Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Telnyx Missions - Python · team-telnyx | DecimalAI

team-telnyx/telnyx-missions-python

SkillScore100Maintained

Create and manage Telnyx Missions — automated workflows, tasks, and sub-resources for AI-driven telecom operations. This skill provides Python SDK examples.

codingby team-telnyx

Links this skill to your agents and keeps it current with the author’s updates.

Automatic

AI Engineer pack

1 · One-time — install the CLI (docs ↗)

pip install decimalai

2 · Get the skill — writes .claude/skills/team-telnyx-telnyx-missions-python/SKILL.md

decimalai skills pull team-telnyx-telnyx-missions-python --out .claude/skills/

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/team-telnyx-telnyx-missions-python/SKILL.md https://app.decimal.ai/s/team-telnyx-telnyx-missions-python/SKILL.md

Raw file: /s/team-telnyx-telnyx-missions-python/SKILL.md ↗ · machine-readable summary at /s/team-telnyx-telnyx-missions-python.json ↗

In productionGlobal

how this skill behaves on real traffic · last 30 days

No production data for this skill yet — usage numbers appear here once agents start running it.

Anonymized aggregate across every org using this skill — proof from real production use, not a demo.

Does this skill help? · Benchmark: with vs. withoutsign in to run this on your agents

25 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 7d ago

Yes — +88% lift · at higher cost+364% tokens0% turns100% of whole cases pass with skill (25/25)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-11	✗→✓	▲ Improved	440%	0%
case-12	✗→✓	▲ Improved	369%	0%
case-02	✗→✓	▲ Improved	208%	0%
case-01	✗→✓	▲ Improved	373%	0%
case-03	✗→✓	▲ Improved	218%	0%

Showing 5 of 25 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

team-telnyx / ai

skills/telnyx-missions-python/SKILL.md

View on GitHub ↗

License MITImported 8/10/2026Version v1

Skill contents

SKILL.md

Telnyx Missions - Python

Installation

bash
pip install telnyx

Setup

python
import os
from telnyx import Telnyx

client = Telnyx(
    api_key=os.environ.get("TELNYX_API_KEY"),  # This is the default and can be omitted
)

All examples below assume client is already initialized as shown above.

Error Handling

All API calls can fail with network errors, rate limits (429), validation errors (422), or authentication errors (401). Always handle errors in production code:

python
import telnyx

try:
    result = client.messages.send(to="+13125550001", from_="+13125550002", text="Hello")
except telnyx.APIConnectionError:
    print("Network error — check connectivity and retry")
except telnyx.RateLimitError:
    # 429: rate limited — wait and retry with exponential backoff
    import time
    time.sleep(1)  # Check Retry-After header for actual delay
except telnyx.APIStatusError as e:
    print(f"API error {e.status_code}: {e.message}")
    if e.status_code == 422:
        print("Validation error — check required fields and formats")

Common error codes: 401 invalid API key, 403 insufficient permissions, 404 resource not found, 422 validation error (check field formats), 429 rate limited (retry with exponential backoff).

Important Notes

Pagination: List methods return an auto-paginating iterator. Use for item in page_result: to iterate through all pages automatically.

List missions

List all missions for the organization

GET /ai/missions

python
page = client.ai.missions.list()
page = page.data[0]
print(page.mission_id)

Returns: created_at (date-time), description (string), execution_mode (enum: external, managed), instructions (string), metadata (object), mission_id (uuid), model (string), name (string), updated_at (date-time)

Create mission

Create a new mission definition

POST /ai/missions — Required: name

Optional: description (string), execution_mode (enum: external, managed), instructions (string), metadata (object), model (string)

python
mission = client.ai.missions.create(
    name="my-resource",
)
print(mission.data)

List recent events

List recent events across all missions

GET /ai/missions/events

python
page = client.ai.missions.list_events()
page = page.data[0]
print(page.event_id)

Returns: agent_id (string), event_id (string), idempotency_key (string), payload (object), run_id (string), step_id (string), summary (string), timestamp (date-time), type (enum: status_change, step_started, step_completed, step_failed, tool_call, tool_result, message, error, custom)

