// Use when a workflow command needs to detect multi-service monorepos, prompt for service scope, and propagate `<focus_context>` to sub-agents. Triggers when `--services` is passed, when focus context already exists in the conversation, or when multiple `pyproject.toml` files exist at the repo root.
This skill should be used to refine brainstorm or plan documents before proceeding to the next workflow step. It applies when a brainstorm or plan document exists and the user wants to improve it.
Configure which review agents run for your project. Auto-detects Python stack and writes compound-engineering.local.md.
Browser automation using Vercel's agent-browser CLI. Use when you need to interact with web pages, fill forms, take screenshots, or scrape data. Alternative to Playwright MCP - uses Bash commands with ref-based element selection. Triggers on "browse website", "fill form", "click button", "take screenshot", "scrape page", "web automation".
Build applications where agents are first-class citizens. Use this skill when designing autonomous agents, creating MCP tools, implementing self-modifying systems, or building apps where features are outcomes achieved by agents operating in a loop.
Analyze changes, group into logical units, and create conventional commits with gitmoji. Use when committing code changes.
Implement async task queues with Celery and real-time WebSocket support with Django Channels. Use when a Django project includes celery or channels in its dependencies, or when implementing background processing, periodic tasks, WebSocket connections, or real-time features.
| name | microservice-focus |
| description | Use when a workflow command needs to detect multi-service monorepos, prompt for service scope, and propagate `<focus_context>` to sub-agents. Triggers when `--services` is passed, when focus context already exists in the conversation, or when multiple `pyproject.toml` files exist at the repo root. |
Consolidates the service-discovery and focus-context-propagation logic used by every Python workflow command in this plugin. Invoked once per command; returns the focused service list plus a <focus_context> block ready to inject into sub-agent prompts.
A workflow command should invoke this skill exactly once, near the top of its execution, before delegating to a superpowers:* skill.
The skill expects to find one of the following, in priority order:
--services service-a,service-b argument parsed from the command's $ARGUMENTS.<focus_context> block in the conversation (set by a prior invocation).pyproject.toml files at the repo root (multi-service repo).--services if present. Skip the interactive prompt and use those services as the focused set.AskUserQuestion to prompt the user with the discovered services as multi-select options. See focus-gate.md for the prompt format.prompt.md (preferred) or README.md (first 50 lines), pyproject.toml, and src/ structure. Cross-reference internal dependencies to build the dependency map.<focus_context> block. See focus-context-block.md for the canonical template.<focus_context> block to the caller. The caller is responsible for injecting it into the prompts of any sub-agents or sub-skills it invokes.The skill returns two pieces of information to the caller:
services: a list like ["service-a", "service-b"], or an empty list in single-service mode.focus_context: a <focus_context>...</focus_context> block ready to splice into sub-agent prompts. Empty string in single-service mode.If only one (or zero) pyproject.toml is found and no --services argument was passed, the skill returns immediately with an empty service list and an empty focus context. The caller proceeds without per-service path overrides.
<focus_context> template & propagation rules