.
npm-update-report
Dependency update workflow with vulnerability assessment and verification. Use when asked to check outdated packages, bump dependencies, run audit, do periodic dependency maintenance, or when security vulnerabilities are reported.
session-insights
Analyze the current conversation for inefficiencies and improvement opportunities. Use when "how did this session go", "what went wrong", "what could I have done better", or reviewing session quality. Not for personal reflection — use retrospect. Not for logging work — use diary.
pr
Create or update a GitHub pull request. Use when asked to create a PR, submit for review, or push changes as a PR. Not for code review comments — use conventional-comments for that.
conventional-comments
Format code review comments using Conventional Comments labels and decorations. Use when writing inline review comments on a PR diff. Not for creating PRs — use pr for that. Not for complexity analysis — use code-critic for that.
Didn't find tool you were looking for?