financeby composio-community
Stripe CLI
composio-community/Stripe CLI
Test webhooks, trigger events, tail API logs, and manage Stripe resources.
What it changes
Passed 23 of 23 test cases with the skill, and 18 of 23 without it.
Without skill78%
With skill100%
Checks it passed that the model alone missed
- The command includes --json
- The command includes --limit 5
- The command includes the --json flag
and 4 more in the full report
5 fixed18 passed either way0 still failing0 broke
- Pass-rate lift
- +22 pp
- Tokens
- -37%
- Agent turns
- 0%
- Response time
- -51%
Model gemini-3.6-flashMeasured 8/28/2026v123 of 23 cases passed with skill
See it in action
One of 5 test cases the skill fixed. Same model, same prompt, with and without the skill.
PromptWhich command lists top-level endpoints and collections supported by the Stripe CLI tool?
What was checked, without and with the skill| Checked | Without skill | With skill |
|---|
| The command named is stripe resources list | Missed | Passed |
|---|
What's inside
The instructions your model reads when the skill loads.
SKILL.md31 linessingle file
Stripe CLI
Test webhooks, trigger events, tail API logs, and manage Stripe resources from the terminal.
Installation
brew install stripe/stripe-cli/stripe
stripe login
Key Commands
stripe listen --forward-to localhost:4242/webhook
stripe trigger payment_intent.succeeded
stripe logs tail
stripe resources list
stripe customers list --json
stripe payments list --limit 5 --json
Agent-Friendly Features
--json flag for structured output- API key auth via
STRIPE_API_KEY
- Non-interactive webhook forwarding
- Event triggering for testing
Track record
Benchmark
23 / 23
test cases passed, vs 18 / 23 without
Adoption
- Users
- 2
- Times used
- 33
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