Run your own AI team from your phone. Claude Code, Codex and more on your own server: shared tasks, always-on agents, a small composable bash core. MIT.
5dive builds a self-hosted AI agent runtime, and the skills published under this name help an agent diagnose a failing runtime on its own server, review diffs and pull requests for logic bugs and missing tests, and prove web changes in a real browser with Playwright end-to-end tests. Other skills cover writing conversion-focused landing page copy, editing drafts toward plainer prose, compiling interlinked markdown knowledge bases, and finding or authoring recurring scheduled agent loops. The collection is oriented toward running and maintaining an agent team, with much of it concerned with how agents themselves are operated and kept healthy.
Skills
15 skills · 1 stars · MIT
5Dive Cli Operate the local 5dive runtime: coordinate sibling agents and inspect or update shared tasks.
5Dive Cli Extras Administer the local 5dive runtime beyond everyday delegation: accounts and auth recovery, declar…
Ad Creative Generate and iterate paid-ad creative at scale — headlines, descriptions, primary text and full a…
Code Review Review a diff or pull request for correctness first and quality second — logic bugs, edge cases,…
Compile Knowledge Compile durable, judgement-shaped knowledge into interlinked markdown — atomic files, [[wiki-link…
Copywriting Write, rewrite or improve conversion-focused marketing copy for a web page — homepage, landing, p…
Deep Research Run structured multi-source research that produces a cited, adversarially verified synthesis with…
Diagnose Diagnose a failing 5dive agent runtime on its own VM — auth state, service health, disk, memory,…
Find Loops Search the agenticloops.dev directory for an existing agentic loop (a recurring, scheduled agent)…
Loops Author or modify a LOOP.md — the portable agenticloops.dev format for a recurring, scheduled agen…
No Ai Slop Edit drafts into sharper, more human writing while preserving the writer's personal voice, or det…
Openagent Author your own OpenAgent persona file and mint its shareable holo trading card — write, validate…
Playwright E2E End-to-end test and click-verify a web app with Playwright — write specs, drive authenticated pag…
Verify Grade a delivered claim against the artifact instead of against the report of it, emitting a thre…
Zero Human Dev Team Every rule for running a team of AI coding agents that write, review, test and release code, file…