McFuzzySquirrel

Adds new data fields or entities to Knowledge Dungeon's persistence layer, covering type definitions, store updates, save/load logic, backward compatibility, and test coverage.

Adds a new interactive structure type (building, landmark, or interaction point) to the Knowledge Dungeon village hub. Use this skill when adding any new structure that players can approach and interact with - fishing ponds, new buildings, interactable decorations, or custom landmarks. Covers the full cross-agent pipeline: layout data, Phaser rendering, React info panel, and interaction routing.

Scaffolds a new Phaser game object (NPC, decoration, portal, item, or interactive element) in a Knowledge Dungeon scene, following the project's patterns for texture loading, positioning, animation, and state integration.

Discover which LLM models are available to the user (cloud subscription + local Ollama), classify each generated agent's workload, and recommend (and optionally apply) a per-agent model assignment so that lightweight agents do not default to the most expensive model. Use this skill after `forge-build-agent-team` has produced an agent team, or any time the team changes.

Analyze a Product Requirements Document (PRD), Product Vision with Feature documents, or Feature PRD and generate a complete team of custom agents and reusable skills tailored to the project. Use this skill when asked to create, scaffold, or design a development team from requirements documents.

Build a Feature PRD that captures a feature - either as a new addition to an existing project, or as part of initial project decomposition from a Product Vision. Use this skill when you need a self-contained feature document with user stories, requirements, and implementation tasks.

Build a comprehensive Product Requirements Document (PRD) or Technical Specification from a user's idea, concept, or research document. Use this skill when asked to create, draft, or formalize a PRD, spec, or requirements document.

Decompose an existing monolithic Product Requirements Document (PRD) into a Product Vision document and individual Feature documents. Use this skill when you want to break a large PRD into independent, self-contained features that can be prioritized, built, and delivered separately.

Discover which LLM models are available to the user (cloud subscription + local Ollama), classify each generated agent's workload, and recommend (and optionally apply) a per-agent model assignment so that lightweight agents do not default to the most expensive model. Use this skill after `forge-build-agent-team` has produced an agent team, or any time the team changes.

Meta-skill that bootstraps a new project end-to-end from a one-liner idea by chaining the deterministic Forge skills: forge-build-prd → (pause for review) → forge-build-agent-team → (pause for review) → optionally forge-assign-models. Use this skill when a user wants to go from idea to a reviewable PRD and a generated agent team in a single guided flow, without losing the human review gates between steps.

Analyze a Product Requirements Document (PRD), Product Vision with Feature documents, or Feature PRD and generate a complete team of custom agents and reusable skills tailored to the project. Use this skill when asked to create, scaffold, or design a development team from requirements documents.

Build a Feature PRD that captures a feature - either as a new addition to an existing project, or as part of initial project decomposition from a Product Vision. Use this skill when you need a self-contained feature document with user stories, requirements, and implementation tasks.

Coordinate specialist agents through PRD implementation phases. Provides the full execution process for PRD full builds, Feature PRD executions, and feature-based builds from decomposed documents. Use this skill when the project-orchestrator agent invokes it, or when you need to drive a build step by step.

Scaffold a working Microsoft Agent Framework solution from a PRD that has selected Microsoft Agent Framework (https://learn.microsoft.com/en-us/agent-framework/) as the technology choice. Use this skill when asked to create, scaffold, bootstrap, or generate an Agent Framework project (single-agent, multi-agent, or workflow-based) in .NET or Python from an existing PRD, Feature PRD, or Product Vision + Feature documents.

Build a comprehensive Product Requirements Document (PRD) or Technical Specification from a user's idea, concept, or research document. Use this skill when asked to create, draft, or formalize a PRD, spec, or requirements document.

Decompose an existing monolithic Product Requirements Document (PRD) into a Product Vision document and individual Feature documents. Use this skill when you want to break a large PRD into independent, self-contained features that can be prioritized, built, and delivered separately.

Add a complete Repo Dungeon biome content pack, including tileset references, prop/NPC dressing, palette cues, and ambient audio hooks for a language or topic zone.

Add Repo Dungeon unit, component, or integration coverage for a gameplay, UI, or platform subsystem using Vitest, React Testing Library, and MSW as appropriate.

Scaffold a Repo Dungeon Phaser scene with lifecycle hooks, typed event wiring, and integration points for generation, UI overlays, and progression events.

Build an accessible Repo Dungeon React overlay, panel, or screen that consumes shared game state without moving feature logic out of its specialist owner.

Add or extend a Repo Dungeon GitHub data flow, including Octokit access, typed models, caching, backoff, and mocked verification coverage.

Discover which LLM models are available to the user (cloud subscription + local Ollama), classify each generated agent's workload, and recommend (and optionally apply) a per-agent model assignment so that lightweight agents do not default to the most expensive model. Use this skill after `forge-build-agent-team` has produced an agent team, or any time the team changes.

