agent-creator
Use when creating expert agents. Generates agent.md with frontmatter, hooks, required sections, and skill references.
Use when writing or refactoring Python code, structuring modules/[feature]/ layers, or defining Protocol-based interfaces (SOLID, files < 100 lines).
$ npx -y skills add fusengine/agents --skill solid-python --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/solid-pythonContext preview
The summary Claude sees to decide when to auto-load this skill.
Use when writing or refactoring Python code, structuring modules/[feature]/ layers, or defining Protocol-based interfaces (SOLID, files < 100 lines).
name: solid-python description: "Use when writing or refactoring Python code, structuring modules/[feature]/ layers, or defining Protocol-based interfaces (SOLID, files < 100 lines)." versions: python: "3.12" user-invocable: true references: references/principles.md, references/patterns.md related-skills: solid-detection
<objective> SOLID Python enforces a modular architecture for Python 3.12+: every feature lives under `modules/[feature]/` (routes, services, repositories, interfaces, models) with shared code in `core/`, interfaces are defined with `typing.Protocol` and live only in `interfaces/` directories, type hints are mandatory on every signature, and every public function carries a docstring.
Before writing any new code it requires a DRY check against `core/services` and `core/interfaces`. See `principles.md` for the 5 SOLID principles and `patterns.md` for directory layout, testing, and typing conventions. </objective>
Before ANY implementation, spawn 3 agents in parallel, one `Agent` call each with a `name`:
1. **fuse-ai-pilot:explore-codebase** - Analyze existing architecture 2. **fuse-ai-pilot:research-expert** - Verify Python docs via Context7 3. **fuse-ai-pilot:sniper** - Post-implementation validation
---
**Before writing ANY new code:** 1. **Grep the codebase** for similar interfaces, services, or logic 2. Check shared locations: `core/services/`, `core/interfaces/` 3. If similar code exists -> extend/reuse instead of duplicate 4. If code will be used by 2+ features -> create it in `core/`
---
| Layer | Location | Max Lines | |-------|----------|-----------| | Routes | `modules/[feature]/routes/` | 50 | | Services | `modules/[feature]/services/` | 100 | | Repositories | `modules/[feature]/repositories/` | 100 | | Interfaces | `modules/[feature]/interfaces/` | 30 | | Models | `modules/[feature]/models/` | 50 | | Shared | `core/{services,interfaces,models}/` | - |
**NEVER use flat `src/` structure - always `modules/[feature]/`**
---
| Rule | Value | |------|-------| | File limit | 100 lines (split at 90) | | Routes | < 50 lines, delegate to services | | Interfaces | `interfaces/` directory ONLY | | Docstrings | Every public function documented | | Type hints | MANDATORY on all signatures | | Protocols | Use `typing.Protocol` for interfaces | | Small interfaces | 1-3 methods max |
---
| Topic | Reference | When to consult | |-------|-----------|-----------------| | **SOLID Principles** | [principles.md](references/principles.md) | Quick reference for all 5 principles | | **Patterns & Structure** | [patterns.md](references/patterns.md) | Directory layout, testing, typing |
---
| Anti-Pattern | Fix | |--------------|-----| | Files > 100 lines | Split at 90 | | Interfaces in impl files | Move to `interfaces/` directory | | Fat interfaces (4+ methods) | Split into small Protocols | | Flat `src/` structure | Use `modules/[feature]/` | | Concrete dependencies | Use Protocol + dependency injection | | Missing type hints | Add type annotations to all signatures |
A plugin ecosystem that turns Claude Code into a supervised, multi-agent development environment.
Repo: fusengine/agents
Use when creating expert agents. Generates agent.md with frontmatter, hooks, required sections, and skill references.
Use when starting ANY development task -- feature, bug fix, refactor, hotfix (triggers: implement, create, build, fix, add feature, refactor, develop).
Use when creating a feature/component or adding functionality. Fires BEFORE APEX Analyze to refine requirements via structured questioning.
Use before a root-cause, done/verified claim, irreversible action, or 2nd-time fix reaches the owner (APEX or plain conversation); also fires at every…
Use when validating code quality after modifications -- SOLID compliance, DRY duplication, linter errors, architecture violations. Do NOT use for functional…
Use when an expert agent self-reviews and self-corrects code after the Execute phase, before sniper validation (BMAD-METHOD elicitation techniques).