{
  "schema_version": 2,
  "name": "ai-customer-reply-coach",
  "slug": "ai-customer-reply-coach",
  "title": "Let AI Draft Routine Replies, Keep the Human on the Conversation",
  "description": "Use this Brali skill when the user's situation matches the bounded protocol \"Let AI Draft Routine Replies, Keep the Human on the Conversation\". For repetitive support or service messages, AI can propose a response from the case facts and approved guidance while the human checks diagnosis, policy, tone, and the actual next step. Large-scale field evidence supports gains in one customer-support setting, especially for less experienced workers. Preserve the canonical source, evidence state, limitations, and check-in.",
  "protocol_id": "brali:ai-customer-reply-coach",
  "canonical_protocol_url": "https://brali-lifeos.github.io/life-os/ai-customer-reply-coach/",
  "machine_record_url": "https://brali-lifeos.github.io/life-os/ai-customer-reply-coach/index.json",
  "skill_page_url": "https://brali-lifeos.github.io/skill-packs/ai-customer-reply-coach/",
  "skill_markdown_url": "https://brali-lifeos.github.io/skill-packs/ai-customer-reply-coach/SKILL.md",
  "skill_mode": "usable",
  "recommendation_eligible": true,
  "operational_guidance": true,
  "evidence_state": "reviewed",
  "sensitive": false,
  "reviewed_at": "2026-09-15",
  "topics": [
    "Clear Communication",
    "Difficult Conversations"
  ],
  "methods": [],
  "lenses": [
    "AI Collaboration"
  ],
  "license": "CC-BY-NC-SA-4.0",
  "source_library": "https://brali-lifeos.github.io/skill-packs/library.json",
  "trusted_feed": "https://brali-lifeos.github.io/life-os/datasets/protocols.json",
  "format": {
    "name": "Agent Skills",
    "specification": "https://agentskills.io/specification",
    "artifact": "SKILL.md"
  },
  "compatible_hosts": [
    "Claude Code",
    "Hermes Agent",
    "OpenClaw",
    "AgentSkills.io-compatible hosts"
  ],
  "install": {
    "generic": {
      "artifact_url": "https://brali-lifeos.github.io/skill-packs/ai-customer-reply-coach/SKILL.md",
      "directory_name": "ai-customer-reply-coach"
    },
    "claude_code": {
      "personal_path": "~/.claude/skills/ai-customer-reply-coach/SKILL.md",
      "project_path": ".claude/skills/ai-customer-reply-coach/SKILL.md",
      "docs": "https://platform.claude.com/docs/en/agents-and-tools/agent-skills/overview"
    },
    "hermes_agent": {
      "command": "hermes skills install https://brali-lifeos.github.io/skill-packs/ai-customer-reply-coach/SKILL.md",
      "docs": "https://hermes-agent.nousresearch.com/docs/guides/work-with-skills"
    },
    "openclaw": {
      "workspace_path": "<workspace>/skills/ai-customer-reply-coach/SKILL.md",
      "global_path": "~/.openclaw/skills/ai-customer-reply-coach/SKILL.md",
      "docs": "https://github.com/openclaw/openclaw/blob/main/docs/tools/skills.md"
    }
  },
  "verification": {
    "status": "brali-ci-verified",
    "scope": "one-skill-per-hack coverage + format + evidence-state parity + provenance + stable links + SHA-256; not third-party vendor endorsement",
    "sha256": "9bb4da2084716dee66c069adcde92cbe638d7f593b7d8036863beea4033279b1",
    "trust_gate": "reviewed",
    "source_protocol_id": "brali:ai-customer-reply-coach"
  }
}