av/harbor
19 skills
$npx skills add av/harborSkillInstalls
agent-integration-testingannealUse when the user wants to systematically fix AI code slop — duplicated logic, over-engineering, silent error swallowing, convention drift, cargo-cult…bugbashbughuntFully autonomous bug hunting pipeline — discover bugs in a scoped area using parallel subagents, independently triage each finding, fix confirmed issues with…disciplinefactsManage .facts files — atomic, validatable truth statements about a project. Install, check, list, add, edit, remove, and lint facts via the CLI.facts-discoverScan the codebase and classify every fact by lifecycle stage — tag @draft, @spec, or @implemented based on what the code actually shows.facts-implementOperate on @spec facts — implement them in code, then tag @implemented.facts-refineOperate on @draft facts — collaboratively refine them into precise, actionable @spec facts.harborCLI toolkit for managing containerized LLM services. Use when the user wants to start, stop, configure, or manage AI/LLM services like Ollama, Open WebUI,…harbor-daytonaUse Harbor's Daytona sandbox platform for computer use — creating sandboxes, taking screenshots, sending mouse/keyboard input, and building agent loops.ideateTimeboxed ideation on a topic using propose-and-critique subagent pairs.new-boost-moduleCreate new Harbor Boost modules — the Python plugins that run inside Harbor's LLM proxy.new-serviceAdd a new service to Harbor — scaffold the compose config, environment variables, metadata, documentation, and cross-service integrations.releasePerform Harbor release procedures — version bumping, codegen, committing, pushing, and drafting GitHub releases.run-llmsComprehensive guide for setting up and running local LLMs using Harbor.skill-creatortest-boost-moduleLive-test a Harbor Boost module by sending a real prompt through llamacpp via pi and validating the output.timeboxed-iterating