Ready to supercharge your AI agents?

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

Telnyx Missions - JavaScript · team-telnyx | DecimalAI

team-telnyx/telnyx-missions-javascript

SkillScore100Maintained

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

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

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

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

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

22 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 — +86% lift · at higher cost+371% tokens0% turns100% of whole cases pass with skill (22/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-01	✗→✓	▲ Improved	303%	0%
case-02	✗→✓	▲ Improved	441%	0%
case-03	✗→✓	▲ Improved	250%	0%
case-05	✗→✓	▲ Improved	600%	0%
case-06	✗→✓	▲ Improved	371%	0%

Showing 5 of 22 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/10/2026

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-javascript/SKILL.md

View on GitHub ↗

License MITImported 8/10/2026Version v2

Skill contents

SKILL.md

Telnyx Missions - JavaScript

Installation

bash
npm install telnyx@6.74.2

Setup

javascript
import Telnyx from 'telnyx';

const client = new Telnyx({
  apiKey: process.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:

javascript
try {
  const result = await client.messages.send({ to: '+13125550001', from: '+13125550002', text: 'Hello' });
} catch (err) {
  if (err instanceof Telnyx.APIConnectionError) {
    console.error('Network error — check connectivity and retry');
  } else if (err instanceof Telnyx.RateLimitError) {
    // 429: rate limited — wait and retry with exponential backoff
    const retryAfter = err.headers?.['retry-after'] || 1;
    await new Promise(r => setTimeout(r, retryAfter * 1000));
  } else if (err instanceof Telnyx.APIError) {
    console.error(`API error ${err.status}: ${err.message}`);
    if (err.status === 422) {
      console.error('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 await (const item of result) { ... } to iterate through all pages automatically.

List missions

List all missions for the organization

GET /ai/missions

javascript
// Automatically fetches more pages as needed.
for await (const missionData of client.ai.missions.list()) {
  console.log(missionData.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)

javascript
const mission = await client.ai.missions.create({ name: 'my-resource' });

console.log(mission.data);

List recent events

List recent events across all missions

GET /ai/missions/events

javascript
// Automatically fetches more pages as needed.
for await (const eventData of client.ai.missions.listEvents()) {
  console.log(eventData.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

javascript
// Automatically fetches more pages as needed.
for await (const missionRunData of client.ai.missions.runs.listRuns()) {
  console.log(missionRunData.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}

javascript
const mission = await client.ai.missions.retrieve('182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e');

console.log(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)

javascript
const response = await client.ai.missions.updateMission('182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e');

console.log(response.data);

Delete mission

Delete a mission

DELETE /ai/missions/{mission_id}

javascript
await client.ai.missions.deleteMission('182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e');

Clone mission

Clone an existing mission

POST /ai/missions/{mission_id}/clone

javascript
const response = await client.ai.missions.cloneMission('mission_id');

console.log(response);

List knowledge bases

List all knowledge bases for a mission

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

javascript
const response = await client.ai.missions.knowledgeBases.listKnowledgeBases('mission_id');

console.log(response);

Create knowledge base

Create a new knowledge base for a mission

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

javascript
const response = await client.ai.missions.knowledgeBases.createKnowledgeBase('mission_id');

console.log(response);

Get knowledge base

Get a specific knowledge base by ID

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

javascript
const response = await client.ai.missions.knowledgeBases.getKnowledgeBase('knowledge_base_id', {
  mission_id: '550e8400-e29b-41d4-a716-446655440000',
});

console.log(response);

Update knowledge base

Update a knowledge base definition

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

javascript
const response = await client.ai.missions.knowledgeBases.updateKnowledgeBase('knowledge_base_id', {
  mission_id: '550e8400-e29b-41d4-a716-446655440000',
});

console.log(response);

Delete knowledge base

Delete a knowledge base from a mission

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

javascript
await client.ai.missions.knowledgeBases.deleteKnowledgeBase('knowledge_base_id', {
  mission_id: '550e8400-e29b-41d4-a716-446655440000',
});

