devopsby composio-community
Resend CLI
composio-community/Resend CLI
Send emails, manage domains, API keys, contacts, and broadcasts.
What it changes
Passed 22 of 23 test cases with the skill, and 14 of 23 without it.
Without skill61%
With skill96%
Checks it passed that the model alone missed
- Mentions 53 commands
- Mentions 13 resources
- Includes the --from parameter
and 7 more in the full report
8 fixed14 passed either way1 still failing0 broke
- Pass-rate lift
- +35 pp
- Tokens
- -47%
- Agent turns
- 0%
- Response time
- -69%
Model gemini-3.6-flashMeasured 8/27/2026v122 of 23 cases passed with skill
See it in action
One of 8 test cases the skill fixed. Same model, same prompt, with and without the skill.
PromptInstead of writing custom Node.js code with the Resend SDK to fetch API keys, what is the exact terminal command to display them?
What was checked, without and with the skill| Checked | Without skill | With skill |
|---|
| Provides the command resend api-keys list | Missed | Passed |
|---|
What's inside
The instructions your model reads when the skill loads.
SKILL.md32 linessingle file
Resend CLI
Send emails, manage domains, API keys, contacts, and broadcasts. 53 commands across 13 resources.
Installation
npm i -g resend
resend login
Key Commands
resend emails send --from "[email protected]" --to "[email protected]" --subject "Hello" --text "Hi there"
resend domains list
resend contacts list --audience-id <id>
resend api-keys list
resend broadcasts list
Agent-Friendly Features
- Auto-detects TTY — outputs JSON when piped
- Natural language scheduling
- Idempotency keys for safe retries
resend doctor for agent environment detection- 53 commands across 13 resources
- Meaningful exit codes
Track record
Benchmark
22 / 23
test cases passed, vs 14 / 23 without
Adoption
- Users
- 0
- Times used
- 0
Safety and source details
SkillSafety
✓ 3 of 3 passed✓Code scan15 of 15 checks clean
0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026
View 15 scanner checks
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
ImportedImported 8/3/2026Version v1