Research

Prepare newsletters for publication by validating format, structure, frontmatter, and content. Use when reviewing drafts before sending.

Persistent graph-based memory for AI agents via KIP (Knowledge Interaction Protocol). Provides structured knowledge storage (concepts, propositions), retrieval (KQL queries), schema discovery (META), and memory metabolism. Use when: (1) remembering user preferences, identities, or relationships across sessions, (2) storing conversation summaries or episodic events, (3) building and querying knowledge graphs, (4) the user says "remember this", "what do you know about me", or asks about past conversations, (5) needing to maintain context continuity across sessions. Requires HTTP access to a KIP backend (anda_cognitive_nexus_server).

This skill should be used when the user asks to "verify claims", "fact check", "validate documentation", "check sources", or needs verification of external source references. Provides patterns for systematic fact verification using Context7 and WebSearch.

This skill should be used when the user asks to "use serena", "semantic search", "symbol analysis", "find references", "code navigation", or needs Serena MCP guidance. Provides Serena tool usage patterns.

Manages MkDocs documentation site and API references for ComposeWebView. Use when creating, updating, or building documentation, adding guides, or generating API docs. Handles mkdocs serve, build, and validation.

Aggregate multi-reviewer feedback into consolidated, actionable recommendations. Use when relevant to the task.

Scrape documentation websites into organized reference files. Use when converting docs sites to searchable references or building Claude skills.

Synthesize audience insights from multiple data sources into unified personas and segments. Use when relevant to the task.

Scrape documentation websites into organized reference files. Use when converting docs sites to searchable references or building Claude skills.

Resume exploration from where previous Claude session left off by reading the exploration journal (docs/exploration/). Use at start of session when user says "continue", "resume", or "pick up where we left off".

Automatically save exploration findings, discoveries, and current state to the exploration journal (docs/exploration/). Use when making important discoveries or completing a phase of work. Ensures future Claude sessions can continue where this session left off.

Create comprehensive technical documentation including API docs, component libraries, README files, architecture diagrams, and developer guides using tools like JSDoc, Storybook, or Docusaurus. Use when documenting APIs, creating component documentation, writing README files, generating API references, documenting architecture decisions, creating onboarding guides, maintaining changelogs, documenting configuration options, or building developer documentation sites.

Research topics thoroughly and write comprehensive, well-structured content including articles, documentation, blog posts, and technical writing with proper citations and sources. Use when writing blog posts, creating technical articles, researching topics, gathering sources, writing documentation, creating educational content, or producing research-backed content.

Research competitors, analyze market positioning, identify differentiators, and understand competitive landscape to inform product strategy and positioning. Use when researching competitors, analyzing features, identifying market gaps, understanding pricing strategies, evaluating competitive advantages, researching market trends, or informing product decisions.

Reference manual for framework methodology throughout session. Provides guidance on cognitive architecture that replaces default AI assistant behaviors with systematic patterns proven through collaborative experience. Consult this manual throughout session when applying framework procedures.

Best practices for designing reproducible experiments

Orchestrates Stage 0 research and planning for JUCE plugins - creates architecture.md and plan.md contracts through subagent delegation. Use when creative brief exists and plugin needs DSP architecture specification, complexity assessment, or implementation planning. Invoke via /plan command, natural language (plan architecture, research DSP), or as first implementation step.

Use when creating temporary files, drafts, experiments, or any content that should not be committed to version control. Ensures proper placement in .claude/.scratch with gitignore configuration.

Fix bugs, add features to completed plugins. Includes versioning, backups, regression testing, changelog automation. Auto-detects deep-research handoffs to preserve investigation context. Trigger terms - improve, fix, add feature, modify plugin, version bump, rollback

Use when C# nullable reference types and value types for null safety, nullable annotations, and patterns for handling null values.