didww/ai / skills/didww-connect
didww-connect
VerifiedConnect a DIDWW phone number to ANY AI voice platform: helps choose the platform, then wires the SIP trunk pair and number. Use whenever the user wants a voice AI agent on a DIDWW number and has not committed to a platform, asks which AI platform to use with DIDWW, or names a platform that has no dedicated didww-to-X skill installed. Covers ElevenLabs, Vapi, Retell, Ultravox, Vogent, OpenAI Realtime, xAI, LiveKit and the enterprise-gated platforms.
| File | Kind | Size |
|---|---|---|
| .npmignore | other | 66 B |
| LICENSE | other | 1.1 KB |
| README.md | markdown | 2.2 KB |
| SKILL.md | skill md | 7.7 KB |
| bin/install.jsexecutable | script | 5.3 KB |
| install.shexecutable | script | 1.0 KB |
| package.json | manifest | 888 B |
| publish.shexecutable | script | 604 B |
| references/panels-and-billing.md | markdown | 6.2 KB |
| scripts/monitor.py | script | 5.7 KB |
| test.shexecutable | script | 488 B |
| tests/mock_didww.py | script | 3.0 KB |
| tests/test_monitor.py | script | 3.8 KB |
tests/mock_didww.py
View on GitHubimport json, sys, urllib.parse
from http.server import BaseHTTPRequestHandler, HTTPServer
SCEN, PORT = sys.argv[1], int(sys.argv[2])
def data():
bal = 5.0 if SCEN == "lowbal" else 42.5
credit = 0.0
if SCEN == "creditline":
bal, credit = -37723.54, 50000.00
dids = [{"id":"d1","type":"dids","attributes":{"number":"33144556677","blocked": SCEN=="blocked","awaiting_registration":False}},
{"id":"d2","type":"dids","attributes":{"number":"441234567890","blocked":False,"awaiting_registration": SCEN=="awaiting"}}]
if SCEN in ("many", "offhost"): # 150 DIDs: two pages at the 100 maximum
dids = [{"id": f"m{i}", "type": "dids", "attributes": {"number": f"3314400{i:04d}", "blocked": SCEN == "many" and i == 149, "awaiting_registration": False}} for i in range(150)]
if SCEN == "terminated":
dids.append({"id":"d3","type":"dids","attributes":{"number":"13614157804","blocked":True,"terminated":True,"awaiting_registration":False}})
trunks = [] if SCEN == "notrunk" else [{"id":"t1","type":"trunks","attributes":{"name":"in-elevenlabs"}}]
return {"/balance":{"data":{"id":"b","type":"balances","attributes":{"balance":str(bal),"credit":str(credit),"total_balance":str(round(bal+credit,2))}}},
"/dids":{"data":dids}, "/trunks":{"data":trunks}}
class H(BaseHTTPRequestHandler):
def do_GET(self):
path = self.path.split("?")[0]
if SCEN == "http500" and path == "/balance":
self.send_response(500); self.end_headers(); self.wfile.write(b'{"errors":[{"title":"boom"}]}'); return
if self.headers.get("Api-Key") != "fake" or "vnd.api+json" not in self.headers.get("Accept",""):
self.send_response(401); self.end_headers(); self.wfile.write(b'{"errors":[{"title":"bad headers"}]}'); return
q = urllib.parse.parse_qs(urllib.parse.urlsplit(self.path).query)
size = int(q.get("page[size]", ["50"])[0]); num = int(q.get("page[number]", ["1"])[0])
if size > 100: # DIDWW's documented maximum page size
self.send_response(400); self.end_headers(); self.wfile.write(b'{"errors":[{"title":"page size too large"}]}'); return
if (SCEN == "dids500" and path == "/dids") or (SCEN == "trunks500" and path == "/trunks"):
self.send_response(500); self.end_headers(); self.wfile.write(b'{"errors":[{"title":"boom"}]}'); return
full = data().get(path, {"data": []})
if isinstance(full.get("data"), list):
items = full["data"]; page = {"data": items[(num - 1) * size: num * size], "links": {}}
if num * size < len(items):
host = "https://evil.example" if SCEN == "offhost" else f"http://127.0.0.1:{PORT}"
page["links"]["next"] = f"{host}{path}?page[number]={num + 1}&page[size]={size}"
full = page
body = json.dumps(full).encode()
self.send_response(200); self.send_header("Content-Type","application/vnd.api+json"); self.end_headers(); self.wfile.write(body)
def log_message(self, *a): pass
HTTPServer(("127.0.0.1", PORT), H).serve_forever()
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |