Research

Generate, edit, or transform images with Gemini Nano Banana using bundled Python scripts (Flash or Pro) including aspect ratio, resolution, image-to-image edits, logo overlays, and reference images. Use when users request image generation, image edits, image-to-image transformations, logo placement, or specific aspect ratios or resolutions.

Fetch up-to-date documentation and code examples for any library or framework. Use when needing API references, code examples, library documentation, or framework guides. Supports React, Next.js, MongoDB, Supabase, and thousands of other libraries.

Example skill demonstrating YAML best practices. Use when learning skill structure, reviewing formatting standards, or creating new skills as a reference.

⚠️ DEPRECATED - Use faber-planner + faber-executor instead.This skill is preserved for reference only.See: SPEC-20251208-faber-two-phase-architecture.md

Plan work before coding: do repo research, analyze options/risks, and ask clarifying questions before proposing an implementation plan. Use when the user asks for a plan, design/approach, scope breakdown, or implementation steps.

Execute and coordinate work on PLAN files with phased breakdown. Tracks progress via JSON state, coordinates worker sub-agents in worker mode, and manages commits. Use when user references a PLAN file or asks to continue/execute a plan.

Comprehensive proofreading and editing for biblical, pastoral, and theological writing. Use when the user requests grammar checking, spelling correction, proofreading, or style improvement for sermons, sermonettes, devotionals, blogs, academic papers, or book chapters. Specializes in US English, pastoral tone, academic theological writing, and creative devotional styles.

Comprehensive biblical accuracy verification for sermons, teachings, and theological content aligned with United Church of God theology. Validates scripture references, quotations, contextual integrity, theological soundness per UCG doctrine, and performs deep linguistic analysis of Greek and Hebrew original language texts to ensure fidelity to biblical meaning. Use when writing or reviewing any biblical, theological, or sermon content.

Validate completed implementation against plan tasks and acceptance criteria. Sixth phase of research-discussion-specification-plan-implement-review workflow. Use when: (1) Implementation phase is complete, (2) User wants validation before merging/shipping, (3) Quality gate check needed after implementation. Reviews ALL plan tasks for implementation correctness, test adequacy, and code quality. Produces structured feedback (approve, request changes, or comments) - does NOT fix code.

Understanding Reinforcement Learning from Human Feedback (RLHF) for aligning language models. Use when learning about preference data, reward modeling, policy optimization, or direct alignment algorithms like DPO.

Validate that Skill() invocations use full prefixed names. Use when (1) before creating a pull request to ensure skill references resolve correctly, (2) after adding new skills to verify invocations use proper names, (3) when verifying repository health, (4) as part of comprehensive validation alongside other check skills.

Recover lost context after session compaction or when information from previous sessions is needed. Use when: user mentions "what were we working on", "I lost context", "before the compact", "previous session", or asks about decisions/implementations/discussions that aren't in current context. Also use proactively when you notice references to prior work you lack context for.

Creates formal academic research papers following IEEE/ACM formatting standards with proper structure, citations, and scholarly writing style. Use when the user asks to write a research paper, academic paper, or conference paper on any topic.

Natural language wrapper for research command - automatically triggers /research when users ask questions requiring deep research, best practices lookup, or multi-source information gathering

Advanced optimization for trading: OCO, multi-objective, DRO, MIP, Bayesian opt, plus convex/Markowitz/BL references.

Test system resilience through controlled failures. Use when validating fault tolerance, disaster recovery, or system reliability. Covers chaos experiments.

This skill should be used when evaluating UI components against UX best practices. Use for reviewing buttons, navigation elements, spacing, visual hierarchy, or any interface element. Provides a systematic 3-dimension framework (Position, Visual Weight, Spacing) aligned with industry standards (Balsamiq, Nielsen heuristics). Invoke when user asks to "review UX", "check button design", "evaluate layout", or references design guidelines.

Transform raw research into actionable insights that inform design decisions. Use during Define phase after completing research.

Use when user says "synthesize goals", "show goals", "what are my goals", "update goals", "show non-goals", "what am I building", "project direction", or asks about the overall direction or intent of the project - generates two markdown files summarizing the user's goals based on approved story nodes (what the goals ARE) and rejected story nodes with notes (what the non-goals ARE).

Orchestrates multi-model deliberation from Claude, Gemini, and Codex.INVOKE THIS SKILL when user wants:- Multiple AI perspectives: "ask the council", "get opinions", "what do the models think"- Debate/both sides: "both sides of", "pros and cons", "I'm torn between", "arguments for and against"- Stress-testing: "poke holes", "what could go wrong", "find flaws", "what am I missing", "blind spots"- Choosing between options: "help me choose", "which should I pick", "A vs B vs C"- Deep understanding: "deeply understand", "thorough research", "comprehensive analysis"- Direct model query: "ask Claude directly", "just Gemini", "Codex only", "skip the council"