List MCP servers

List all MCP servers for a mission

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

javascript
const response = await client.ai.missions.mcpServers.listMcpServers('mission_id');

console.log(response);

Create MCP server

Create a new MCP server for a mission

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

javascript
const response = await client.ai.missions.mcpServers.createMcpServer('mission_id');

console.log(response);

Get MCP server

Get a specific MCP server by ID

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

javascript
const response = await client.ai.missions.mcpServers.getMcpServer('mcp_server_id', {
  mission_id: '550e8400-e29b-41d4-a716-446655440000',
});

console.log(response);

Update MCP server

Update an MCP server definition

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

javascript
const response = await client.ai.missions.mcpServers.updateMcpServer('mcp_server_id', {
  mission_id: '550e8400-e29b-41d4-a716-446655440000',
});

console.log(response);

Delete MCP server

Delete an MCP server from a mission

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

javascript
await client.ai.missions.mcpServers.deleteMcpServer('mcp_server_id', { mission_id: '550e8400-e29b-41d4-a716-446655440000' });

List runs for mission

List all runs for a specific mission

GET /ai/missions/{mission_id}/runs

javascript
// Automatically fetches more pages as needed.
for await (const missionRunData of client.ai.missions.runs.list(
  '182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e',
)) {
  console.log(missionRunData.mission_id);
}

Start a run

Start a new run for a mission

POST /ai/missions/{mission_id}/runs

Optional: input (object), metadata (object)

javascript
const run = await client.ai.missions.runs.create('182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e');

console.log(run.data);

Get run details

Get details of a specific run

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

javascript
const run = await client.ai.missions.runs.retrieve('182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e', {
  mission_id: '182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e',
});

console.log(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)

javascript
const run = await client.ai.missions.runs.update('182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e', {
  mission_id: '182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e',
});

console.log(run.data);

Cancel run

Cancel a running or paused run

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

javascript
const response = await client.ai.missions.runs.cancelRun('182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e', {
  mission_id: '182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e',
});

console.log(response.data);

List events

List events for a run (paginated)

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

javascript
// Automatically fetches more pages as needed.
for await (const eventData of client.ai.missions.runs.events.list(
  '182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e',
  { mission_id: '182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e' },
)) {
  console.log(eventData.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)

javascript
const response = await 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',
});

console.log(response.data);

Get event details

Get details of a specific event

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

javascript
const response = await client.ai.missions.runs.events.getEventDetails('event_id', {
  mission_id: '182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e',
  run_id: '182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e',
});

console.log(response.data);

Pause run

Pause a running run

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

javascript
const response = await client.ai.missions.runs.pauseRun('182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e', {
  mission_id: '182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e',
});

console.log(response.data);

Get plan

Get the plan (all steps) for a run

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

javascript
const plan = await client.ai.missions.runs.plan.retrieve('182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e', {
  mission_id: '182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e',
});

console.log(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

javascript
const plan = await 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',
    },
  ],
});

console.log(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

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

console.log(response.data);

Get step details

Get details of a specific plan step

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

javascript
const response = await client.ai.missions.runs.plan.getStepDetails('step_id', {
  mission_id: '182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e',
  run_id: '182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e',
});

console.log(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)

javascript
const response = await client.ai.missions.runs.plan.updateStep('step_id', {
  mission_id: '182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e',
  run_id: '182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e',
});

console.log(response.data);

Resume run

Resume a paused run

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

javascript
const response = await client.ai.missions.runs.resumeRun('182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e', {
  mission_id: '182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e',
});

console.log(response.data);

