agent-creator
Use when creating expert agents. Generates agent.md with frontmatter, hooks, required sections, and skill references.
Use when determining which language-specific SOLID skill to load, detecting project type from config files, or resolving interface directory conventions.
$ npx -y skills add fusengine/agents --skill solid-detection --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/solid-detectionContext preview
The summary Claude sees to decide when to auto-load this skill.
Use when determining which language-specific SOLID skill to load, detecting project type from config files, or resolving interface directory conventions.
name: solid-detection description: "Use when determining which language-specific SOLID skill to load, detecting project type from config files, or resolving interface directory conventions." argument-hint: "[file-or-directory] [--language]" user-invocable: false
<objective> SOLID Detection identifies a project's language/framework from its config files (package.json + next/react, tsconfig.json/bun files, composer.json + laravel, Package.swift/*.xcodeproj, pom.xml/build.gradle, go.mod, Gemfile+Rakefile, Cargo.toml, pyproject.toml/requirements.txt) in a fixed priority order, then maps it to the matching SOLID skill and sets `SOLID_PROJECT_TYPE`, `SOLID_FILE_LIMIT`, `SOLID_INTERFACE_DIR`, and `SOLID_STRUCTURE` environment variables via `detect-project.sh`.
An interface found in the wrong location is a hard BLOCK; exceeding the file-size limit or missing documentation is a WARNING only. See `language-rules.md` for the full per-language interface-location, forbidden-zone, and line-counting rules. </objective>
Detect project type from configuration files:
# Next.js (priority over React) [ -f "package.json" ] && grep -q '"next"' package.json # React (no "next" in package.json) [ -f "package.json" ] && grep -q '"react"' package.json && ! grep -q '"next"' package.json # Generic TypeScript (no react/next, has .ts files) [ -f "package.json" ] && ! grep -q '"react"' package.json && ! grep -q '"next"' package.json [ -f "tsconfig.json" ] || [ -f "bun.lockb" ] || [ -f "bunfig.toml" ] # Laravel [ -f "composer.json" ] && grep -q '"laravel' composer.json # Swift [ -f "Package.swift" ] || ls *.xcodeproj # Java [ -f "pom.xml" ] || [ -f "build.gradle" ] || [ -f "build.gradle.kts" ] # Go [ -f "go.mod" ] # Ruby [ -f "Gemfile" ] && [ -f "Rakefile" ] # Rust [ -f "Cargo.toml" ] # Python [ -f "pyproject.toml" ] || [ -f "requirements.txt" ]
**Priority order:** Next.js > React > Generic TS > Laravel > Swift > Java > Go > Ruby > Rust > Python
For the full per-language rule tables (interface location, forbidden zones, pattern-detection regex) and line-counting rules, see [language-rules.md](references/language-rules.md).
| Severity | Action | |----------|--------| | Interface in wrong location | **BLOCK** (exit 2) | | File over limit | **WARNING** (exit 0) | | Missing documentation | **WARNING** |
| Project Type | SOLID Skill | Skill Path | |--------------|-------------|------------| | `nextjs` | solid-nextjs | `nextjs-expert/skills/solid-nextjs/` | | `react` | solid-react | `react-expert/skills/solid-react/` | | `generic` | solid-generic | `solid/skills/solid-generic/` | | `laravel` | solid-php | `laravel-expert/skills/solid-php/` | | `swift` | solid-swift | `swift-apple-expert/skills/solid-swift/` | | `java` | solid-java | `solid/skills/solid-java/` | | `go` | solid-go | `solid/skills/solid-go/` | | `ruby` | solid-ruby | `solid/skills/solid-ruby/` | | `rust` | solid-rust | `solid/skills/solid-rust/` | | `python` | _(no skill yet)_ | - |
Set by `detect-project.sh`:
SOLID_PROJECT_TYPE=nextjs|react|generic|laravel|swift|java|go|ruby|rust|python|unknown SOLID_FILE_LIMIT=100|150 SOLID_INTERFACE_DIR=path/to/interfaces SOLID_STRUCTURE=modular
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).