一键导入
bolta-agent-configure
Modify an existing agent's configuration including persona, model tier, enabled skills, and job settings
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Modify an existing agent's configuration including persona, model tier, enabled skills, and job settings
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Activate a paused job after preview and voice validation - the explicit trust moment where user says "yes, start posting"
Create and onboard a new AI agent teammate from marketplace presets with conversational discovery and preview generation.
Store and retrieve information across job runs - how agents learn and improve over time
Handle @mention interactions where users ask agents for quick feedback on posts and drafts
Bolta Skills Registry - canonical index and orchestration layer for all Bolta skills, organized by plane
Export audit/activity events for a workspace (agent + human actions) for debugging and compliance.
| name | bolta.agent.configure |
| version | 2.0.0 |
| description | Modify an existing agent's configuration including persona, model tier, enabled skills, and job settings |
| category | agent |
| roles_allowed | ["Editor","Admin"] |
| required_scopes | ["workspace:read"] |
| agent_types | ["custom"] |
| safe_defaults | {"require_job_pause_for_breaking_changes":true} |
| tools_required | ["bolta.get_agent","bolta.update_agent","bolta.list_jobs","bolta.update_job"] |
| inputs_schema | {"type":"object","required":["agent_id","updates"],"properties":{"agent_id":{"type":"string","description":"Agent UUID to configure"},"updates":{"type":"object","properties":{"persona":{"type":"string","description":"Personality and behavioral guidelines"},"model":{"type":"string","enum":["claude-sonnet-4","claude-opus-4","claude-haiku-4"],"description":"Claude model tier"},"enabled_skills":{"type":"array","items":{"type":"string"},"description":"Skills this agent can use"},"job_updates":{"type":"array","items":{"type":"object","properties":{"job_id":{"type":"string"},"schedule":{"type":"object"},"run_instructions":{"type":"string"}}}}}}}} |
| outputs_schema | {"type":"object","properties":{"agent_id":{"type":"string"},"updated_fields":{"type":"array","items":{"type":"string"}},"warnings":{"type":"array","items":{"type":"string"}}}} |
| organization | bolta.ai |
| author | Bolta Team |
Modify an existing agent's configuration to customize persona, model tier, enabled skills, and job settings after hiring.
bolta.get_agent(agent_id) → verify agent exists and belongs to workspacebolta.list_jobs(agent_id) → verify all job_ids belong to this agentbolta.update_agent(agent_id, updates)bolta.update_job(job_id, {schedule, run_instructions}){
"agent_id": "uuid",
"updated_fields": ["persona", "model", "enabled_skills"],
"warnings": ["Model downgrade from Opus to Sonnet may reduce output quality"]
}
{
"agent_id": "uuid",
"updates": {
"persona": "More enthusiastic and emoji-heavy for social engagement"
}
}
Result: Agent persona updated, no other changes
{
"agent_id": "uuid",
"updates": {
"model": "claude-opus-4"
}
}
Result: Agent now uses Opus (higher quality, higher cost)
{
"agent_id": "uuid",
"updates": {
"job_updates": [
{
"job_id": "uuid",
"schedule": {"cron": "0 9 * * 1,3,5"},
"run_instructions": "Create 1 LinkedIn post about remote work best practices"
}
]
}
}
Result: Job now runs Monday, Wednesday, Friday at 9am with new instructions