Meta-skill that bootstraps a new project end-to-end from a one-liner idea by chaining the deterministic Forge skills: forge-build-prd → (pause for review) → forge-build-agent-team → (pause for review) → optionally forge-assign-models. Use this skill when a user wants to go from idea to a reviewable PRD and a generated agent team in a single guided flow, without losing the human review gates between steps.

Scaffold a working Microsoft Agent Framework solution from a PRD that has selected Microsoft Agent Framework (https://learn.microsoft.com/en-us/agent-framework/) as the technology choice. Use this skill when asked to create, scaffold, bootstrap, or generate an Agent Framework project (single-agent, multi-agent, or workflow-based) in .NET or Python from an existing PRD, Feature PRD, or Product Vision + Feature documents.

Create a README.md file for the project

Initialize an Engineering Journey System (EJS) session by creating a Session Journey file, refreshing the ADR/journey database index, and setting up metadata for continuous recording throughout the session.

Finalize an Engineering Journey System (EJS) session by completing all journey sections, populating machine extracts, evaluating the ADR decision rubric, and optionally creating an ADR document.

Capture sub-agent decisions, rationale, and inter-agent handoffs during multi-agent Engineering Journey System (EJS) workflows. Ensures that delegated work is properly attributed and traceable.

Scaffolds a typed gameplay entity module (player, asteroid, projectile) with lifecycle, update logic, and event hooks for the 3D Space Rocks architecture.

Creates reusable particle and impact-feedback effects for 3D Space Rocks with performance-aware defaults and gameplay event integration.

Implements a Babylon GUI screen or overlay pattern for 3D Space Rocks, including keyboard navigation, accessibility checks, and state lifecycle hooks.

Sets up the Babylon.js engine, scene, camera, lighting, and asset loading pipeline for 3D Space Rocks.

Enhance a hook-scaffolded EJS session journey file with semantic content (problem/intent, agents involved) and confirm initialization.

Capture sub-agent decisions, rationale, and inter-agent handoffs during multi-agent Engineering Journey System (EJS) workflows. Ensures that delegated work is properly attributed and traceable.

Analyze a Product Requirements Document (PRD) and generate a complete team of GitHub Copilot custom agents and reusable skills tailored to the project. Use this skill when asked to create, scaffold, or design a development team from a PRD or technical specification.

Build a Feature PRD that captures a new feature request in the context of an existing, completed project. Use this skill when the initial PRD has been implemented and you need to add a new feature without regenerating the entire project plan or agent team.

Build a comprehensive Product Requirements Document (PRD) or Technical Specification from a user's idea, concept, or research document. Use this skill when asked to create, draft, or formalize a PRD, spec, or requirements document.

Initialize and manage EJS artifacts throughout session lifecycle (Session Journey initialization, continuous updates, and finalization; ADR only when significant)

Step-by-step process for adding a new event type to the Copilot Agent Activity Visualizer. Touches four locations in sequence: event schema definition, hook emitter registration, state machine transition handling, and web UI rendering rule. Use this skill whenever a new lifecycle event type needs to be introduced beyond the MVP set.

Create a README.md file for the project

Analyze a Product Requirements Document (PRD), Product Vision with Feature documents, or Feature PRD and generate a complete team of GitHub Copilot custom agents and reusable skills tailored to the project. Use this skill when asked to create, scaffold, or design a development team from requirements documents.

Build a Feature PRD that captures a feature — either as a new addition to an existing project, or as part of initial project decomposition from a Product Vision. Use this skill when you need a self-contained feature document with user stories, requirements, and implementation tasks.

Decompose an existing monolithic Product Requirements Document (PRD) into a Product Vision document and individual Feature documents. Use this skill when you want to break a large PRD into independent, self-contained features that can be prioritized, built, and delivered separately.

Process for creating a fixture-driven integration test that exercises the full hook-emitter → JSONL → ingest-service → state-machine → web-UI pipeline for the Copilot Activity Visualiser. Use this skill whenever you need to write an end-to-end integration test without requiring a live Copilot CLI session or a running browser.

Scaffold a new ingest provider for the copilot-trace-importer pipeline (e.g., Claude Code, Cursor, Codex). Creates the provider source file under `src/providers/`, the quirks doc under `docs/providers/<name>.md`, the registry entry in `BUILTIN_PROVIDERS`, and the unit-test fixture layout — all without touching the orchestrator. Use this skill whenever someone says "add a new provider" or "add support for <tool> as an ingest source".

Scaffold a new sink (destination) for the copilot-trace-importer pipeline against the ADR-005 Sink interface. Creates the sink source file under `src/sinks/`, the configuration doc under `docs/sinks/<name>.md`, wires the CLI flag through cli-engineer, and adds per-sink success/failure counters to `DatastoreImportResult`. Use this skill whenever someone says "add a new sink", "add an OTLP / Parquet / warehouse / cloud destination", or "ship a codeburn-export sink".

