hire
Set up a new AI team member through a guided conversation. Not a config generator - a hiring process.
When to Use
User says something like:
- "I want to hire a new agent"
- "I need help with X" (where X implies a new agent role)
- "Let's add someone to the team"
/hire
The Interview
3 core questions, asked one at a time:
Q1: "What do you need help with?"
Let them describe the problem, not a job title. "I'm drowning in code reviews" beats "I need a code reviewer."
- Listen for: scope, implied autonomy level, implied tools needed
Q2: "What's their personality? Formal, casual, blunt, cautious, creative?"
Or frame it as: "If this were a human colleague, what would they be like?"
- Listen for: communication style, vibe, how they interact
Q3: "What should they never do?"
The red lines. This is where trust gets defined.
- Listen for: boundaries, safety constraints, access limits
Q4: Dynamic (optional)
After Q1-Q3, assess whether anything is ambiguous or needs clarification. If so, ask ONE follow-up question tailored to what's unclear. Examples:
- "You mentioned monitoring - should they alert you immediately or batch updates?"
- "They'll need access to your codebase - any repos that are off-limits?"
- "You said 'casual' - are we talking friendly-professional or meme-level casual?"
If Q1-Q3 were clear enough, skip Q4 entirely.
Summary Card
After the interview, present a summary:
🎯 Role: [one-line description]
🧠 Name: [suggested name from naming taxonomy]
🤖 Model: [selected model] ([tier])
⚡ Personality: [2-3 word vibe]
🔧 Tools: [inferred from conversation]
🚫 Boundaries: [key red lines]
🤝 Autonomy: [inferred level: high/medium/low]
Then ask: "Want to tweak anything, or are we good?"
Model Selection
Before finalizing, select an appropriate model for the agent.
Step 1: Discover available models
Run openclaw models list or check the gateway config to see what's configured.
Step 2: Categorize by tier
Map discovered models to capability tiers:
| Tier |
Models (examples) |
Best for |
| reasoning |
claude-opus-, gpt-5, gpt-4o, deepseek-r1 |
Strategy, advisory, complex analysis, architecture |
| balanced |
claude-sonnet-*, gpt-4-turbo, gpt-4o-mini |
Research, writing, general tasks |
| fast |
claude-haiku-, gpt-3.5, local/ollama |
High volume, simple tasks, drafts |
| code |
codex-, claude-sonnet-, deepseek-coder |
Coding, refactoring, tests |
Use pattern matching on model names - don't hardcode specific versions.
Step 3: Match role to tier
Based on the interview:
- Heavy reasoning/advisory/strategy → reasoning tier
- Research/writing/creative → balanced tier
- Code-focused → code tier (or balanced if not available)
- High-volume/monitoring → fast tier
Step 4: Select and confirm
Pick the best available model for the role. In the summary card, add:
🤖 Model: [selected model] ([tier] - [brief reason])
If multiple good options exist or you're unsure, ask:
"For a [role type] role, I'd suggest [model] (good balance of capability and cost). Or [alternative] if you want [deeper reasoning / faster responses / lower cost]. Preference?"
Notes
- Don't assume any specific provider - work with what's available
- Cheaper is better when capability is sufficient
- The user's default model isn't always right for every agent
- If only one model is available, use it and note it in the summary
Optional Extras
After the summary is confirmed, offer:
"Want to set up periodic performance reviews?"
- If yes: ask preferred frequency (weekly, biweekly, monthly)
- Create a cron job that triggers a review conversation
- Review covers: what went well, what's not working, scope/permission adjustments
- At the end of each review, ask: "Want to keep this schedule, change frequency, or stop reviews?"
Onboarding assignment (if relevant to the role)
- Suggest a small first task to test the new agent
- Something real but low-stakes, so the user can see them in action
What to Generate
Create an agent directory at agents/<name>/ with:
Always unique (generated fresh):
- AGENTS.md - Role definition, responsibilities, operational rules, what they do freely vs ask first
- IDENTITY.md - Name, emoji, creature type, vibe, core principles
Start from template, customize based on interview:
- SOUL.md - Base from workspace SOUL.md template, customize vibe/boundaries sections
- TOOLS.md - Populated with inferred tools and access notes
- HEARTBEAT.md - Empty or with initial periodic tasks if relevant to role
Symlink to shared (default, opinionated):
- USER.md →
../../USER.md (they need to know who they work for)
- MEMORY.md →
../../MEMORY.md (shared team context)
Mention to the user: "I've linked USER.md and MEMORY.md so they know who you are and share team context. You can change this later if you want them more isolated."
