PROACTIVELY USE after implementing code to add docstrings, type hints, cleanup. Delegates grunt work to local LLMs — saves cloud tokens. Files must be <500 lines. Use for mechanical polish, not logic changes. Changes are auto-applied.
Dispatches local LLMs to add docstrings, type hints, and cleanup to code files.
/plugin marketplace add felixmanojh/minions/plugin install minions@felixmanojh-minionsThis skill is limited to using the following tools:
Dispatch local model to add mechanical polish. Changes are auto-applied.
source .venv/bin/activate && python scripts/minions.py --json polish <files> --task <task>
| Task | Description |
|---|---|
all | Docstrings + types + headers (default) |
docstrings | Add function/class docstrings |
types | Add type hints |
headers | Add module-level docstrings |
# Polish single file
python scripts/minions.py --json polish src/foo.py --task all
# Multiple files
python scripts/minions.py --json polish src/foo.py src/bar.py --task docstrings
# Dry run
python scripts/minions.py --json polish src/foo.py --task all --dry-run
{
"applied": true,
"files_modified": ["src/foo.py"],
"changes": ["src/foo.py: Added 3 docstring(s)"],
"errors": [],
"stats": {"total": 1, "applied": 1, "failed": 0}
}
After completing code:
This skill should be used when the user asks about libraries, frameworks, API references, or needs code examples. Activates for setup questions, code generation involving libraries, or mentions of specific frameworks like React, Vue, Next.js, Prisma, Supabase, etc.