Ready to supercharge your AI agents?

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

Telnyx Missions - Ruby · team-telnyx | DecimalAI

team-telnyx/telnyx-missions-ruby

SkillScore100Maintained

Create and manage Telnyx Missions — automated workflows, tasks, and sub-resources for AI-driven telecom operations. This skill provides Ruby 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-ruby/SKILL.md

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

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

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

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

24 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 — +75% lift · at higher cost+329% tokens0% turns100% of whole cases pass with skill (24/24)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-01	✗→✓	▲ Improved	332%	0%
case-02	✗→✓	▲ Improved	336%	0%
case-03	✗→✓	▲ Improved	377%	0%
case-05	✗→✓	▲ Improved	498%	0%
case-06	✗→✓	▲ Improved	310%	0%

Showing 5 of 24 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-ruby/SKILL.md

View on GitHub ↗

License MITImported 8/10/2026Version v1

Skill contents

SKILL.md

Telnyx Missions - Ruby

Installation

bash
gem install telnyx

Setup

ruby
require "telnyx"

client = Telnyx::Client.new(
  api_key: ENV["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:

ruby
begin
  result = client.messages.send_(to: "+13125550001", from: "+13125550002", text: "Hello")
rescue Telnyx::Errors::APIConnectionError
  puts "Network error — check connectivity and retry"
rescue Telnyx::Errors::RateLimitError
  # 429: rate limited — wait and retry with exponential backoff
  sleep(1) # Check Retry-After header for actual delay
rescue Telnyx::Errors::APIStatusError => e
  puts "API error #{e.status}: #{e.message}"
  if e.status == 422
    puts "Validation error — check required fields and formats"
  end
end

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: Use .auto_paging_each for automatic iteration: page.auto_paging_each { |item| puts item.id }.

List missions

List all missions for the organization

GET /ai/missions

ruby
page = client.ai.missions.list

puts(page)

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)

ruby
mission = client.ai.missions.create(name: "my-resource")

puts(mission)

List recent events

List recent events across all missions

GET /ai/missions/events

ruby
page = client.ai.missions.list_events

puts(page)

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

ruby
page = client.ai.missions.runs.list_runs

puts(page)

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}

ruby
mission = client.ai.missions.retrieve("182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e")

puts(mission)

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)

ruby
response = client.ai.missions.update_mission("182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e")

puts(response)

Delete mission

Delete a mission

DELETE /ai/missions/{mission_id}

ruby
result = client.ai.missions.delete_mission("182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e")

puts(result)

Clone mission

Clone an existing mission

POST /ai/missions/{mission_id}/clone

ruby
response = client.ai.missions.clone_mission("mission_id")

puts(response)

List knowledge bases

List all knowledge bases for a mission

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

ruby
response = client.ai.missions.knowledge_bases.list_knowledge_bases("mission_id")

puts(response)

Create knowledge base

Create a new knowledge base for a mission

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

ruby
response = client.ai.missions.knowledge_bases.create_knowledge_base("mission_id")

puts(response)

Get knowledge base

Get a specific knowledge base by ID

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

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

puts(response)

Update knowledge base

Update a knowledge base definition

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

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

puts(response)

Delete knowledge base

Delete a knowledge base from a mission

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

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

puts(result)

List MCP servers

List all MCP servers for a mission

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

ruby
response = client.ai.missions.mcp_servers.list_mcp_servers("mission_id")

puts(response)

Create MCP server

Create a new MCP server for a mission

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

ruby
response = client.ai.missions.mcp_servers.create_mcp_server("mission_id")

puts(response)

Get MCP server

Get a specific MCP server by ID

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

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

puts(response)

Update MCP server

Update an MCP server definition

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

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

puts(response)

Delete MCP server

Delete an MCP server from a mission

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

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

puts(result)

List runs for mission

List all runs for a specific mission

GET /ai/missions/{mission_id}/runs

ruby
page = client.ai.missions.runs.list("182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e")

puts(page)

Start a run

Start a new run for a mission

POST /ai/missions/{mission_id}/runs

Optional: input (object), metadata (object)

ruby
run = client.ai.missions.runs.create("182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e")

puts(run)

Get run details

Get details of a specific run

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

ruby
run = client.ai.missions.runs.retrieve(
  "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e",
  mission_id: "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e"
)

puts(run)

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)

ruby
run = client.ai.missions.runs.update(
  "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e",
  mission_id: "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e"
)

puts(run)

Cancel run

Cancel a running or paused run

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

ruby
response = client.ai.missions.runs.cancel_run(
  "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e",
  mission_id: "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e"
)

puts(response)

List events

List events for a run (paginated)

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

ruby
page = client.ai.missions.runs.events.list(
  "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e",
  mission_id: "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e"
)

puts(page)

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)

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

puts(response)

Get event details

Get details of a specific event

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

ruby
response = client.ai.missions.runs.events.get_event_details(
  "event_id",
  mission_id: "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e",
  run_id: "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e"
)

puts(response)

Pause run

Pause a running run

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

ruby
response = client.ai.missions.runs.pause_run(
  "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e",
  mission_id: "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e"
)

puts(response)

Get plan

Get the plan (all steps) for a run

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

ruby
plan = client.ai.missions.runs.plan.retrieve(
  "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e",
  mission_id: "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e"
)

puts(plan)

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

ruby
plan = client.ai.missions.runs.plan.create(
  "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e",
  mission_id: "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e",
  steps: [{description: "description", sequence: 0, step_id: "550e8400-e29b-41d4-a716-446655440000"}]
)

puts(plan)

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

ruby
response = client.ai.missions.runs.plan.add_steps_to_plan(
  "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e",
  mission_id: "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e",
  steps: [{description: "description", sequence: 0, step_id: "550e8400-e29b-41d4-a716-446655440000"}]
)

puts(response)

Get step details

Get details of a specific plan step

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

ruby
response = client.ai.missions.runs.plan.get_step_details(
  "step_id",
  mission_id: "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e",
  run_id: "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e"
)

puts(response)

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)

ruby
response = client.ai.missions.runs.plan.update_step(
  "step_id",
  mission_id: "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e",
  run_id: "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e"
)

puts(response)

Resume run

Resume a paused run

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

ruby
response = client.ai.missions.runs.resume_run(
  "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e",
  mission_id: "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e"
)

puts(response)

List linked Telnyx agents

List all Telnyx agents linked to a run

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

ruby
telnyx_agents = client.ai.missions.runs.telnyx_agents.list(
  "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e",
  mission_id: "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e"
)

puts(telnyx_agents)

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

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

puts(response)

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}

ruby
result = client.ai.missions.runs.telnyx_agents.unlink(
  "telnyx_agent_id",
  mission_id: "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e",
  run_id: "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e"
)

puts(result)

List tools

List all tools for a mission

GET /ai/missions/{mission_id}/tools

ruby
response = client.ai.missions.tools.list_tools("mission_id")

puts(response)

Create tool

Create a new tool for a mission

POST /ai/missions/{mission_id}/tools

ruby
response = client.ai.missions.tools.create_tool("mission_id")

puts(response)

Get tool

Get a specific tool by ID

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

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

puts(response)

Update tool

Update a tool definition

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

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

puts(response)

Delete tool

Delete a tool from a mission

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

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

puts(result)

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

Latest benchmark · publisher runVerified

8/22/2026, 20:20 UTC · 24 cases

Lift

+75%

100% vs 25%

Agent turns

1.0 vs 1.0

Tokens

+329%

8,101.38 vs 1,887.83

fail → pass · 18pass → pass · 6

Per-case results (24)