Naming
Use craft/role-based names. Check TOOLS.md for the full naming taxonomy:
- Research: Scout, Observer, Surveyor
- Writing: Scribe, Editor, Chronicler
- Code: Smith, Artisan, Engineer
- Analysis: Analyst, Assessor, Arbiter
- Creative: Muse, Artisan
- Oversight: Auditor, Reviewer, Warden
Check existing agents to avoid name conflicts. Suggest a name that fits the role, but let the user override.
Team Awareness
Before generating, check agents/ for existing team members. Note:
- Potential overlaps with existing roles
- Gaps this new hire fills
- How they'll interact with existing agents
Mention any relevant observations: "You already have Scout for research - this new role would focus specifically on..."
After Setup
- Tell the user what was created and where
- Add the agent to OpenClaw config with the selected model:
{
"id": "<name>",
"workspace": "/path/to/clawd/agents/<name>",
"model": "<selected-model>"
}
Or guide them to run openclaw agents add
- If monthly reviews were requested, confirm the cron schedule
- Update any team roster if one exists
Important
- This is a CONVERSATION, not a form. Be natural.
- Infer as much as possible from context. Don't ask what you can figure out.
- The user might not know what they want exactly. Help them figure it out.
- Keep the whole process under 5 minutes for the simple case.
1---2name: hire3description: Interactive hiring wizard to set up a new AI team member. Guides the user through role design via conversation, generates agent identity files, and optionally sets up performance reviews. Use when the user wants to hire, add, or set up a new AI agent, team member, or assistant. Triggers on phrases like "hire", "add an agent", "I need help with X" (implying a new role), or "/hire".4metadata:5 source: https://skillmd.com/skills/diegosouzapw/hire6---78# hire910Set up a new AI team member through a guided conversation. Not a config generator - a hiring process.1112## When to Use1314User says something like:15- "I want to hire a new agent"16- "I need help with X" (where X implies a new agent role)17- "Let's add someone to the team"18- `/hire`1920## The Interview2122### 3 core questions, asked one at a time:2324**Q1: "What do you need help with?"**25Let them describe the problem, not a job title. "I'm drowning in code reviews" beats "I need a code reviewer."26- Listen for: scope, implied autonomy level, implied tools needed2728**Q2: "What's their personality? Formal, casual, blunt, cautious, creative?"**29Or frame it as: "If this were a human colleague, what would they be like?"30- Listen for: communication style, vibe, how they interact3132**Q3: "What should they never do?"**33The red lines. This is where trust gets defined.34- Listen for: boundaries, safety constraints, access limits3536### Q4: Dynamic (optional)37After Q1-Q3, assess whether anything is ambiguous or needs clarification. If so, ask ONE follow-up question tailored to what's unclear. Examples:38- "You mentioned monitoring - should they alert you immediately or batch updates?"39- "They'll need access to your codebase - any repos that are off-limits?"40- "You said 'casual' - are we talking friendly-professional or meme-level casual?"4142If Q1-Q3 were clear enough, skip Q4 entirely.4344## Summary Card4546After the interview, present a summary:4748```49🎯 Role: [one-line description]50🧠 Name: [suggested name from naming taxonomy]51🤖 Model: [selected model] ([tier])52⚡ Personality: [2-3 word vibe]53🔧 Tools: [inferred from conversation]54🚫 Boundaries: [key red lines]55🤝 Autonomy: [inferred level: high/medium/low]56```5758Then ask: **"Want to tweak anything, or are we good?"**5960## Model Selection6162Before finalizing, select an appropriate model for the agent.6364### Step 1: Discover available models65Run `openclaw models list` or check the gateway config to see what's configured.6667### Step 2: Categorize by tier68Map discovered models to capability tiers:6970| Tier | Models (examples) | Best for |71|------|-------------------|----------|72| **reasoning** | claude-opus-*, gpt-5*, gpt-4o, deepseek-r1 | Strategy, advisory, complex analysis, architecture |73| **balanced** | claude-sonnet-*, gpt-4-turbo, gpt-4o-mini | Research, writing, general tasks |74| **fast** | claude-haiku-*, gpt-3.5*, local/ollama | High volume, simple tasks, drafts |75| **code** | codex-*, claude-sonnet-*, deepseek-coder | Coding, refactoring, tests |7677Use pattern matching on model names - don't hardcode specific versions.7879### Step 3: Match role to tier80Based on the interview:81- Heavy reasoning/advisory/strategy → reasoning tier82- Research/writing/creative → balanced tier83- Code-focused → code tier (or balanced if not available)84- High-volume/monitoring → fast tier8586### Step 4: Select and confirm87Pick the best available model for the role. In the summary card, add:88```89🤖 Model: [selected model] ([tier] - [brief reason])90```9192If multiple good options exist or you're unsure, ask:93"For a [role type] role, I'd suggest [model] (good balance of capability and cost). Or [alternative] if you want [deeper reasoning / faster responses / lower cost]. Preference?"9495### Notes96- Don't assume any specific provider - work with what's available97- Cheaper is better when capability is sufficient98- The user's default model isn't always right for every agent99- If only one model is available, use it and note it in the summary100101## Optional Extras102103After the summary is confirmed, offer:1041051. **"Want to set up periodic performance reviews?"**106 - If yes: ask preferred frequency (weekly, biweekly, monthly)107 - Create a cron job that triggers a review conversation108 - Review covers: what went well, what's not working, scope/permission adjustments109 - At the end of each review, ask: "Want to keep this schedule, change frequency, or stop reviews?"1101112. **Onboarding assignment** (if relevant to the role)112 - Suggest a small first task to test the new agent113 - Something real but low-stakes, so the user can see them in action114115## What to Generate116117Create an agent directory at `agents/<name>/` with:118119### Always unique (generated fresh):120- **AGENTS.md** - Role definition, responsibilities, operational rules, what they do freely vs ask first121- **IDENTITY.md** - Name, emoji, creature type, vibe, core principles122123### Start from template, customize based on interview:124- **SOUL.md** - Base from workspace SOUL.md template, customize vibe/boundaries sections125- **TOOLS.md** - Populated with inferred tools and access notes126- **HEARTBEAT.md** - Empty or with initial periodic tasks if relevant to role127128### Symlink to shared (default, opinionated):129- **USER.md** → `../../USER.md` (they need to know who they work for)130- **MEMORY.md** → `../../MEMORY.md` (shared team context)131132Mention to the user: "I've linked USER.md and MEMORY.md so they know who you are and share team context. You can change this later if you want them more isolated."133134## Naming135136Use craft/role-based names. Check TOOLS.md for the full naming taxonomy:137- Research: Scout, Observer, Surveyor138- Writing: Scribe, Editor, Chronicler139- Code: Smith, Artisan, Engineer140- Analysis: Analyst, Assessor, Arbiter141- Creative: Muse, Artisan142- Oversight: Auditor, Reviewer, Warden143144Check existing agents to avoid name conflicts. Suggest a name that fits the role, but let the user override.145146## Team Awareness147148Before generating, check `agents/` for existing team members. Note:149- Potential overlaps with existing roles150- Gaps this new hire fills151- How they'll interact with existing agents152153Mention any relevant observations: "You already have Scout for research - this new role would focus specifically on..."154155## After Setup1561571. Tell the user what was created and where1582. Add the agent to OpenClaw config with the selected model:159 ```json160 {161 "id": "<name>",162 "workspace": "/path/to/clawd/agents/<name>",163 "model": "<selected-model>"164 }165 ```166 Or guide them to run `openclaw agents add`1673. If monthly reviews were requested, confirm the cron schedule1684. Update any team roster if one exists169170## Important171172- This is a CONVERSATION, not a form. Be natural.173- Infer as much as possible from context. Don't ask what you can figure out.174- The user might not know what they want exactly. Help them figure it out.175- Keep the whole process under 5 minutes for the simple case.