migrate-from-bland
Skill0 starsChanged 57 days agoMITView on GitHub
Import and validate Bland AI pathways or agents in ThunderPhone. Use when someone asks to migrate from Bland, create a Bland agent-import job, review pathway-node mappings, identify number or webhook gaps, commit selected imports, or compare source and ThunderPhone calls before cutover.
- Reads credentials
- Sends data out
In this repository21 other files it gives its agents.
- AGENTS.mdAGENTS.md
- add-knowledgeSkill
- build-tool-integrationSkill
- create-agentSkill
- embed-web-widgetSkill
- get-phone-numberSkill
- handle-inbound-callsSkill
- iterate-on-agentSkill
- migrate-from-elevenlabsSkill
- migrate-from-retellSkill
- migrate-from-vapiSkill
- place-outbound-callsSkill
- run-campaignSkill
- setup-api-keySkill
- setup-webhooksSkill
- test-agentSkill
- thunderphone-mcp-setupSkill
- thunderphone-prompt-builderSkill
- use-with-livekitSkill
- use-with-openai-realtimeSkill
- use-with-pipecatSkill
The file
We split this skill into the rules it gives an agent
6 rules. About 0 are common, 3 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 16
Choose a protected import mode: Use api_key only with authorized Bland access, or paste with a permitted export.
- Very specific: line 53
Poll and review items: Read GET /v1/agent-imports/{public_id} until the item list is ready.
- Very specific: line 63
Test matching paths: Use test-agent to traverse the same source pathway cases and ThunderPhone outcomes.
- Distinctive: line 82
Use import agents and agent imports.
- Distinctive: line 83
Never expose source credentials or infer phone-number transfer from agent creation.
- Distinctive: line 85
Treat pathway conversion as behavior migration, not text copying.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Migrate from Bland
- Inventory the source. Export pathways/agents, nodes, prompts, numbers, tools, webhooks, credentials, traffic, and test cases. Record source versions before changing either platform.
- Choose a protected import mode. Use
api_keyonly with authorized Bland access, orpastewith a permitted export. Never persist source credentials in the import file or conversation. - Create the job at
POST /v1/agent-importswithsource: bland.
{
"source": "bland",
"auth_mode": "paste",
"payload": "${EXPORTED_AGENT_JSON}"
}curl --fail-with-body -X POST https://api.thunderphone.com/v1/agent-imports \
-H "Authorization: Bearer $THUNDERPHONE_API_KEY" -H "Content-Type: application/json" \
-H "X-ThunderPhone-Client: skills/migrate-from-bland@1.0" --data-binary @bland-import.jsonimport json, os, requests
with open("bland-import.json", encoding="utf-8") as f: payload = json.load(f)
r = requests.post("https://api.thunderphone.com/v1/agent-imports", json=payload,
headers={"Authorization": f"Bearer {os.environ['THUNDERPHONE_API_KEY']}",
"X-ThunderPhone-Client": "skills/migrate-from-bland@1.0"}, timeout=60)
r.raise_for_status(); print(r.json())import { readFile } from "node:fs/promises";
const r = await fetch("https://api.thunderphone.com/v1/agent-imports", { method: "POST",
headers: { Authorization: `Bearer ${process.env.THUNDERPHONE_API_KEY}`,
"Content-Type": "application/json", "X-ThunderPhone-Client": "skills/migrate-from-bland@1.0" },
body: await readFile("bland-import.json", "utf8") });
if (!r.ok) throw new Error(await r.text()); console.log(await r.json());- Poll and review items. Read
GET /v1/agent-imports/{public_id}until the item list is ready. Select and correct items withPATCH /v1/agent-imports/{public_id}/items/{item_id}. - Review mapping. Prompt, first message, language, model, voice, supported tools, pathway-node content, and maximum duration can map. Owned numbers, webhooks, credentials, and unsupported pathway behavior need manual work. See references/bland-mapping.md.
- Commit reviewed selections with
POST /v1/agent-imports/{public_id}/commit, poll to terminal, and record all created agent IDs. Delete an unwanted job before commit. - Test matching paths. Use
test-agentto traverse the same source pathway cases and ThunderPhone outcomes. Compare facts, branch outcomes, tools, transfer/end behavior, language, audio, and error recovery. Keep live number cutover separate and reversible. - Use the current price index at
https://thunderphone.com/data/voice-ai-price-index.json; do not invent comparison figures.
Errors
| Symptom | Cause | Fix |
| Pathway nodes collapse incorrectly | Source graph has unsupported or ambiguous semantics | Reconstruct the intent as general prompt/tool rules and test every path. |
| Agent imports without its number | Numbers are separate manual assets | Provision/connect and verify the number in a separate cutover plan. |
| Source webhooks stop working | Vendor endpoint assumptions were copied incompletely | Rebuild signed ThunderPhone webhooks and test deliveries before cutover. |
| Commit creates only some agents | Some review items were unselected or invalid | Inspect item states and errors; do not repeat the whole import blindly. |
Source and safety rules
- Use import agents and agent imports.
- Never expose source credentials or infer phone-number transfer from agent creation.
- Preserve source configuration and traffic until side-by-side evidence and rollback exist.
- Treat pathway conversion as behavior migration, not text copying.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

