meta-agentic-template

Spec-Driven Development methodology for meta-agentic workflows. Use when planning or executing green-field, brown-field, or modernization scenarios that require team formation, capability mapping, confidence scoring, and iterative spec-first development. Covers 10-phase SDD pipeline, artifact conventions, team-formation algorithm, capability-acquisition decision tree, and 6-dimension confidence rubric.

Generate and update real-time HTML progress reports for meta-agentic workflows. Use when generating progress dashboards, tracking multi-phase SDD execution, visualizing confidence scores, reporting team composition, displaying capability gaps, or updating status for green-field, brown-field, and modernization scenarios. Self-contained HTML with embedded JSON data island.

Extend or modify existing codebases using Spec-Driven Development (SDD). Use when adding features to an existing system, modifying current functionality, or working within an established codebase. Discovers existing architecture, analyzes change requirements, forms specialized agent team, and delivers safe changes with confidence scoring.

Build new systems from scratch using Spec-Driven Development (SDD). Use when creating a new application, service, or project with no existing codebase. Gathers requirements, forms specialized agent team, acquires capabilities (MCP/skills/instructions), and delivers verified solutions with confidence scoring.

Migrate or modernize legacy systems using Spec-Driven Development (SDD). Use when migrating between platforms, modernizing legacy code to current-generation stacks, or performing cross-platform migrations. Assesses legacy capabilities, maps to target platform, forms specialized agent team, and delivers verified migration with parity testing and confidence scoring.

Create and maintain an LLM-owned repo wiki for indexing and understanding existing codebases. Use for codebase understanding, repo wiki, LLM wiki, brown-field or modernization Discovery context, source assessment, architecture discovery, token-efficient repository indexing, and replacing ad hoc RAG with maintained markdown knowledge.