johnnymo87

Use on any NixOS host (devbox on Hetzner, cloudbox on GCP) when SSH connection fails, host key mismatch, NixOS issues, CPU/IO contention (high load), or verifying the host is properly configured

Launch headless opencode sessions from CLI. Use when you need to start a new opencode session in the background to work on a task in parallel, or when spawning work on a specific directory.

How to apply configuration changes to NixOS hosts (devbox, cloudbox). Use when you need to rebuild the system, apply home-manager changes, or recover from issues.

Use when setting up or rotating PagerDuty MCP auth for OpenCode on macOS Keychain or cloudbox sops, or when debugging missing PagerDuty tools.

Use when setting up or rotating Rollbar MCP auth for OpenCode on macOS Keychain or cloudbox sops, when triaging a Rollbar error paged via PagerDuty, or when debugging missing Rollbar tools.

Documents the OpenCode agent set — what each does, when to use it, and why the others were cut. Use when questioning agent choices or considering adding/removing agents.

Use when operating, deploying, debugging, or extending the aigateway LLM cost-capture proxy on cloudbox — routing opencode's Vertex providers through it, querying the per-request cost ledger (gateway_request_log), adding model prices, or rolling routing back.

Use when an opencode-serve pool member is unresponsive/wedged, when the serve-canary restarted a serve overnight, or when tuning the serve units' memory limits. Covers the "alive but frozen" failure mode, the canary timer, and where its forensics dumps land.

Use when deploying pigeon code changes across all machines after merging to main

Use when you need to understand worker architecture, endpoint flow, and command routing behavior before making changes

Use when you need to understand daemon route flow, storage model, worker connectivity, and command injection architecture before making changes

Use when you need to understand the OpenCode plugin event lifecycle, session state transitions, and daemon API contracts

Use when developing or refactoring OpenCode plugin handlers, tests, and daemon integration payloads

Use when you need to understand the swarm IPC subsystem — tables, routes, the per-target arbiter, the session→directory registry, and the wire envelope — before changing it

Use when implementing or testing swarm IPC features (new kinds, channels, plugin tools, or schema changes) with a TDD-first workflow

Use for day-to-day swarm IPC ops — health checks, inspecting queued/handed-off/failed messages, debugging stuck deliveries, force-failing retry loops, tailing arbiter logs

Create, inspect, and update Datadog monitors via API - get monitor details by ID or URL, create or update metric/query alerts with thresholds and Slack notifications. Use when setting up alerting, tuning monitors, investigating monitor triggers, or checking monitor group states.

Troubleshoot Datadog API authentication issues (401/403 errors), understand API keys vs app keys, and configure correct regions. Use when hitting auth errors or setting up Datadog API access.

Search and manage Datadog Error Tracking issues via API - find grouped errors by service, resolve/ignore issues. Use when investigating production errors or managing error tracking issue states.

Work with Datadog Incidents API - fetch incidents with enrichment, update incident fields, understand incident data structures. Use when working with incidents or the dd-cli get-incident/update-incident commands.

Create log-based count metrics via API - works with all storage tiers including flex. Use when you need to monitor log patterns but logs are in flex tier (where log monitors don't work).

Search Datadog logs via API - query syntax, storage tiers (indexes, flex, online-archives), pagination. Use when searching logs or using the dd-cli search-logs command.

List and inspect Datadog SLOs via API - view SLI values, error budgets, thresholds, and history. Use when checking SLO compliance, reviewing error budgets, or finding SLOs by tag.

Fetch Datadog Workflow Automation definitions and instances via API. Use when inspecting workflow configurations or execution history.

This skill teaches how to access GitHub's REST and GraphQL APIs via gh api for inline PR comments, review threads, and data not available through standard gh commands. Use this when you need PR review comments, thread status, or other GitHub data that gh pr view doesn't provide.

This skill creates ephemeral pods cloned from existing deployments for interactive shell access with full application context. Use this when you need Rails console, database access, or debugging with env vars and secrets without affecting production pods.

This skill repairs tmux socket connection errors when the socket directory is deleted while tmux is running. Use this when you see "error connecting to /private/tmp/tmux-UID/default (No such file or directory)" while tmux sessions are still active.

This skill guides working with Neovim configuration including testing changes headlessly, managing plugins with lazy.nvim, configuring LSP servers, and troubleshooting startup errors. Use this when modifying nvim config files or debugging nvim issues.

This skill guides the process of creating context-free queries for a web search agent (another Claude instance with web search tools). Use this when you need expert guidance from web research but the search agent has no access to the codebase or conversation history.

This skill teaches how to manage stacked PRs (pr1 → pr2 → pr3) after the base PR merges. Covers rebasing dependent PRs onto the updated base branch using cherry-pick workflow. Use this when you have a chain of dependent PRs and need to update them after merging earlier PRs in the stack.

Use when FP Digest or The Rundown is stuck, missing, delayed, retrying, or marked errored, and you need to inspect current job state, interpret failure counters, or recover manually.

Use when debugging The Rundown writer and collection path, especially opencode timeouts, reused collection artifacts, empty script output, or delayed daily episodes.

Use when a FP Digest or The Rundown job has status=errored and the consumer has stopped retrying it automatically.

Monitors and validates the my-podcasts production pipeline. Use when checking service health, queue backlog, feed endpoints, R2 artifacts, or end-to-end delivery status.

Builds and deploys my-podcasts Cloudflare workers and validates routes. Use when shipping email-ingest or podcast-serve worker updates.

Use when reasoning about a chess position to advise a player, after the position has been set up via chess_ MCP tools. Covers the discipline that prevents legality hallucinations (off-diagonal moves, pin blindness, miscounted material).

Use when a chess analysis session hits a gap in chess-support-mcp (missing legal-move list, no pins, no undo, etc.) and you're tempted to plug it. Catalogues known gaps, their priority, and the constraint that keeps this workspace engine-free.

Use when setting up the MCP game state from a SAN PGN, before analyzing a position. Covers the SAN→UCI conversion discipline and the "one illegal move cascades" gotcha that can waste a session's worth of tokens.

Send prompts to ChatGPT via browser automation. Use this when you need to query ChatGPT from the command line or integrate with the /ask-question slash command.