What’s New

Understand-Anything v2.3.1

v2.3.1
Added
  • Introduce `/understand-knowledge` skill for analyzing LLM wiki knowledge bases with entity extraction, implicit relationships, and topic clustering across five phases
  • Add `article-analyzer` agent that extracts implicit knowledge from wiki articles including entities, claims, and semantic edges
  • Add `assemble-reviewer` agent that performs post-merge quality review and verifies cross-batch consistency
  • Add KnowledgeGraphView dashboard component with force-directed visualization, search, tour highlighting, and relationship-typed edge styling
  • Introduce `.understandignore` support for user-configurable file exclusion with IgnoreFilter and IgnoreGenerator
  • Add Phase 0.5 in `/understand` workflow that pauses for user confirmation after generating ignore file
  • Implement subdomain graph merging in Phase 0 to merge multiple domain-specific graphs into unified graph with deduplication
  • Add batch graph merging Python script with ID normalization, complexity mapping, and detailed fix reports
  • Support incremental updates with structural fingerprinting and `--auto-update` / `--no-auto-update` flags
  • Add language and framework context injection for architecture analysis
  • Expand review paths with inline validation option and `--review` flag for full LLM review
  • Add type aliases for flexible input such as `func` → `function` and `doc` → `document`
  • Add Korean and Spanish README translations
  • Add animated showcase GIFs for structural and domain views
Changed
  • Expand node types from 13 to 21, adding domain, flow, step, article, entity, topic, claim, and source types
  • Expand edge types to 35 covering structural, behavioral, data flow, dependency, semantic, infrastructure, domain, and knowledge relationships
  • Enhance project scanner to handle non-code files including configs, docs, infrastructure, and data with explicit fileCategory assignment
  • Implement deterministic script-based file discovery with improved language and framework detection
Fixed
  • Include access token in dashboard URL
  • Fix connected edges to highlight correctly on node selection
What's New
/understand-knowledge — Knowledge Base Analysis

New skill for analyzing Karpathy-pattern LLM wiki knowledge bases. Detects raw sources and wiki markdown with wikilinks, then produces interactive knowledge graphs with entity extraction, implicit relationships, and topic clustering across five phases (DETECT → SCAN → ANALYZE → MERGE → SAVE).

Comes with two new agents:

  • article-analyzer — extracts implicit knowledge from wiki articles: entities (people, tools, papers), claims (decisions, assertions), and semantic edges (builds_on, contradicts, exemplifies, authored_by, cites)
  • assemble-reviewer — post-merge quality reviewer that recovers dropped nodes/edges, remaps unknown types, and verifies cross-batch consistency

A dedicated KnowledgeGraphView dashboard component provides force-directed visualization with search, tour highlighting, and relationship-typed edge styling.

.understandignore Support

User-configurable file exclusion for /understand analysis:

  • IgnoreFilter — runtime filtering with hardcoded defaults (node_modules, build outputs, lock files, binaries) plus layered .understandignore files from .understand-anything/ and project root
  • IgnoreGenerator — auto-generates a starter .understandignore by parsing your existing .gitignore and detecting project directories
  • New Phase 0.5 in the /understand workflow pauses for user confirmation after generating the ignore file
/understand Pipeline Improvements
  • Subdomain graph merging (Phase 0) — merges multiple domain-specific graphs into one unified graph with deduplication
  • Batch graph merging — new Python script with ID normalization, complexity mapping, and detailed fix reports
  • Incremental updates — structural fingerprinting with --auto-update / --no-auto-update flags
  • Language/framework context injection for architecture analysis
  • Expanded review paths — inline validation vs. full LLM review via --review
Schema & Type Expansion
  • Node types expanded from 13 → 21 (added domain, flow, step, article, entity, topic, claim, source)
  • Edge types expanded to 35 covering structural, behavioral, data flow, dependency, semantic, infrastructure, domain, and knowledge relationships
  • Type aliases for flexible input (func → function, doc → document, etc.)
Project Scanner Improvements
  • Now handles non-code files (configs, docs, infrastructure, data) with explicit fileCategory assignment
  • Deterministic script-based file discovery with improved language and framework detection
Documentation & Internationalization
  • Korean (README.ko-KR.md) and Spanish (README.es-ES.md) README translations
  • Animated showcase GIFs for structural and domain views
  • Multi-platform badges (Codex, Copilot, Gemini CLI, OpenCode)
Fixes
  • Dashboard URL now includes access token
  • Connected edges highlight correctly on node selection
  • Stable layout and scoped infrastructure filter in graph view
  • Marketplace JSON schema validation fixes
  • Edge weight coercion for graph merge scripts
View original