Skip to content

ericrisco/rsc-harness / skills/google-workspace

google-workspace

Verified

Use when server-side code reads or writes Gmail, Drive, Calendar, or Sheets with a GCP service account and no human in the OAuth loop: picking the auth mode (app-owned vs domain-wide delegation vs keyless), scoping to least privilege, building the authed Node/Python client, staying under per-user quota, and debugging unauthorized_client / 403 / 429. NOT SMTP providers or deliverability (that is `email-connector`), NOT slot-finding and booking UX (that is `calendar-scheduling`).

FileKindSize
SKILL.mdskill md12.6 KB
evals/README.mdmarkdown1.1 KB
evals/cases.yamlconfig4.6 KB
references/api-recipes.mdmarkdown4.6 KB
references/auth-setup.mdmarkdown4.7 KB
scripts/verify.shexecutablescript4.8 KB

evals/README.md

View on GitHub
# Evals — google-workspace

These cases are routing and coverage checks for the skill harness, not live
Google API calls. `should_trigger` asserts a prompt should load and use this
skill (server-side Gmail/Drive/Calendar/Sheets via a service account, scope and
delegation decisions, 403/429/unauthorized_client debugging), including a
Spanish phrasing and non-obvious error-symptom triggers. `should_not_trigger`
asserts that a neighboring concern instead routes to the named real sibling
(email-deliverability, calendar-scheduling, spreadsheet-ops, document-processing,
automation-flows), guarding the boundaries in SKILL.md. The single `capability`
case is a rubric: feed the scenario to the skill and check the generated answer
covers every `must_include` bullet (correct DWD `subject`, minimal scopes, the
Admin-console client-ID authorization, the googleapis client build, backoff on
429, and the never-commit-the-key / keyless guidance). Nothing here touches a
real GCP project or sends mail; `scripts/verify.sh` is the only executable
artifact and it is a no-network static linter you can run against any repo.
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