Converts documents and knowledge gathered from Microsoft Copilot into well-structured, SharePoint-compatible markdown files. Use when a user has content from Copilot (summaries, research, meeting notes, process steps) and wants to produce a formatted page for a SharePoint site, wiki, or knowledge base. Triggers include "create a markdown file from this", "format this for SharePoint", "write this up as a knowledge base article", "turn this Copilot output into a page", or when a user pastes Copilot-generated content and asks for it to be documented.
Search the Claude knowledge graph vault for past Q&A sessions, concepts, and developer knowledge. Use when you need to find information from previous conversations, recall how something was done before, or look up stored technical knowledge. Supports Korean and English queries.
Ingest or update a codebase in the agent-knowledge base. First run bootstraps the knowledge base from scratch; subsequent runs are incremental (only changed/new/deleted files reprocessed). Uses tree-sitter for zero-token structural extraction. Trigger on "/knowledge-ingest", "ingest this codebase", "load this into knowledge", "scan this project", "index this repo", "update knowledge", "refresh knowledge", "re-ingest". --- # knowledge-ingest Populate or update agent-knowledge from a codebase. Tree-sitter extracts structure (zero LLM tokens), then the agent distills clusters into knowledge entries + graph edges via existing MCP tools. **First run**: full ingest — scans all files, creates entries from scratch. **Subsequent runs**: incremental — only reprocesses files whose SHA256 changed, adds entries for new files, removes entries for deleted files. The `.knowledge-ingest-cache.json` file in the target directory tracks state between runs. ## When to use - **Onboarding a new project** — bootstrap the knowledge base so future sessions have context - **After a refactor** — re-run to update subsystem boundaries and relationships - **Periodic refresh** — re-run after significant changes to keep knowledge current - **Importing documentation** — PDFs, architecture diagrams, or external URLs ## When NOT to use - Single-file changes — just write a knowledge entry manually - No code changes since last ingest — the cache will skip everything anyway (fast no-op) ## Procedure ### Phase 0 — Validation 1. Confirm the target path exists and is a directory. 2. Detect project name: - Check `package.json` → `name` field - Check `Cargo.toml` → `[package] name` - Check `go.mod` → `module` line - Check `pyproject.toml` → `[project] name` - Fall back to directory basename 3. Check for `.knowledge-ingest-cache.json` in the target directory. If found, load it — this is an incremental run. Report how many files changed since last ingest. ### Phase 1 — Structural Extraction (zero tokens) 4. Loc
Use when user says "update/refresh knowledge graph", "graph status", "blind spots", "CLAUDE.md coverage", or "init knowledge graph". Also use when receiving a "[kg auto-trigger]" message injected by hooks. Do not use for regular coding tasks.
Capture a specific piece of knowledge, constraint, or decision to the Kindex knowledge graph. Use when the user says "remember this", "add this to kindex", or "this is important".
Use when Claude makes repeated mistakes, users correct behavior, tool failures indicate missing knowledge, or managing learning via /coach commands.
Bootstrap a knowledge store by exploring codebase architecture — use when starting with a new or empty project, seeding knowledge, or running /bootstrap
Query mahdi navigator about Knowledge navigator for Mahdi. Use when user asks to "ask mahdi" or needs information from this knowledge base.
- 📁 references/
- 📁 scripts/
- 📄 SKILL.md
Search and retrieve knowledge from agentic_kb knowledge base. Use when the user requests to search the KB, asks "How do I..." questions that should consult the KB, wants to document new knowledge, or at session start to update the KB submodule. Also use when User wants to udpate the knowledge base with new knowledge. Knowledge Capture when you learn new, reusable knowledge during tasks. Supports Typesense (fast full-text search), FAISS (semantic vector search), and ripgrep (exact pattern matching). All KB is Obsidian formatted and can be browsed easily and visually with network maps in Obsidian.
Self-amendment MCP server framework with layered skill architecture and blockchain auditability. Use when the user wants to manage knowledge, evolve skills, track changes with blockchain, audit skill health, promote knowledge between layers, or perform persona assembly for decision support. --- # KairosChain - Self-Amendment MCP Server Framework KairosChain provides a layered skill architecture (L0/L1/L2) where skills can evolve, promote, and audit themselves with blockchain-backed auditability. ## Architecture ### Three-Layer System - **L0 (Constitution/Law)**: Immutable safety rules and meta-governance. Changes require human approval and full blockchain recording. - **L1 (Knowledge)**: Project knowledge in Anthropic skills format. Changes recorded with hash references. - **L2 (Context)**: Temporary session context. Free modification, no blockchain recording. ### Core Capabilities #### Knowledge Management - `knowledge_list` / `knowledge_get` - Browse and read L1 knowledge skills - `knowledge_update` - Create, update, or delete L1 knowledge with blockchain recording - `context_save` - Save temporary L2 context for session work #### Skill Evolution - `skills_evolve` - Propose and apply changes to L0 skill definitions (requires human approval) - `skills_rollback` - Version management with snapshot and rollback capabilities - `skills_promote` - Promote knowledge between layers (L2→L1, L1→L0) with optional Persona Assembly #### Blockchain Auditability - `chain_status` / `chain_verify` - Check and verify blockchain integrity - `chain_history` - View skill transitions, knowledge updates, and state commits - `chain_record` - Record data to the blockchain - `state_commit` - Create snapshots of all layers for auditability #### Health & Safety - `skills_audit` - Audit knowledge health across layers (conflicts, staleness, dangerous patterns) - `tool_guide` - Dynamic tool discovery and workflow recommendations #### Persona Assembly - Multi-perspective decision support using pe
- 📁 .claude/
- 📁 .claude-plugin/
- 📁 .github/
- 📄 .gitignore
- 📄 .mcp.json
- 📄 CHANGELOG.md
Intelligent skill knowledge gateway. Routes tasks to the right knowledge without loading all skills into context. MUST be consulted before any coding task — call the search_skills MCP tool to retrieve relevant expertise from 100+ indexed skills covering Swift, SwiftUI, concurrency, testing, architecture, performance, and security.
LLM-compiled knowledge base manager. Activates when user works with wiki directories, mentions knowledge base management, asks knowledge questions in a project with a wiki, wants to ingest/compile/query/lint knowledge, or uses /wiki commands. Also activates when user says "wiki", "knowledge base", "ingest", "compile wiki", "add to wiki", "search wiki", or asks a factual question in a directory containing .wiki/ or when ~/wiki/ exists.
