Skip to content

mikehasa/golive-skill / skills/golive

golive

Flagged

Take an agent-written app from repo to live production on the user's OWN accounts, with providers they choose (hosting, database, auth, payments, email, domain/DNS). The human connects accounts and approves changes; supported wiring operations run through a local CLI and produce verification evidence with explicit limits. Use when the user wants to ship, deploy, go live, launch, publish, or put their app online, or asks to wire up env vars, webhooks, auth settings (signup, email confirmation, password policy), a real signup → confirmation email → login journey, password recovery, account isolation between two users, auth redirects, email DNS or a custom domain.

FileKindSize
LICENSEother1.0 KB
SKILL.mdskill md50.0 KB
THIRD_PARTY_NOTICES.mdmarkdown817 B
references/cloudflare-dns.mdmarkdown7.9 KB
references/godaddy.mdmarkdown3.9 KB
references/guided.mdmarkdown9.2 KB
references/neon.mdmarkdown4.4 KB
references/netlify.mdmarkdown6.9 KB
references/plan-and-verify.mdmarkdown47.4 KB
references/porkbun.mdmarkdown3.4 KB
references/posthog.mdmarkdown10.2 KB
references/resend.mdmarkdown8.6 KB
references/sentry.mdmarkdown10.7 KB
references/stripe.mdmarkdown13.1 KB
references/supabase.mdmarkdown49.7 KB
references/troubleshooting.mdmarkdown5.2 KB
references/updates.mdmarkdown5.0 KB
references/uptimerobot.mdmarkdown12.3 KB
references/vercel.mdmarkdown13.2 KB
release.jsonconfig2.4 KB
scripts/golive.mjsscript1.2 MB
scripts/install-cli.mjsscript5.0 KB
scripts/install-lib.mjsscript24.4 KB

references/neon.md

View on GitHub
# Neon

Automated database provider with mock coverage and an approved Netlify + Neon throwaway live run
on 2026-09-23. New Free-project creation, connection transfer to both hosting environments and
read-only database/role verification passed after the `--data=-` parser fix. Separately approved
schema, two-session API and browser CRUD/refresh checks also passed. Exact-resource cleanup later
passed under its own approval using a supervised fixture helper (Neon projects remain a manual
handoff in `golive teardown`).
This validates the tested Free organization and app, not every account or workload. It supplies
server-only pooled `db.url` and direct `db.directUrl`. It does not supply Supabase keys or migrate a
Supabase SDK application, and it does not provision Neon Auth, Data API or application schemas.

1. Have the human install `npm install -g neon` and run `neon auth` in a **separate terminal**.
   golive reuses the official CLI's login without reading its credential cache. The CLI must support
   `neon api`. Alternatively use `NEON_API_KEY`: on macOS run
   `credentials --prompt NEON_API_KEY --json` for private native entry. Their own editor is the
   fallback if unavailable, unsupported, or preferred; follow
   [How the human connects accounts](../SKILL.md#how-the-human-connects-accounts) for fallback,
   replacement and cancellation. Never print or
   inspect credential contents, pass keys on argv, or ask for a chat paste. An explicit token wins
   over the CLI login; fix a rejected token instead of silently switching identities.
2. Choose the exact organization (`neon.organizationId`, or non-secret `NEON_ORG_ID`). New project
   creation requires its API-confirmed `free` plan; several Free organizations need a choice. No
   upgrades, purchases or alternate-organization fallback are automated. Free quotas remain Neon
   enforced. New projects use `aws-us-east-2` unless `neon.region` is set, with fixed
   main/neondb/neondb_owner and 0.25 CU compute defaults. Do not set branch/database/role overrides
   for a new project.
3. For an existing project set `projects.db` to its exact ID, plus `neon.branchId`, `neon.database`
   and `neon.role`. Ask which existing branch the human wants; never infer a production/default
   branch. Same-name adoption without selectors is refused. These non-secret selectors appear in
   env approval. Both deployment targets use this selected branch; per-target branches are not
   automatically created.
4. Show the plan's account, org/project/region and connection selectors, obtain explicit approval,
   then apply. golive keeps returned credentials inside Secrets and transfers them directly to the
   chosen hosting env store. Never run a raw connection-string command in agent-visible output.
   A failed, timed-out or malformed creation response may still mean the create succeeded:
   inspect the exact approved organization and re-plan before another create. Pending project
   and operation IDs are saved for recovery; no password resets or automatic remote rollback.
5. `db-connection` uses one fixed read-only SQL transaction against the API-verified endpoint,
   and checks the exact database and role. It runs only on verified Free organizations. A pass
   proves connectivity from golive, **not** deployed app queries, schema, migrations, RLS or user
   isolation. Approve schema work separately and test real application behavior. Unsupported
   Supabase-specific checks remain skips.

Doctor success proves authentication reads, not create permission or quota. CLI failures emit only
fixed diagnostic categories; `unknown` does not mean the user needs to log in again. CLI 5.0.1
handler-only stdin testing initially missed the argv bug; exact parser coverage now verifies the
equals-form marker. The body stays in Secret stdin. Argument errors require checking syntax,
not automatically asking the user to upgrade.
If diagnostics remain unknown on a separately approved retry, return only an in-memory allowlisted
HTTP status/category. Never expose or save raw provider/debug output, and never retry a create just
to inspect its error.

Neon's official [CLI](https://neon.com/docs/reference/neon-cli),
[API](https://neon.com/docs/reference/api) and [remote MCP](https://mcp.neon.tech/mcp) are available.
MCP is optional and is not this adapter's transport. `neon init` or MCP setup can mint credentials
and change agent config; do not run it as a read-only login check.
writing-skillsobra/superpowersUse when creating new skills, editing existing skills, or verifying skills work before deploymentStars: 322kUpdated Claude CodeCodexVerifiedInstall
xlsxanthropics/skillsUse this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
shipping-and-launchaddyosmani/agent-skillsPrepares production launches. Use when preparing to deploy to production, or when asking what needs to be in place before shipping. Use when you need a pre-launch checklist, when setting up monitoring, when planning a staged rollout, or when you need a rollback strategy.Stars: 119kUpdated Claude CodeCodexVerifiedInstall
childhoodthedotmack/claude-memBabysit a shipped release after merge, publication, or deployment. Verify published packages, production behavior, installed plugins, and late CI or user reports until the observation window is clean; use babysit for PR readiness before release.Stars: 118kUpdated Claude CodeCodexVerifiedInstall