List linked Telnyx agents

List all Telnyx agents linked to a run

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

javascript
const telnyxAgents = await client.ai.missions.runs.telnyxAgents.list(
  '182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e',
  { mission_id: '182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e' },
);

console.log(telnyxAgents.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

javascript
const response = await client.ai.missions.runs.telnyxAgents.link(
  '182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e',
  { mission_id: '182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e', telnyx_agent_id: '550e8400-e29b-41d4-a716-446655440000' },
);

console.log(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}

javascript
await client.ai.missions.runs.telnyxAgents.unlink('telnyx_agent_id', {
  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

javascript
const response = await client.ai.missions.tools.listTools('mission_id');

console.log(response);

Create tool

Create a new tool for a mission

POST /ai/missions/{mission_id}/tools

javascript
const response = await client.ai.missions.tools.createTool('mission_id');

console.log(response);

Get tool

Get a specific tool by ID

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

javascript
const response = await client.ai.missions.tools.getTool('tool_id', { mission_id: '550e8400-e29b-41d4-a716-446655440000' });

console.log(response);

Update tool

Update a tool definition

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

javascript
const response = await client.ai.missions.tools.updateTool('tool_id', { mission_id: '550e8400-e29b-41d4-a716-446655440000' });

console.log(response);

Delete tool

Delete a tool from a mission

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

javascript
await client.ai.missions.tools.deleteTool('tool_id', { mission_id: '550e8400-e29b-41d4-a716-446655440000' });

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

Latest benchmark · publisher runVerified

8/22/2026, 20:14 UTC · 22 cases

Lift

+86%

100% vs 14%

Agent turns

1.0 vs 1.0

Tokens

+371%

8,439.55 vs 1,790.77

fail → pass · 19pass → pass · 3

Per-case results (22)

