Onboards and troubleshoots GitHub PR CI fixing by configuring GitHub CLI authentication, a non-exposed GitHub token, a matching local checkout, and a ready coding agent before running fixgithubprci. Use for first-time setup, failed prerequisites, demos, or action-shaped requests to onboard the user onto the local…
Summarise PostHog product analytics into a per-metric team pulse. Use for PostHog usage overviews, per-metric summaries, product-analytics digests, or "what happened this week" reporting.
Read Yandex Cloud through its REST API. Applies to any question about VMs, metrics, logs, audit events, Kubernetes, managed databases, serverless, networking or any other Yandex Cloud resource. Never shell out to the yc CLI — it is not how this agent reaches Yandex Cloud and is usually not installed.
A read-only shell skill for examining files and running diagnostic commands in a restricted environment. A shell is a text interface for operating-system commands.
Compare AI coding providers side by side. Use this skill whenever the user asks to compare Claude vs Gemini vs Codex, wants a provider comparison, asks "which provider is better/cheaper/faster", wants to see differences between CLIs, or mentions "compare", "versus", "vs", "head to head", "side by side". Also trigger…
Show AI coding cost and token usage. Use this skill whenever the user asks how much they spent, wants a cost breakdown by provider or model, asks about token consumption, wants to compare Claude vs Gemini costs, or mentions anything about budget, spend, billing, or usage dollars. Supports time ranges like today…
Show tool usage statistics and error rates. Use this skill whenever the user asks about which tools are used most, tool error rates, wants to see Read/Edit/Bash/Grep call counts, asks about tool failures, sensitive file access, or wants a breakdown of tool usage by provider or repository. Also trigger when the user…
Use when verifying that a frontend code change, LLM harness edit, or system prompt update produces the expected result in the running Graft plugin UI (http://localhost:3000/a/vikshana-graft-app). Drives a real headed Chrome session via Chrome DevTools MCP — navigate, click, inspect console errors, inspect network…
Use when troubleshooting, implementing, reviewing, or auditing platform infrastructure as a system — where Kubernetes, GitOps, CI/CD, and security concerns intersect. Provides structured diagnosis with blast radius, validation steps, and rollback plan for: Kubernetes, Flux CD, Argo CD, Terraform, GitHub Actions…
Release the Grafana Cube datasource plugin end-to-end: babysit a feature PR until green and merge it, merge the release-please PR to publish a release, and run the CD workflow to deploy to Grafana Cloud. Use when the user mentions release, publish, ship, deploy the plugin, or babysit a PR.
Write, install and test an n-dashboard widget — the TypeScript function in data/widgets/ /widget.ts that returns typed card data. Use when asked to add or change a dashboard card or widget, choose a kind, trigger or history setting, or debug a widget that errors, returns the wrong shape, or shows a stale card.
Use when the user wants to tune, benchmark, or optimise TCP performance on Kubernetes worker nodes — walks through baseline measurement, the SLO convergence loop, the sysctl tuning playbook, fault-injection testing, and saving a runbook. Also activates for phrases like "improve throughput", "reduce retransmits"…