Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Use the Telnyx CLI to manage phone numbers, send messages, make calls, and access all Telnyx APIs from the terminal. 946 commands auto-generated from the OpenAPI spec — every API endpoint is a CLI command.
.claude/skills/team-telnyx-telnyx-cli/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | -13% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 28% | 0% |
| case-08 | ✗→✓ | ▲ Improved | -31% | 0% |
| case-09 | ✗→✓ | ▲ Improved | -48% | 0% |
| case-06 | ✗→✓ | ▲ Improved | -30% | 0% |
The Telnyx CLI provides command-line access to the entire Telnyx API. Every API endpoint maps to a CLI command — 946 commands covering messaging, voice, numbers, IoT, AI, and more.
bash# Homebrew (macOS/Linux) brew install telnyx/tap/telnyx # Go install go install github.com/team-telnyx/telnyx-go/cmd/telnyx@latest # Or download a binary from GitHub releases: # https://github.com/team-telnyx/telnyx-go/releases
bashexport TELNYX_API_KEY="KEY..."
The CLI reads TELNYX_API_KEY from your environment. Set it once in your shell profile.
The CLI is fully self-documenting. Use --help at any level to explore:
bash# Top-level resource list telnyx --help # Commands for a specific resource telnyx messages --help # Full usage for a specific command telnyx messages create --help
Commands follow a consistent pattern:
texttelnyx <resource> <action> [--flag value ...]
Resources match API paths. Actions are list, create, get, update, delete, and resource-specific verbs.
bashtelnyx messages create \ --from +15551234567 \ --to +15559876543 \ --text "Hello from the CLI"
bashtelnyx phone-numbers list --page-size 25
bashtelnyx available-phone-numbers list \ --country-code US \ --state CA \ --features sms
bashtelnyx number-orders create \ --phone-numbers +15551234567
bashtelnyx calls create \ --connection-id 1234567890 \ --from +15551234567 \ --to +15559876543
bashtelnyx sim-cards list --page-size 10
bashtelnyx assistants create \ --name "Support Agent" \ --model telnyx_ai
bashtelnyx balance get
bash# Default: human-readable table telnyx phone-numbers list # JSON output for scripting telnyx phone-numbers list --format json # Pipe to jq for filtering telnyx phone-numbers list --format json | jq '.data[].phone_number'
| Use case | Recommended | |----------|-------------| | Quick one-off operations | CLI | | Shell scripts and automation | CLI | | Application code | SDK (Python, JS, Go, Java, Ruby) | | Interactive exploration | CLI | | CI/CD pipelines | CLI or SDK | | Complex business logic | SDK |
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 7,879 | 2,364 | -70% | 1 | 1 | 0% | 1,358 | 1,178 | -13% | 0 | 0 | — |
case-02 | fail→pass | 6,456 | 4,003 | -38% | 1 | 1 | 0% | 1,134 | 1,446 | +28% | 0 | 0 | — |
case-03 | pass→pass | 5,540 | 3,307 | -40% | 1 | 1 | 0% | 1,098 | 1,427 | +30% | 0 | 0 | — |
case-04 | pass→pass | 10,333 | 3,412 | -67% | 1 | 1 | 0% | 1,671 | 1,375 | -18% | 0 | 0 | — |
case-05 | pass→pass | 7,071 | 3,220 | -54% | 1 | 1 | 0% | 1,249 | 1,337 | +7% | 0 | 0 | — |
case-07 | pass→pass | 6,708 | 3,600 | -46% | 1 | 1 | 0% | 1,285 | 1,479 | +15% | 0 | 0 | — |
case-08 | fail→pass | 11,203 | 3,823 | -66% | 1 | 1 | 0% | 1,889 | 1,295 | -31% | 0 | 0 | — |
case-09 | fail→pass | 11,818 | 2,667 | -77% | 1 | 1 | 0% | 2,211 | 1,148 | -48% | 0 | 0 | — |
case-06 | fail→pass | 10,178 | 3,052 | -70% | 1 | 1 | 0% | 1,851 | 1,295 | -30% | 0 | 0 | — |
case-10 | fail→pass | 8,547 | 3,387 | -60% | 1 | 1 | 0% | 1,431 | 1,304 | -9% | 0 | 0 | — |
case-11 | pass→pass | 2,683 | 1,771 | -34% | 1 | 1 | 0% | 397 | 1,020 | +157% | 0 | 0 | — |
case-12 | fail→pass | 5,780 | 2,153 | -63% | 1 | 1 | 0% | 916 | 1,108 | +21% | 0 | 0 | — |
case-13 | fail→pass | 8,682 | 3,414 | -61% | 1 | 1 | 0% | 1,432 | 1,293 | -10% | 0 | 0 | — |
case-14 | pass→pass | 7,514 | 2,413 | -68% | 1 | 1 | 0% | 1,297 | 1,216 | -6% | 0 | 0 | — |
case-15 | fail→pass | 6,202 | 2,560 | -59% | 1 | 1 | 0% | 1,009 | 1,215 | +20% | 0 | 0 | — |
case-16 | fail→pass | 5,396 | 2,043 | -62% | 1 | 1 | 0% | 977 | 1,082 | +11% | 0 | 0 | — |
case-17 | pass→pass | 9,530 | 4,909 | -48% | 1 | 1 | 0% | 1,610 | 1,577 | -2% | 0 | 0 | — |
case-23 | pass→pass | 4,038 | 2,206 | -45% | 1 | 1 | 0% | 707 | 1,177 | +66% | 0 | 0 | — |
case-18 | pass→pass | 13,403 | 11,123 | -17% | 1 | 1 | 0% | 2,121 | 2,551 | +20% | 0 | 0 | — |
case-19 | pass→pass | 15,992 | 11,283 | -29% | 1 | 1 | 0% | 2,445 | 2,664 | +9% | 0 | 0 | — |
case-20 | fail→pass | 16,219 | 7,975 | -51% | 1 | 1 | 0% | 2,886 | 2,240 | -22% | 0 | 0 | — |
case-21 | pass→pass | 11,970 | 7,987 | -33% | 1 | 1 | 0% | 1,793 | 2,070 | +15% | 0 | 0 | — |
case-22 | pass→pass | 3,659 | 3,588 | -2% | 1 | 1 | 0% | 710 | 1,400 | +97% | 0 | 0 | — |
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. 23 cases were attempted. The headline lift of +48 percentage points is the difference between those two pass rates over the 23 comparable cases.
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.
Other measured skills in the registry, with their headline benchmark lift.