List recent runs

List recent runs across all missions

GET /ai/missions/runs

python
page = client.ai.missions.runs.list_runs()
page = page.data[0]
print(page.mission_id)

Returns: error (string), finished_at (date-time), input (object), metadata (object), mission_id (uuid), result_payload (object), result_summary (string), run_id (uuid), started_at (date-time), status (enum: pending, running, paused, succeeded, failed, cancelled), updated_at (date-time)

Get mission

Get a mission by ID (includes tools, knowledge_bases, mcp_servers)

GET /ai/missions/{mission_id}

python
mission = client.ai.missions.retrieve(
    "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e",
)
print(mission.data)

Update mission

Update a mission definition

PUT /ai/missions/{mission_id}

Optional: description (string), execution_mode (enum: external, managed), instructions (string), metadata (object), model (string), name (string)

python
response = client.ai.missions.update_mission(
    mission_id="182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e",
)
print(response.data)

Delete mission

Delete a mission

DELETE /ai/missions/{mission_id}

python
client.ai.missions.delete_mission(
    "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e",
)

Clone mission

Clone an existing mission

POST /ai/missions/{mission_id}/clone

python
response = client.ai.missions.clone_mission(
    "mission_id",
)
print(response)

List knowledge bases

List all knowledge bases for a mission

GET /ai/missions/{mission_id}/knowledge-bases

python
response = client.ai.missions.knowledge_bases.list_knowledge_bases(
    "mission_id",
)
print(response)

Create knowledge base

Create a new knowledge base for a mission

POST /ai/missions/{mission_id}/knowledge-bases

python
response = client.ai.missions.knowledge_bases.create_knowledge_base(
    "mission_id",
)
print(response)

Get knowledge base

Get a specific knowledge base by ID

GET /ai/missions/{mission_id}/knowledge-bases/{knowledge_base_id}

python
response = client.ai.missions.knowledge_bases.get_knowledge_base(
    knowledge_base_id="550e8400-e29b-41d4-a716-446655440000",
    mission_id="550e8400-e29b-41d4-a716-446655440000",
)
print(response)

Update knowledge base

Update a knowledge base definition

PUT /ai/missions/{mission_id}/knowledge-bases/{knowledge_base_id}

python
response = client.ai.missions.knowledge_bases.update_knowledge_base(
    knowledge_base_id="550e8400-e29b-41d4-a716-446655440000",
    mission_id="550e8400-e29b-41d4-a716-446655440000",
)
print(response)

Delete knowledge base

Delete a knowledge base from a mission

DELETE /ai/missions/{mission_id}/knowledge-bases/{knowledge_base_id}

python
client.ai.missions.knowledge_bases.delete_knowledge_base(
    knowledge_base_id="550e8400-e29b-41d4-a716-446655440000",
    mission_id="550e8400-e29b-41d4-a716-446655440000",
)

List MCP servers

List all MCP servers for a mission

GET /ai/missions/{mission_id}/mcp-servers

python
response = client.ai.missions.mcp_servers.list_mcp_servers(
    "mission_id",
)
print(response)

Create MCP server

Create a new MCP server for a mission

POST /ai/missions/{mission_id}/mcp-servers

python
response = client.ai.missions.mcp_servers.create_mcp_server(
    "mission_id",
)
print(response)

Get MCP server

Get a specific MCP server by ID

GET /ai/missions/{mission_id}/mcp-servers/{mcp_server_id}

python
response = client.ai.missions.mcp_servers.get_mcp_server(
    mcp_server_id="550e8400-e29b-41d4-a716-446655440000",
    mission_id="550e8400-e29b-41d4-a716-446655440000",
)
print(response)

Update MCP server

Update an MCP server definition

PUT /ai/missions/{mission_id}/mcp-servers/{mcp_server_id}

python
response = client.ai.missions.mcp_servers.update_mcp_server(
    mcp_server_id="550e8400-e29b-41d4-a716-446655440000",
    mission_id="550e8400-e29b-41d4-a716-446655440000",
)
print(response)

