Cutseven/community-agent-skills

Twelve free, MIT-licensed Agent Skills for everyday work: inbox triage, finding files, scheduling meetings, tracking subscriptions, meal planning, backups, task capture, translation and summaries, batch file jobs, careful Cloudflare administration, careful UniFi network administration, and careful Home Assistant administration.
They follow the open Agent Skills format (skills/ /SKILL.md with name and description frontmatter), so the same folders work in Claude Code, Claude.ai, OpenAI Codex, Cursor, GitHub Copilot, Gemini CLI, Grok Build, and other tools that read the format. Each skill also has a plain copy-paste prompt in prompts/ for chatbots that don't support skills.
This is the any-agent edition of Cutseven/grok-community-skills. The Grok edition is packaged as a Grok Build plugin, has been submitted to xAI's plugin marketplace (pending review), and adds two Grok-only extras: a hook that asks before destructive shell commands and a read-only subagent for untrusted content.
Skills
| Skill | What it does | Prompt version |
|---|---|---|
| smart-inbox-triage | Sorts email into urgent/action/info/spam, pulls out action items and due dates, writes a short digest | prompt |
| universal-file-finder | Finds local files from a plain-language description (name, content, size, date, type) | prompt |
| meeting-sync-bot | Collects availability across time zones, ranks slots, drafts invites | prompt |
| subscription-tracker | Finds recurring charges in statements, flags renewals, drafts cancellation requests | prompt |
| meal-planner-grocery | Plans meals from what you have and builds a low-waste grocery list | prompt |
| auto-backup-restore | Plans and runs encrypted, versioned backups (restic) and safe restores | prompt |
| one-command-task-capturer | Turns one sentence into a structured task, catches duplicates, runs a weekly review | prompt |
| context-translator-summarizer | Translates for meaning, then gives a bullet summary and glossary | prompt |
| batch-task-runner | Chains rename/convert/resize/compress/zip jobs, with a dry-run preview first | prompt |
| cloudflare-infra-worker | Read-first Cloudflare engineer: DNS, Workers/Pages, WAF, SSL/TLS, Tunnel/Access; changes only in EXECUTE mode, with previews, rollback plans and explicit confirmation for destructive actions | prompt |
| unifi-network-admin | Careful UniFi network admin: read-only by default, one approved change at a time with backup, verification and rollback; troubleshooting, severity-ranked reports, quiet scheduled health checks | prompt |
| home-assistant-admin | Careful Home Assistant admin: safe (read-only) mode by default, approval-gated admin mode, one verified change at a time with backup and rollback; automations, integrations, updates, entity/battery/offline checks, energy, quiet scheduled checks | prompt |
How they work
The skills are instructions only: no scripts, no MCP servers, nothing that runs on install. Each one has a **Capabilities to use** section that describes the actions it needs (for example "fetch emails" or "search files"). The agent uses whatever tools it already has for those actions: email or calendar connectors, MCP servers, file access, a shell. If it has no suitable tool, the skill tells it to say so and offer a manual alternative instead of pretending.
Safety
Every skill follows the same rules:
- It never sends, posts, deletes, moves, or overwrites anything until you've seen exactly what will happen and said yes.
- Content from emails, files, statements, and web pages is treated as data, never as instructions.
- unifi-network-admin is read-only by default and makes one change at a time, each only after you approve its written change proposal.