shunt
claudeShunts I/O-heavy work to AiKA modes to save tokens. Hooks block large file reads and redirect to bulk-reader/code-writer scripts backed by the Portal CLI.
2 skills · hooks
Set up, diagnose, search, and operate Spotify Portal through focused Portal CLI workflows.
Plugin portal from marketplace portal in Prasanth595/portal-ai-plugins. Commands read from the repo's manifest — 5 days ago.
bulk-readerDelegate bulk file reading to AiKA. Use when you need to read files >350 lines, answer questions across 3+ files, or summarize large diffs.
code-writerDelegate boilerplate code generation to AiKA. Use for tests, config, docstrings, type stubs, or any generation where >80% is predictable from reference files.
actionsDiscover, inspect, and invoke Spotify Portal actions through the Portal CLI. Use when the user asks what Portal can do, names an action ID, or wants to run a Portal operation.
doctorDiagnose Spotify Portal plugin, CLI, authentication, and action access without changing state. Use when setup is failing, commands are missing, authentication is unclear, a plugin update looks stale, or the user asks whether Portal is ready.
feedbackSubmit feedback about the Spotify Portal CLI to the Portal team. Use when the user explicitly asks to send CLI feedback, or voices an impression, complaint, suggestion, or praise about the Portal CLI or these Portal workflows and confirms they want it submitted.
fleetshift-check-shiftRead-only status check on Fleetshift shifts: what ran, which targets finished/failed, which PRs were opened and their state. Safe to run days or weeks after a shift was created or run. Use when the user asks "how is my shift going", "what happened to that fleetshift", "are the PRs merged yet", or wa
fleetshift-create-prsOpen pull requests from completed Fleetshift shift runs. Use after a shift has run and targets reached a "finished/jobComplete" state — this turns the agent-made changes into reviewable PRs on the target repositories. Requires explicit user confirmation before creating any PRs. Only opens PRs; it ne
fleetshift-create-shiftCreate a Fleetshift shift definition that runs an agent to apply transformations across a set of repository targets. Use when the user wants to set up a reusable, repeatable change (e.g. "add a header to every service", "migrate every repo from X to Y") that can later be run, checked on, and have PR
fleetshift-run-shiftRun an existing Fleetshift shift against its targets: triggers the agent jobs and monitors them to completion with a bounded wait. Also covers the kill switch for stopping a run (halt triggering, stop running jobs) when the user changes their mind. Use when the user wants to actually execute a previ
fleetshift-troubleshoot-shiftDiagnose why a Fleetshift shift or job failed: find failed targets, pull their job logs and status, and explain the root cause and the safe next step. Read-only and safe to run anytime. Use when a shift run fails, a target ends in jobFailed/stopped, or a soundcheck check is still failing after a run
searchSearch Spotify Portal's software catalog and technical documentation using natural language. Use when the user asks to find services, APIs, systems, components, owners, or Portal documentation and does not already know the exact entity reference.
serviceInspect a Spotify Portal service's owner, team, on-call contact, Slack channel, runbook, build, deployment, runtime, incidents, or documentation. Use when the user asks who owns a service, whether a service is healthy, where its runbook or docs are, or requests a service briefing.
setupSet up, authenticate, and verify Spotify Portal for the current coding agent. Use when the user asks to install or connect Portal, authenticate the Portal CLI, select a Portal instance, or verify CLI access.
Shunts I/O-heavy work to AiKA modes to save tokens. Hooks block large file reads and redirect to bulk-reader/code-writer scripts backed by the Portal CLI.
2 skills · hooks
Scaffold, validate, and publish new Claude Code plugins with proper structure
3 skills · 1 command · 1 agent
Claude Code skill for creating and presenting Slidev slidedecks
1 skill
Observability plugin for Claude Code with MLflow tracing
Skills for adding DeepEval evaluations, tracing, datasets, Confident AI reports, and iterative improvement loops to AI applications.
3 skills
Connect to your Phoenix instance to debug, evaluate, and improve LLM applications.
1 MCP server
OpenRouter for tools - 4,000+ agent-friendly tools, pay for the usage, not subscription
1 skill · 1 MCP server
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.