kmgraph

Shared upgrade inspector module — detects missing dirs, templates, and config fields for an existing KG

Manually link existing lesson or ADR to a GitHub issue with bidirectional references

Display all configured knowledge graphs from ~/.claude/kg-config.json

Initialize and manage meta-issue tracking for complex multi-attempt problems

List migration restore points and roll back knowledge graph files to a previous archived state

Search across project memory systems (lessons, decisions, knowledge graph, sessions)

Restore archived MEMORY.md entries from MEMORY-archive.md to restore previously archived context

Create a summary of the current active chat session

Detect installed AI coding tools and configure KMGraph for each one — useful when you install a new AI tool after initial setup

Initialize issue tracking for a specific problem or enhancement with structured documentation and Git branch creation

Display active knowledge graph status, stats, and quick command reference

Change the active knowledge graph. Subsequent skills will operate on the selected KG.

Automated knowledge sync orchestrator — replaces 4-step manual pipeline with 1 command

Update an existing documentation file — plugin/project documentation (--user-facing) or knowledge graph content

Extract structured insights from lessons-learned and sync to knowledge graph with git metadata preservation

Synchronize Knowledge Graph extraction with active plans and local/GitHub issue tracking

Add a new category to an existing knowledge graph with optional custom prefix

Archive stale MEMORY.md entries to prevent bloat while preserving historical context

Document lessons learned, problems solved, and patterns with git metadata tracking

Scan active knowledge graph for potentially sensitive information before public sharing

Interactive wizard to set up pre-commit hooks for sensitive data detection

Create Architecture Decision Records with auto-filled git metadata, sequential numbering, and index auto-update

Scaffold new documentation files with v0.0.7 language standards, Section 508 compliance, and optional cross-reference auto-update

Extract chat history from Claude and Gemini local log sources

Create comprehensive project handoff documentation for transitions or context limits

Display help for any knowledge graph command — shows purpose, usage, examples, and tips pulled directly from COMMAND-GUIDE.md

Create or register a personal knowledge graph for cross-project lessons

Shared config entry write module — writes or backfills a KG entry in kg-config.json

Shared directory scaffold module — creates the standard KG directory tree

Shared FTS5 rebuild module — offers to build/rebuild the search index for a KG

Shared migration module — archives rules.md and relocates Claude-specific lines to the platform's native config file

Shared template seed module — non-destructive copy of core/templates/ into a KG directory

Creates Architecture Decision Records — interactive wizard with auto-numbered files, git metadata, template population, and index updates. Uses kg_capture MCP tool for platform-agnostic writes.

**Role:** Parse large chat history files, lesson documents, and session logs to extract structured insights and relationships for the knowledge graph. Prevents the main context window from being consumed by 2000+ line source files. Also handles the full KG entry extraction pipeline when delegated from `update-graph`.

Reviews knowledge graph entries for quality, completeness, and proper bidirectional linking. Use when creating or updating KG entries to ensure they meet quality standards.

Captures a single lesson learned from the current session — problem, solution, context, and git metadata. Uses kg_capture MCP tool for platform-agnostic writes.

Detects IDE environment and auto-configures MCP server registration when kg_* tools fail. Enables knowledge graph operations across platforms without manual setup.

Syncs relevant portions of platform config files (CLAUDE.md, GEMINI.md, .cursorrules, etc.) when one is updated. Understands which content belongs in each platform's file — not a full copy, but a targeted sync of applicable sections.

Searches the knowledge graph and memory systems for relevant lessons, decisions, and patterns. Use when the user asks about past work, previous decisions, or familiar problems.

**Purpose:** Receive a structured context payload from `rules-capture` skill, read the target rules file, check for duplicate/conflicting rules, draft the new rule in house style, display for approval, and write on confirmation. Never fires wizards — context payload is always pre-structured.

**Role:** Parse git diffs, commit logs, and file modification history to auto-generate session summaries. Handles the git archaeology so the main context isn't consumed by log output.

Creates a lightweight summary of the current session — what was built, decided, and learned. Checks for open plans, draft ADRs, and uncaptured lessons before saving. Uses kg_capture for platform-agnostic writes.

Executes the full knowledge sync pipeline — scans lessons, extracts KG entries, links to plans/issues, drafts GitHub comments, and refreshes search index. Called by the sync-all thin dispatcher.

**Purpose:** Auto-surface ADR creation when user makes architectural decisions or chooses between technical approaches. Dispatches to the `create-adr-agent` for the full creation workflow.

**Purpose:** Route "capture that" / "remember that" requests to the correct destination (memory, lesson, or ADR) via auto-detection and single confirmation prompt. Provides visibility into where content lands and allows user correction before write.

**Purpose:** Intercept explicit doc-update requests and route to the correct command. Prevents doc edits from bypassing the `/kmgraph:update-doc` wizard, standards validation, and changelog enforcement.

Use when the user is about to push to origin, open a PR, create a PR, merge changes, or says "push and merge", "push and merge with admin", "push to origin", "finishing up", or "ready to push". Scans for all user-facing docs affected by the current branch's changes before any update wizard runs.

**Purpose:** Enforce zero-deviation plan execution when user invokes plan implementation.

**Purpose:** Auto-invoke knowledge graph search when user asks about project history, past decisions, or previously solved problems.

This skill orients the system to the four-layer architecture (context, logic, lifecycle, data) and how each layer coordinates knowledge capture, retrieval, and synchronization. Skill recognizes knowledge capture opportunities, provides command reference for manual interactive use, and guides understanding of how skills and hooks automate triggering.

**Purpose:** Auto-capture lessons when user solves complex bugs, makes breakthroughs, identifies patterns, or completes debugging sessions.

**Purpose:** Detect implicit mid-session behavioral corrections and preferences — phrases the user issues without asking to "capture" anything — and offer to write them to the authoritative rule files (`knowledge/rules.md` or `~/.kmgraph/me.md`), rather than only the MEMORY.md feedback system.

**Purpose:** Prompt for session summary when user indicates they're stopping work, approaching context limits, reaching milestones, or when open plan items, draft decisions, or uncaptured lessons are detected.

Use when a user-facing documentation file (guide, reference, concept page, etc.) is being moved, renamed, or has just been moved or renamed. Detects the stale sidebar entry and updates sidebars.js to match the new path.

Use when a bug, failing test, blocked plan task, integration failure, or reproducibility issue has resisted 3+ distinct fix attempts or 30+ minutes of effort. Activates powerful-tier diagnosis, enforces hypothesis logging, and drives to a structured exit-path decision.

8 hooks across 5 events