fuse-ai-pilot

Quick Flow for simple fixes - Single expert handles explore, code, review, and validate in one pass. Inspired by BMAD Barry.

APEX Methodology - The systematic Analyze-Plan-Execute-eLicit-eXamine approach for intelligent development. Eliminates hallucinations, errors, and bugs to produce clean, maintainable code.

Memory optimization - removes duplicates, consolidates knowledge, and cleans memory banks for better performance.

Smart conventional commits with auto-detection. Analyzes changes, detects type, commits with minimal interaction.

Auto-generate Pull Request with comprehensive description, test plan, and changelog. Uses gh CLI for creation.

Creative design agent for APEX workflow. Use when: new features, component creation, major changes, adding functionality. Triggers BEFORE Analyze phase. Structured questioning to refine requirements, propose alternatives, get design approval. Do NOT use for: bug fixes, trivial changes, refactoring, read-only tasks.

Codebase discovery specialist. Use when: unknown project structure, mapping dependencies, finding existing patterns before coding, architectural analysis. Read-only — no file modifications. Do NOT use for: documentation lookup (use research-expert), code fixes (use sniper), UI tasks (use design-expert).

Technical research expert. Use when: library docs lookup, API verification, best practices research. ALWAYS cross-reference BOTH Context7 (official docs) + Exa (latest community practices) for complete answers — never use only one source. Do NOT use for: codebase exploration (use explore-codebase), code fixes (use sniper).

SEO/SEA/GEO 2026 expert. Use when: optimizing page content for search, keyword research, meta tags, structured data, Google Ads campaigns, AI search visibility (GEO). Do NOT use for: technical SEO code implementation (use nextjs-expert or laravel-expert for the actual code changes).

Micro-fix applicator for ALREADY IDENTIFIED errors (linter output, sniper report, user-specified). ONLY for 1-10 line corrections. NEVER use for new features, refactoring, analysis, or any task requiring understanding. Use sniper (full 7-phase) for validation.

Use when creating expert agents. Generates agent.md with frontmatter, hooks, required sections, and skill references.

Systematic development workflow: Analyze → Plan → Execute → eLicit → eXamine. Use for ANY development task: features, bug fixes, refactoring, hotfixes. Triggers: "implement", "create", "build", "fix", "add feature", "refactor", "develop". Auto-detects project type (Laravel, Next.js, React, Swift) and loads framework-specific references. Enforces: files <100 lines, interfaces separated, SOLID principles, expert self-review, sniper validation. Modes: --auto (default), --manual, --skip-elicit

Use when user requests creative work - creating features, building components, adding functionality, or modifying behavior. Activates BEFORE APEX Analyze phase to refine requirements through structured questioning.

Code quality validation with linters, SOLID principles, DRY detection, error detection, and architecture compliance across all languages.

Auto-review skill for expert agents. After coding, expert applies elicitation techniques to self-correct before sniper validation. Inspired by BMAD-METHOD.

17 hooks across 6 events