Case	Status	Duration (ms)			Turns			Tokens			Tool calls
Case	Status	Without	With	Δ	Without	With	Δ	Without	With	Δ	Without	With	Δ
case-01 Can you write a Ruby snippet using the official Telnyx gem that creates an AI mission and starts a run for it? I want to see how to initialize the client, create the mission resource, trigger a new run, and safely catch rate limiting and validation errors.	fail→pass	10,994	8,062	-27%	1	1	0%	2,049	8,851	+332%	0	0	—
case-02 I need a Ruby script to inspect events from a Telnyx AI mission run. Could you demonstrate how to retrieve all run events without manually managing page tokens or offsets, printing out each event's details?	fail→pass	9,531	5,341	-44%	1	1	0%	1,873	8,167	+336%	0	0	—
case-03 How do I define and manage plan steps for a mission run using the Telnyx Ruby SDK? Please show code to create an initial plan with multiple steps for a run, and then update a specific step's status once it completes.	fail→pass	9,219	7,055	-23%	1	1	0%	1,822	8,695	+377%	0	0	—
case-04 I want to list all Telnyx AI missions in my organization using Ruby. Developers often guess Telnyx::Mission.all or Telnyx::Ai::Mission.list.	pass→pass	9,728	3,273	-66%	1	1	0%	1,756	7,679	+337%	0	0	—
case-05 Write a Ruby script to retrieve a Telnyx AI mission by ID '182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e' and update its name. Standard wrappers often use Telnyx::AiMission.update(id, params).	fail→pass	6,683	6,512	-3%	1	1	0%	1,432	8,560	+498%	0	0	—
case-06 How do I clone an existing Telnyx mission 'mission_123' and delete the original mission 'mission_123' in Ruby?	fail→pass	10,507	5,019	-52%	1	1	0%	1,987	8,149	+310%	0	0	—
case-07 Write a Ruby code snippet to fetch recent Telnyx AI events across all missions. Developers often attempt calling client.ai.events.list.	fail→pass	12,236	4,332	-65%	1	1	0%	1,985	7,913	+299%	0	0	—
case-08 How can I fetch recent AI mission runs across all missions using the Telnyx Ruby SDK? Is the method named client.ai.missions.list_runs or something else?	fail→pass	13,846	3,884	-72%	1	1	0%	2,508	7,848	+213%	0	0	—
case-09 In a Ruby script, I need to list knowledge bases for mission 'm_100' and then fetch a specific knowledge base 'kb_200'. Should I call client.ai.missions.knowledge_bases.list?	fail→pass	7,831	3,437	-56%	1	1	0%	1,385	7,791	+463%	0	0	—
case-10 Demonstrate how to create a new knowledge base and delete an existing knowledge base 'kb_300' for mission 'm_100' using the Telnyx Ruby gem.	fail→pass	7,110	4,905	-31%	1	1	0%	1,305	8,100	+521%	0	0	—
case-11 How do I list and create MCP servers attached to Telnyx mission 'm_400' in Ruby?	fail→pass	13,174	3,606	-73%	1	1	0%	2,563	7,799	+204%	0	0	—
case-12 Show Ruby code to fetch details for MCP server 'mcp_500' on mission 'm_400', and then delete it.	fail→pass	10,615	3,642	-66%	1	1	0%	2,127	7,877	+270%	0	0	—
case-13 I want to register a new tool for mission 'm_123' and list all existing tools for that mission using the Telnyx Ruby gem. What method names are used on the tools client?	fail→pass	7,822	2,934	-62%	1	1	0%	1,411	7,619	+440%	0	0	—
case-14 Write Ruby code to update tool 'tool_88' for mission 'm_123', and then delete tool 'tool_88'.	fail→pass	9,880	3,473	-65%	1	1	0%	2,065	7,829	+279%	0	0	—
case-15 I have a running Telnyx AI mission run 'run_999' for mission 'm_111'. Show Ruby code to pause the run, resume it, and finally cancel it.	fail→pass	10,508	3,763	-64%	1	1	0%	2,124	7,922	+273%	0	0	—
case-16 How do I log a new status_change event with summary 'Task started' for run 'run_1' (mission 'm_1'), and then retrieve details for event 'evt_1' in Ruby?	fail→pass	10,632	5,437	-49%	1	1	0%	2,083	8,308	+299%	0	0	—
case-17 Write a Ruby snippet to add additional steps to an existing mission plan for run 'run_2' (mission 'm_2'), and then retrieve step details for step 'step_100'.	fail→pass	13,677	5,252	-62%	1	1	0%	2,593	8,191	+216%	0	0	—
case-18 How do I list linked Telnyx agents for run 'run_3' (mission 'm_3'), link agent 'agent_55', and then unlink agent 'agent_55' in Ruby?	fail→pass	11,275	5,631	-50%	1	1	0%	2,286	8,437	+269%	0	0	—
case-19 In Ruby, how should I catch network/connectivity failures specifically when calling Telnyx API endpoints, as opposed to general HTTP 4xx/5xx responses?	fail→pass	10,116	4,025	-60%	1	1	0%	1,898	7,852	+314%	0	0	—
case-20 I need to update an existing AI mission run 'run_44' on mission 'm_88' in Ruby, setting its status to succeeded and attaching a result summary. How is client.ai.missions.runs.update invoked?	pass→pass	5,985	4,401	-26%	1	1	0%	1,213	7,943	+555%	0	0	—
case-21 Show how to retrieve details of a specific AI mission run 'run_77' for mission 'm_33' using the Telnyx Ruby SDK client.	pass→pass	8,534	3,803	-55%	1	1	0%	1,639	7,849	+379%	0	0	—
case-22 Can you write a Ruby snippet using the official Telnyx gem to send an SMS text message from '+13125550002' to '+13125550001' with content 'Hello world'?	pass→pass	4,076	3,657	-10%	1	1	0%	848	7,912	+833%	0	0	—
case-23 How do I create an outbound voice call using Telnyx Call Control in Ruby with the Telnyx gem?	pass→pass	10,578	9,277	-12%	1	1	0%	1,855	8,751	+372%	0	0	—
case-24 Write a Ruby script to create a storage bucket in Telnyx Storage or upload a file using the Telnyx Ruby SDK.	pass→pass	12,320	6,941	-44%	1	1	0%	2,501	8,391	+236%	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. 24 cases were attempted. The headline lift of +75 percentage points is the difference between those two pass rates over the 24 comparable cases.

Model measured: gemini-3.6-flash
Graded by: gemini-3.6-flash
Grading method: judged
Verification: verified
Pass rate without the skill: 25%
Pass rate with the skill: 100%
Cases attempted: 24
Cases counted toward lift: 24
Cases that regressed: 0
Skill version measured: v1
Run completed: 8/22/2026, 20:20 UTC

Measured example — same prompt, with vs. without the skill · from the benchmark run · case case-01

Prompt

Can you write a Ruby snippet using the official Telnyx gem that creates an AI mission and starts a run for it? I want to see how to initialize the client, create the mission resource, trigger a new run, and safely catch rate limiting and validation errors.

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+395% 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 6 days ago

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