Delete MCP server

Delete an MCP server from a mission

DELETE /ai/missions/{mission_id}/mcp-servers/{mcp_server_id}

python
client.ai.missions.mcp_servers.delete_mcp_server(
    mcp_server_id="550e8400-e29b-41d4-a716-446655440000",
    mission_id="550e8400-e29b-41d4-a716-446655440000",
)

List runs for mission

List all runs for a specific mission

GET /ai/missions/{mission_id}/runs

python
page = client.ai.missions.runs.list(
    mission_id="182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e",
)
page = page.data[0]
print(page.mission_id)

Start a run

Start a new run for a mission

POST /ai/missions/{mission_id}/runs

Optional: input (object), metadata (object)

python
run = client.ai.missions.runs.create(
    mission_id="182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e",
)
print(run.data)

Get run details

Get details of a specific run

GET /ai/missions/{mission_id}/runs/{run_id}

python
run = client.ai.missions.runs.retrieve(
    run_id="182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e",
    mission_id="182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e",
)
print(run.data)

Update run

Update run status and/or result

PATCH /ai/missions/{mission_id}/runs/{run_id}

Optional: error (string), metadata (object), result_payload (object), result_summary (string), status (enum: pending, running, paused, succeeded, failed, cancelled)

python
run = client.ai.missions.runs.update(
    run_id="182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e",
    mission_id="182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e",
)
print(run.data)

Cancel run

Cancel a running or paused run

POST /ai/missions/{mission_id}/runs/{run_id}/cancel

python
response = client.ai.missions.runs.cancel_run(
    run_id="182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e",
    mission_id="182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e",
)
print(response.data)

List events

List events for a run (paginated)

GET /ai/missions/{mission_id}/runs/{run_id}/events

python
page = client.ai.missions.runs.events.list(
    run_id="182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e",
    mission_id="182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e",
)
page = page.data[0]
print(page.event_id)

Log event

Log an event for a run

POST /ai/missions/{mission_id}/runs/{run_id}/events — Required: type, summary

Optional: agent_id (string), idempotency_key (string), payload (object), step_id (string)

python
response = client.ai.missions.runs.events.log(
    run_id="182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e",
    mission_id="182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e",
    summary="Brief task summary",
    type="status_change",
)
print(response.data)

Get event details

Get details of a specific event

GET /ai/missions/{mission_id}/runs/{run_id}/events/{event_id}

python
response = client.ai.missions.runs.events.get_event_details(
    event_id="550e8400-e29b-41d4-a716-446655440000",
    mission_id="182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e",
    run_id="182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e",
)
print(response.data)

Pause run

Pause a running run

POST /ai/missions/{mission_id}/runs/{run_id}/pause

python
response = client.ai.missions.runs.pause_run(
    run_id="182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e",
    mission_id="182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e",
)
print(response.data)

Get plan

Get the plan (all steps) for a run

GET /ai/missions/{mission_id}/runs/{run_id}/plan

python
plan = client.ai.missions.runs.plan.retrieve(
    run_id="182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e",
    mission_id="182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e",
)
print(plan.data)

Returns: completed_at (date-time), description (string), metadata (object), parent_step_id (string), run_id (uuid), sequence (integer), started_at (date-time), status (enum: pending, in_progress, completed, skipped, failed), step_id (string)

Create initial plan

Create the initial plan for a run

POST /ai/missions/{mission_id}/runs/{run_id}/plan — Required: steps

python
plan = client.ai.missions.runs.plan.create(
    run_id="182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e",
    mission_id="182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e",
    steps=[{
        "description": "description",
        "sequence": 0,
        "step_id": "step_id",
    }],
)
print(plan.data)

Add step(s) to plan

Add one or more steps to an existing plan

POST /ai/missions/{mission_id}/runs/{run_id}/plan/steps — Required: steps

python
response = client.ai.missions.runs.plan.add_steps_to_plan(
    run_id="182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e",
    mission_id="182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e",
    steps=[{
        "description": "description",
        "sequence": 0,
        "step_id": "step_id",
    }],
)
print(response.data)

