ericrisco/rsc-harness / skills/email-connector
email-connector
VerifiedUse when wiring server code to send transactional or bulk email via Resend, SendGrid, or Postmark: a provider-agnostic sendEmail() seam, idempotent retries, 100-cap batches with partial failures, transactional-vs-broadcast streams, bounce webhooks feeding a suppression list. NOT SPF/DKIM/DMARC inbox reputation (that is `email-deliverability`).
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 12.3 KB |
| evals/README.md | markdown | 1.2 KB |
| evals/cases.yaml | config | 3.5 KB |
| references/providers.md | markdown | 4.7 KB |
| scripts/verify.shexecutable | script | 3.1 KB |
evals/README.md
View on GitHub# Evals — email-connector
`cases.yaml` holds three blocks. `should_trigger` (5 prompts) are situations
this skill must own — including the non-obvious "emails double-send on retry"
(idempotency) and a Spanish bounce-webhook phrasing. `should_not_trigger` (4
prompts) are near-misses that each route to a real sibling (`newsletter`,
`email-deliverability`, `google-workspace`, `api-connector-builder`) so the
routing boundary is checked, not just recall. `capability` (1 scenario) is an
end-to-end SaaS wiring task with a `must_include` rubric covering the seam, env
key, idempotency, templating, batch partial-failure, stream split, webhook
signature, and suppression.
There is no automated runner here. To evaluate, paste each `should_trigger` /
`should_not_trigger` prompt into an agent loaded with the catalog and confirm it
selects (or declines to) `email-connector` and routes to the named sibling. For
`capability`, run the scenario and check the produced integration against every
`must_include` line — then run `scripts/verify.sh <path-to-integration>` to
mechanically confirm the env-key, idempotency, seam, and webhook-signature
invariants on the generated code.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| receiving-code-reviewobra/superpowersUse when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| requesting-code-reviewobra/superpowersUse when completing tasks, implementing major features, or before merging to verify work meets requirements | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| using-git-worktreesobra/superpowersUse when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| verification-before-completionobra/superpowersUse when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |