diff --git a/recruitment/SKILL.md b/recruitment/SKILL.md
index 60efb11..8395268 100644
--- a/recruitment/SKILL.md
+++ b/recruitment/SKILL.md
@@ -17,37 +17,54 @@ new-agent --type contractor --contractor-provider <claude|gemini> --agent-id <ag
 
 ## Workflow
 
-The `new-agent` script executes these steps:
+When a request to create a new agent is received, follow this workflow:
 
-1. **Register agent**:
-   - `openclaw`: runs `openclaw agents add {agent-id} --model {primary-model} --workspace ~/.openclaw/workspace/workspace-{agent-id} --non-interactive`
-   - `contractor`: requires `contractor-agent` plugin; runs `openclaw contractor-agents add --agent-id {agent-id} --workspace ~/.openclaw/workspace/workspace-{agent-id} --contractor {contractor-provider}`
+### Step 1 — Gather Requirements
 
-2. **Wait for bindings**:
-   - Poll `openclaw config get bindings` every 10s until `interviewee` accountId is no longer present
-   - Check `~/.openclaw/states/bindings.lock` exists → wait every 10s until it disappears
+Communicate with the requester to collect the following:
+- New agent's `agent-id`
+- New agent's primary model (`--model`)
+- New agent's role and position
+- Whether the agent is a contractor agent (default: not a contractor)
 
-3. **Set bindings**:
-   - Create `~/.openclaw/states/bindings.lock`
-   - Fetch current bindings, append entry:
-     ```json
-     {
-       "agentId": "{agent-id}",
-       "match": {
-         "channel": "discord",
-         "accountId": "interviewee"
-       }
-     }
-     ```
-   - Write back with `openclaw config set`
-   - Delete `bindings.lock`
+### Step 2 — Create Agent
 
-4. **Configure interviewee account**:
-   ```bash
-   openclaw config set channels.discord.accounts.interviewee {
-     "enabled": true,
-     "token": "<secret-mgr get-secret --key interviewee-discord-token>",
-     "groupPolicy": "open",
-     "streaming": { "mode": "off" }
-   }
-   ```
+Execute `{baseDir}/scripts/new-agent` with the gathered parameters:
+```bash
+# openclaw type
+new-agent --type openclaw --agent-id <agent-id> --model <primary-model>
+
+# contractor type
+new-agent --type contractor --contractor-provider <claude|gemini> --agent-id <agent-id>
+```
+
+### Step 3 — Interview
+
+Use the `create-discussion-channel` tool to start an interview with the new agent:
+- Participant: `interviewee`
+- Discussion guide: "`<@{ego-mgr get discord-id}>`请参考{baseDir}/workflow/interview.md"
+
+After receiving the discussion callback, review the discussion summary:
+- If it contains the agent's **name** and **gender** → proceed to Step 4
+- If either field is missing → attempt to gather the missing information via another `create-discussion-channel` call
+- If still unavailable → notify the requester and proceed without it
+
+### Step 4 — Onboard
+
+Use `proxy-pcexec` to call `{baseDir}/scripts/onboard`:
+- `proxy-for`: new agent's `agent-id`
+- Parameters: `--name`, `--role`, `--position`, `--gender`, `--bot-token`
+
+### Step 5 — Report
+
+Notify the requester that onboarding is complete.
+
+## Scripts
+
+### new-agent
+
+Creates and registers the agent, then configures the `interviewee` Discord account binding.
+
+### onboard
+
+Sets up ego-mgr identity fields and configures the agent's Discord account using the name/gender collected during interview.