Get step details

Get details of a specific plan step

GET /ai/missions/{mission_id}/runs/{run_id}/plan/steps/{step_id}

python
response = client.ai.missions.runs.plan.get_step_details(
    step_id="550e8400-e29b-41d4-a716-446655440000",
    mission_id="182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e",
    run_id="182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e",
)
print(response.data)

Update step status

Update the status of a plan step

PATCH /ai/missions/{mission_id}/runs/{run_id}/plan/steps/{step_id}

Optional: metadata (object), status (enum: pending, in_progress, completed, skipped, failed)

python
response = client.ai.missions.runs.plan.update_step(
    step_id="550e8400-e29b-41d4-a716-446655440000",
    mission_id="182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e",
    run_id="182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e",
)
print(response.data)

Resume run

Resume a paused run

POST /ai/missions/{mission_id}/runs/{run_id}/resume

python
response = client.ai.missions.runs.resume_run(
    run_id="182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e",
    mission_id="182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e",
)
print(response.data)

List linked Telnyx agents

List all Telnyx agents linked to a run

GET /ai/missions/{mission_id}/runs/{run_id}/telnyx-agents

python
telnyx_agents = client.ai.missions.runs.telnyx_agents.list(
    run_id="182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e",
    mission_id="182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e",
)
print(telnyx_agents.data)

Returns: created_at (date-time), run_id (string), telnyx_agent_id (string)

Link Telnyx agent to run

Link a Telnyx AI agent (voice/messaging) to a run

POST /ai/missions/{mission_id}/runs/{run_id}/telnyx-agents — Required: telnyx_agent_id

python
response = client.ai.missions.runs.telnyx_agents.link(
    run_id="182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e",
    mission_id="182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e",
    telnyx_agent_id="550e8400-e29b-41d4-a716-446655440000",
)
print(response.data)

Returns: created_at (date-time), run_id (string), telnyx_agent_id (string)

Unlink Telnyx agent

Unlink a Telnyx agent from a run

DELETE /ai/missions/{mission_id}/runs/{run_id}/telnyx-agents/{telnyx_agent_id}

python
client.ai.missions.runs.telnyx_agents.unlink(
    telnyx_agent_id="550e8400-e29b-41d4-a716-446655440000",
    mission_id="182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e",
    run_id="182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e",
)

List tools

List all tools for a mission

GET /ai/missions/{mission_id}/tools

python
response = client.ai.missions.tools.list_tools(
    "mission_id",
)
print(response)

Create tool

Create a new tool for a mission

POST /ai/missions/{mission_id}/tools

python
response = client.ai.missions.tools.create_tool(
    "mission_id",
)
print(response)

Get tool

Get a specific tool by ID

GET /ai/missions/{mission_id}/tools/{tool_id}

python
response = client.ai.missions.tools.get_tool(
    tool_id="550e8400-e29b-41d4-a716-446655440000",
    mission_id="550e8400-e29b-41d4-a716-446655440000",
)
print(response)

Update tool

Update a tool definition

PUT /ai/missions/{mission_id}/tools/{tool_id}

python
response = client.ai.missions.tools.update_tool(
    tool_id="550e8400-e29b-41d4-a716-446655440000",
    mission_id="550e8400-e29b-41d4-a716-446655440000",
)
print(response)

Delete tool

Delete a tool from a mission

DELETE /ai/missions/{mission_id}/tools/{tool_id}

python
client.ai.missions.tools.delete_tool(
    tool_id="550e8400-e29b-41d4-a716-446655440000",
    mission_id="550e8400-e29b-41d4-a716-446655440000",
)

Want to see if team-telnyx/telnyx-missions-python would activate on your phrasing? Try it before you install — no LLM call, no signup.

Latest benchmark · publisher runVerified

8/22/2026, 09:36 UTC · 25 cases

Lift

+88%

100% vs 12%

Agent turns

1.0 vs 1.0

Tokens

+364%

8,787.44 vs 1,893.12

fail → pass · 22pass → pass · 3

Per-case results (25)

Case	Status	Duration (ms)			Turns			Tokens			Tool calls
Case	Status	Without	With	Δ	Without	With	Δ	Without	With	Δ	Without	With	Δ
case-11 Write a Python snippet using the Telnyx SDK to clone an existing mission using mission ID '182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e'.	fail→pass	7,980	3,084	-61%	1	1	0%	1,545	8,340	+440%	0	0	—
case-12 Write a Python snippet using the Telnyx client to list all knowledge bases associated with mission ID '182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e'.	fail→pass	8,780	3,513	-60%	1	1	0%	1,804	8,452	+369%	0	0	—
case-02 Create a Python utility function using the Telnyx SDK to log structured run events and update step statuses in a mission's plan, incorporating error handling for network issues and HTTP status codes like 429 or 422.	fail→pass	17,028	11,787	-31%	1	1	0%	3,375	10,399	+208%	0	0	—
case-01 Write a Python script using the Telnyx SDK that creates a mission named 'support-agent' with custom instructions, initiates a run for that mission, and sets up an initial plan containing a sequence of steps.	fail→pass	15,123	9,280	-39%	1	1	0%	2,053	9,712	+373%	0	0	—
case-03 Develop a Python script that uses the Telnyx client to list all recent mission runs across the account, iterate through pages, and conditionally resume or cancel runs depending on their current status.	fail→pass	16,404	15,106	-8%	1	1	0%	3,155	10,035	+218%	0	0	—
case-04 Write a Python snippet using the Telnyx SDK to send a text message from '+13125550002' to '+13125550001' saying 'Hello World'.	fail→pass	3,941	3,675	-7%	1	1	0%	773	8,438	+992%	0	0	—
case-05 Write a Python snippet using the Telnyx SDK to initiate an outbound call from '+13125550002' to '+13125550001' using a connection ID '123456'.	fail→pass	14,962	5,136	-66%	1	1	0%	948	8,767	+825%	0	0	—
case-06 Write a Python snippet using the Telnyx SDK to generate text embeddings for the string 'customer inquiry' using the 'Mistral-7B' model.	fail→pass	5,033	5,496	+9%	1	1	0%	874	8,791	+906%	0	0	—
case-07 Write a Python snippet to fetch all defined missions in a Telnyx organization using the SDK and print the mission_id of the first mission.	fail→pass	6,294	3,330	-47%	1	1	0%	1,180	8,360	+608%	0	0	—
case-08 Write a Python script using the Telnyx client to retrieve details for a specific mission with ID '182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e'.	fail→pass	8,428	3,880	-54%	1	1	0%	1,595	8,591	+439%	0	0	—
case-09 Write a Python snippet using the Telnyx client to update an existing mission's definition for mission ID '182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e'.	fail→pass	8,977	3,947	-56%	1	1	0%	1,583	8,585	+442%	0	0	—
case-10 Write a Python script using the Telnyx SDK to remove a mission with ID '182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e'.	fail→pass	7,286	3,272	-55%	1	1	0%	1,450	8,415	+480%	0	0	—
case-13 Write a Python function using the Telnyx SDK to fetch details for a knowledge base ID '550e8400-e29b-41d4-a716-446655440000' belonging to mission ID '182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e'.	fail→pass	10,176	17,917	+76%	1	1	0%	2,030	8,662	+327%	0	0	—
case-14 Write a Python script using the Telnyx SDK to retrieve all MCP servers configured under mission ID '182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e'.	fail→pass	19,868	3,798	-81%	1	1	0%	1,965	8,561	+336%	0	0	—
case-15 Write a Python snippet using the Telnyx SDK to remove MCP server '550e8400-e29b-41d4-a716-446655440000' from mission '182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e'.	fail→pass	8,811	2,839	-68%	1	1	0%	1,781	8,402	+372%	0	0	—
case-16 Write a Python script using the Telnyx client to list runs for mission ID '182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e'.	pass→pass	9,065	3,753	-59%	1	1	0%	1,866	8,568	+359%	0	0	—
case-17 Write a Python snippet using the Telnyx SDK to retrieve run details for run ID '990e8400-e29b-41d4-a716-446655440000' under mission ID '182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e'.	pass→pass	11,625	2,872	-75%	1	1	0%	2,490	8,435	+239%	0	0	—
case-18 Write a Python script using the Telnyx SDK to pause an active run with ID '990e8400-e29b-41d4-a716-446655440000' on mission ID '182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e'.	fail→pass	10,944	4,626	-58%	1	1	0%	2,225	8,749	+293%	0	0	—
case-19 Write a Python snippet using the Telnyx SDK to list all events logged for run ID '990e8400-e29b-41d4-a716-446655440000' under mission ID '182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e'.	pass→pass	11,398	3,628	-68%	1	1	0%	2,376	8,568	+261%	0	0	—
case-20 Write a Python code snippet using the Telnyx client to inspect details of event ID '770e8400-e29b-41d4-a716-446655440000' belonging to run ID '990e8400-e29b-41d4-a716-446655440000' in mission ID '182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e'.	fail→pass	8,028	4,105	-49%	1	1	0%	1,729	8,702	+403%	0	0	—
case-21 Write a Python snippet using the Telnyx SDK to append new steps to an existing plan for run ID '990e8400-e29b-41d4-a716-446655440000' under mission ID '182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e'.	fail→pass	8,725	3,647	-58%	1	1	0%	1,771	8,613	+386%	0	0	—
case-22 Write a Python function using the Telnyx client to retrieve details of plan step ID 'step-123' for run ID '990e8400-e29b-41d4-a716-446655440000' in mission ID '182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e'.	fail→pass	9,640	4,072	-58%	1	1	0%	1,937	8,677	+348%	0	0	—
case-23 Write a Python snippet using the Telnyx client to link a Telnyx AI voice agent with agent ID 'agent-555' to a run ID '990e8400-e29b-41d4-a716-446655440000' under mission ID '182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e'.	fail→pass	11,229	4,460	-60%	1	1	0%	2,167	8,864	+309%	0	0	—
case-24 Write a Python script using the Telnyx SDK to remove a linked Telnyx agent 'agent-555' from run ID '990e8400-e29b-41d4-a716-446655440000' under mission ID '182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e'.	fail→pass	12,363	4,888	-60%	1	1	0%	2,519	8,918	+254%	0	0	—
case-25 Write a Python function using the Telnyx SDK to list all tools for mission '182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e' and then fetch details for tool ID 'tool-888'.	fail→pass	10,559	6,327	-40%	1	1	0%	2,137	9,082	+325%	0	0	—

