| 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. |
Microservice Focus
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.
When to invoke this skill
A workflow command should invoke this skill exactly once, near the top of its execution, before delegating to a superpowers:* skill.
Inputs
The skill expects to find one of the following, in priority order:
- A
--services service-a,service-b argument parsed from the command's $ARGUMENTS.
- An existing
<focus_context> block in the conversation (set by a prior invocation).
- Multiple
pyproject.toml files at the repo root (multi-service repo).
- None of the above โ return single-service mode.
What the skill does
- Parse
--services if present. Skip the interactive prompt and use those services as the focused set.
- Discover services on disk when no explicit list was given. See service-discovery.md for the exact glob and parsing rules.
- If multi-service and no explicit list: use
AskUserQuestion to prompt the user with the discovered services as multi-select options. See focus-gate.md for the prompt format.
- Load each focused service's context:
prompt.md (preferred) or README.md (first 50 lines), pyproject.toml, and src/ structure. Cross-reference internal dependencies to build the dependency map.
- Build the
<focus_context> block. See focus-context-block.md for the canonical template.
- Return the service list + the
<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.
Output contract
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.
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.
References
