ericrisco/rsc-harness / skills/gcp-essentials
gcp-essentials
VerifiedUse when running a small product on core Google Cloud via the gcloud CLI: a project, Cloud Run deploys, a locked-down Cloud Storage bucket, managed Cloud SQL, and least-privilege IAM wiring them together. NOT AWS (that is `aws-essentials`), NOT the CI pipeline that ships the image (that is `deployment`), NOT Postgres schema/query tuning (that is `postgresdb`).
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 14.6 KB |
| evals/README.md | markdown | 788 B |
| evals/cases.yaml | config | 2.5 KB |
| references/deploy-recipes.md | markdown | 2.7 KB |
| references/iam-and-auth.md | markdown | 3.7 KB |
| references/networking-and-sql.md | markdown | 3.2 KB |
| scripts/verify.shexecutable | script | 5.5 KB |
evals/README.md
View on GitHub# Evals — gcp-essentials
`cases.yaml` drives two checks through the repo's standard eval harness. The
`should_trigger` / `should_not_trigger` prompts verify routing: each negative case
names the real sibling skill it should defer to (`aws-essentials`, `docker`,
`postgresdb`, `security-audit`, `vercel`) so the boundary is graded, not assumed. The
`capability` case is graded by an LLM judge against its `must_include` rubric — there
are no live GCP calls and nothing is deployed; the judge reads the produced gcloud
commands and checks that they are least-privilege, keyless, private-by-default, and
include a cost/teardown note. Run it the same way as every other skill in this repo
(point the harness at this directory); inspect any rubric miss by hand before trusting
the score.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| writing-skillsobra/superpowersUse when creating new skills, editing existing skills, or verifying skills work before deployment | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| 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: 198k | Updated | Claude CodeCodex | Verified | Install |
| 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: 119k | Updated | Claude CodeCodex | Verified | Install |
| 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: 118k | Updated | Claude CodeCodex | Verified | Install |