Case	Status	Duration (ms)			Turns			Tokens			Tool calls
Case	Status	Without	With	Δ	Without	With	Δ	Without	With	Δ	Without	With	Δ
case-22 How do I verify a Telnyx webhook signature in an Express request handler using the Telnyx JavaScript SDK?	pass→pass	11,563	11,917	+3%	1	1	0%	2,314	9,827	+325%	0	0	—
case-01 I'm building a backend service in Node.js and need to start a new run for a Telnyx mission using their JavaScript SDK. Could you write a code snippet that triggers the run, logs an initial status event for it, and includes proper try-catch error handling for rate limits and validation failures?	fail→pass	12,504	10,407	-17%	1	1	0%	2,393	9,637	+303%	0	0	—
case-02 Write a JavaScript script using the Telnyx package that loops through all existing events across all AI missions without manually handling page numbers, logging each event's ID to the output.	fail→pass	8,706	5,226	-40%	1	1	0%	1,570	8,490	+441%	0	0	—
case-03 How can I use the Telnyx JavaScript library to create a multi-step plan for a specific mission run? Please give me an example script that sends an array of steps containing descriptions and sequence order.	fail→pass	14,139	6,332	-55%	1	1	0%	2,504	8,756	+250%	0	0	—
case-04 Write a Node.js function using the official Telnyx SDK to list all AI missions in an organization. Iterate over them automatically without manual page tokens.	pass→pass	8,088	4,995	-38%	1	1	0%	1,565	8,350	+434%	0	0	—
case-05 Write a Node.js snippet using the Telnyx library to register a new AI mission titled 'customer-support-agent'.	fail→pass	6,237	3,727	-40%	1	1	0%	1,166	8,164	+600%	0	0	—
case-06 I need to fetch recent runs across all missions in my account using the Telnyx Node.js client. Which method handles auto-paginated global run listing?	fail→pass	9,211	3,029	-67%	1	1	0%	1,692	7,969	+371%	0	0	—
case-07 In Node.js, fetch the full mission payload for mission ID '182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e' using the Telnyx SDK.	fail→pass	9,571	3,760	-61%	1	1	0%	1,916	8,197	+328%	0	0	—
case-08 Show how to update an existing AI mission's properties in Node.js using the Telnyx package.	fail→pass	9,645	4,210	-56%	1	1	0%	1,768	8,270	+368%	0	0	—
case-09 How do I duplicate an existing AI mission with ID 'mish_123' using the Telnyx JavaScript SDK?	fail→pass	10,201	3,048	-70%	1	1	0%	1,892	7,971	+321%	0	0	—
case-10 Write a Node.js snippet using the Telnyx SDK to list all knowledge bases attached to mission 'mish_888'.	fail→pass	8,486	3,441	-59%	1	1	0%	1,556	8,079	+419%	0	0	—
case-11 Write JavaScript code to retrieve knowledge base 'kb_999' for mission '550e8400-e29b-41d4-a716-446655440000' using the Telnyx SDK.	fail→pass	7,171	4,173	-42%	1	1	0%	1,477	8,364	+466%	0	0	—
case-12 I need to fetch all MCP servers registered under Telnyx mission 'mish_456' in JavaScript. What SDK method should I call?	fail→pass	7,542	2,664	-65%	1	1	0%	1,410	7,899	+460%	0	0	—
case-13 Write a JavaScript code snippet using the Telnyx package to auto-paginate through all runs belonging specifically to mission '182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e'.	fail→pass	10,193	4,918	-52%	1	1	0%	1,988	8,539	+330%	0	0	—
case-14 Show how to cancel mission run 'run_abc' for mission '182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e' using the Telnyx JS client.	fail→pass	9,248	5,044	-45%	1	1	0%	1,854	8,574	+362%	0	0	—
case-15 Provide JavaScript code examples using the Telnyx package to pause a running run 'run_100' and then resume it, given mission ID 'mish_100'.	fail→pass	8,527	4,718	-45%	1	1	0%	1,747	8,471	+385%	0	0	—
case-16 How do I link Telnyx agent '550e8400-e29b-41d4-a716-446655440000' to mission run '182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e' in Node.js?	fail→pass	10,756	4,700	-56%	1	1	0%	2,302	8,471	+268%	0	0	—
case-17 Write a JavaScript snippet to fetch all tool definitions configured for mission 'mish_999' using the Telnyx Node.js SDK.	fail→pass	5,735	2,780	-52%	1	1	0%	1,123	7,992	+612%	0	0	—
case-18 How can I append additional steps to an existing execution plan for run 'run_777' on mission 'mish_777' using the Telnyx JavaScript SDK?	fail→pass	10,902	5,578	-49%	1	1	0%	1,965	8,559	+336%	0	0	—
case-19 In Node.js with the Telnyx SDK, how do I update the status of plan step 'step_123' for run 'run_1' and mission 'mish_1'?	fail→pass	11,827	3,582	-70%	1	1	0%	2,354	8,188	+248%	0	0	—
case-20 Write a Node.js snippet using the telnyx package to send a basic text message from '+13125550002' to '+13125550001' with text 'Hello world'.	fail→pass	4,806	4,586	-5%	1	1	0%	966	8,400	+770%	0	0	—
case-21 How do I initiate an outbound voice call to '+13125550001' using the Telnyx JavaScript SDK?	pass→pass	9,649	5,535	-43%	1	1	0%	1,875	8,503	+353%	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. 22 cases were attempted. The headline lift of +86 percentage points is the difference between those two pass rates over the 22 comparable cases.

Model measured: gemini-3.6-flash
Graded by: gemini-3.6-flash
Grading method: judged
Verification: verified
Pass rate without the skill: 13.6%
Pass rate with the skill: 100%
Cases attempted: 22
Cases counted toward lift: 22
Cases that regressed: 0
Skill version measured: v2
Run completed: 8/22/2026, 20:14 UTC

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

Prompt

I'm building a backend service in Node.js and need to start a new run for a Telnyx mission using their JavaScript SDK. Could you write a code snippet that triggers the run, logs an initial status event for it, and includes proper try-catch error handling for rate limits and validation failures?

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+364% 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.