Stripe Safe Operations
SkillCommerce & financestripe-safe-operations lets your AI make Stripe changes such as refunds or subscription updates, but only after showing you the details and getting your confirmation. Before anything is carried out, it presents the exact environment, object, amount, currency, customer, and whether the effect can be undone. Nothing is written until you approve it.
Available today. Use it from your connected AI after setup.
No other account needed.
Add the skill, then tell your AI which Stripe change you want made. It will show you the full details and wait for your confirmation before acting.
Then ask your AI: use the Stripe Safe Operations skill
What your AI can do with it
- Refund a customer after you confirm the exact amount and currency
- Update a subscription once you approve the specific change
- Show the environment, object, customer, amount, and currency before any change goes through
- Flag changes that cannot be undone before they happen
- Hold every Stripe write until you explicitly approve it
What this skill tells your AI
The instructions your AI receives, as published by devin-axis/ipollowork in examples/plugin-packages/stripe/skills/stripe-safe-operations/SKILL.md and read by ahel’s review.
Use this skill for refunds, cancellations, subscription changes, or other material Stripe writes.
- Read the target object immediately before acting.
- Present test/live mode, account, object ID, customer, amount and currency, current state, requested change, and irreversible effects.
- Require explicit user confirmation for the exact operation. A general request to investigate is not confirmation to write.
- Execute once and avoid blind retries when the result is uncertain.
- Re-read the object and report the final state and identifiers.
Never expose credentials or full sensitive payment details. Never switch from test to live mode implicitly.
Signals
- GitHub stars
- 6k
- Forks
- 1k
- Last commit
- Sep 2026
ahel review
S4info
community integration — published by devin-axis, not stripe
Automated review, not a security audit. Ruleset v1.
Advanced
- Catalog kind
- skill
- Gateway key
stripe-safe-operations- Source
- github.com/devin-axis/ipollowork