These cases were also screened by the skill’s intent / safety pass.See the Trust review ↗Reproduce this benchmark in Colab ↗

How this skill was measured

DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 25 cases were attempted. The headline lift of +88 percentage points is the difference between those two pass rates over the 25 comparable cases.

Model measured: gemini-3.6-flash
Graded by: gemini-3.6-flash
Grading method: judged
Verification: verified
Pass rate without the skill: 12%
Pass rate with the skill: 100%
Cases attempted: 25
Cases counted toward lift: 25
Cases that regressed: 0
Skill version measured: v1
Run completed: 8/22/2026, 09:36 UTC

Measured example — same prompt, with vs. without the skill · from the benchmark run · case case-11

Prompt

Write a Python snippet using the Telnyx SDK to clone an existing mission using mission ID '182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e'.

Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.

Show both answers

SkillScore blends 4 signals1 of 4 complete

BenchmarkPass rate WITH skill on a verified run100

Live evalNeeds ≥20 evaluated traces in 30 days

AI ratingNeeds ≥10 rated traces

AdoptionNeeds ≥10 serves across ≥2 orgs in 30 days

Efficiency · separate axis (at equal correctness)+0% turns+280% tokens

Shown for transparency; not credited unless a verified run shows no correctness regression.

Backed by 1 of 4 signals — each added signal makes the score more robust.

Verified on gemini-3.6-flash · re-tested 7 days ago

Other measured skills in the registry, with their headline benchmark lift.