Add a new regex-based redaction pattern (or amend an existing one) for the redaction engine with the required fixtures, negative-case tests, policy-preset wiring, and source citation. Use this skill whenever someone says "add a redaction pattern for <secret type>", "we found a credential format the redactor misses", or "extend the strict/moderate/permissive presets".

Author a new Architecture Decision Record (ADR) or amend an existing one in `docs/ADR-NNN-<slug>.md`, following the project's existing `docs/ADR-TEMPLATE.md`. Use this skill whenever a change introduces a public-contract breakage, a new architectural pattern, or a schema/format bump: new provider hook, sink interface change, new redaction policy preset, datastore format change, plugin manifest format change, etc.

Analyze a Product Requirements Document (PRD), Product Vision with Feature documents, or Feature PRD and generate a complete team of GitHub Copilot custom agents and reusable skills tailored to the project. Use this skill when asked to create, scaffold, or design a development team from requirements documents.

Build a complete end-to-end project story from EJS journey and ADR files. Use when: "build story", "generate story", "tell the story", "project narrative", "end-to-end story", "full story", "what happened", "project history", "summarize all sessions". Reads journey sessions and ADRs, synthesizes a chronological narrative covering what was built, how it was built, and collaboration perspectives (human, human+agent, agent, agent-to-agent). Outputs to chat and saves to ejs-docs/narratives/.

Author a CAPS-aligned Markdown content chunk for an eZansiEdgeAI content pack. Use this skill each time a new curriculum topic chunk is created — there will be 3+ chunks and 2+ worked examples per Grade 6 Maths topic across Terms 1–4.

Scaffold a new Android feature module for eZansiEdgeAI with standard structure: Activity/Fragment or Composable, ViewModel, Repository interface, DI setup, and test stubs. Use this skill each time a new feature screen is added (chat, topics, profiles, preferences, library).

Initialize an Engineering Journey System (EJS) session by creating a Session Journey file, refreshing the ADR/journey database index, and setting up metadata for continuous recording throughout the session.

Finalize an Engineering Journey System (EJS) session by completing all journey sections, populating machine extracts, evaluating the ADR decision rubric, and optionally creating an ADR document.

Creates a new SQLite query helper function in the db/ directory, following project conventions: TypeScript-typed parameters and return values, async/await with expo-sqlite v2, integer-based currency amounts, and a corresponding Jest unit test stub. Use this skill whenever a new database operation is needed.

Creates a new React Native screen file following project conventions: TypeScript typed navigation props, basic layout scaffold, StyleSheet or NativeWind class setup, and registration in the root navigator. Use this skill whenever a new screen needs to be created in the app.

Creates a component test file using React Native Testing Library (RNTL) with the correct project mock setup for SQLite, navigation, and context providers. Use this skill whenever a new React Native component or screen needs a test file.

Analyze a Product Requirements Document (PRD) and generate a complete team of GitHub Copilot custom agents and reusable skills tailored to the project. Use this skill when asked to create, scaffold, or design a development team from a PRD or technical specification.

Build a comprehensive Product Requirements Document (PRD) or Technical Specification from a user's idea, concept, or research document. Use this skill when asked to create, draft, or formalize a PRD, spec, or requirements document.

Initialize an Engineering Journey System (EJS) session by creating a Session Journey file, refreshing the ADR/journey database index, and setting up metadata for continuous recording throughout the session.

Finalize an Engineering Journey System (EJS) session by completing all journey sections, populating machine extracts, evaluating the ADR decision rubric, and optionally creating an ADR document.

Create a README.md file for the project

Capture sub-agent decisions, rationale, and inter-agent handoffs during multi-agent Engineering Journey System (EJS) workflows. Ensures that delegated work is properly attributed and traceable.

Builds traceable unit, integration, and e2e test suites from feature requirements. Use when adding or expanding automated verification for Mindmap Dungeon features.

Implements deterministic rule evaluation for note validation, quality scoring, and progression formulas. Use when adding or changing gate/rubric/reward logic.

Implements local-first subject and room persistence with atomic writes, backup retention, and migration hooks. Use for filesystem-backed data operations in Mindmap Dungeon.

Scaffolds a new Mindmap Dungeon feature module with aligned core, feature, UI, and test entry points. Use when introducing a new feature area or extending phase-specific modules.

Implement a Vib'N browser audio flow for microphone permission, capture, pitch analysis, or calibration while preserving privacy and low-latency constraints.

Build a Vib'N test suite for a feature area using the PRD ownership matrix, acceptance criteria, and the project's unit, integration, and manual test strategy.

Create a typed Vib'N state or rules module for gameplay, progression, or shared configuration. Use this for reducers, state machines, selectors, score models, and tuning configs.

Create or extend a Vib'N screen using the project's routed screen structure, domain adapters, and accessibility requirements. Use this for Home, Game, Results, or Progress screen work.