Unify 6+ memory systems into AgentDB with HNSW indexing for 150x-12,500x search improvements. Implements ADR-006 (Unified Memory Service) and ADR-009 (Hybrid Memory Backe — from…
Out-of-core DataFrame for billion-row data via lazy evaluation and memory-mapped files. Use when data exceeds RAM (10 GB–TB) for fast aggregation, filtering, virtual columns, and…
Asks questions and gets synthesized answers grounded in vault history with source citations. Use when: (1) /vault-ask to reason over vault knowledge, (2) user wants to…
Use when curated vault material may need to become stable canonical knowledge, or when an agent wants to update an existing canonical note without direct authority.
Capture project-internal knowledge into the Obsidian wiki as it's produced. Use PROACTIVELY and IMMEDIATELY after: adding a new data source (new scripts// folder),…
Use when analyzing vault structure, finding orphan notes, discovering missing connections, identifying bridge concepts, or checking vault health from a graph perspective.
Use when user says 'lint the vault', 'health check', 'find stale notes', 'vault audit'. Scans for contradictions, orphan pages, stale claims, missing cross-refs.
Use when storing, retrieving, or managing persistent memory across the Starlight Vaults — handles reading, writing, querying, and organizing entries across all vaults.
Bootstrap an agent collaboration system into an Obsidian vault — memory, protocols, task boards, and per-client instruction files via a conversational interview.
Organize and maintain the user's Obsidian vault for Hermes Agent. Apply when user asks to reorganize, clean up, classify notes, or when documenting system configs in the vault.
Periodic on-demand audit pass to keep the entire pod vault current and consistent. Complements the per-ingest enforcement (which prevents drift in real-time) by catching anything…
Write a design proposal to the project Obsidian vault. Use when the user asks to design, plan, or propose changes to regime inference, evaluation, model selection, or any major…
Use when user asks 'what do we know about X?', 'have we solved this before?', 'find notes on Y'. Reads vault index → drills into relevant pages → synthesizes answer with…
Read structured artifacts from an Obsidian vault following the vault's CLAUDE.md frontmatter schema. Supports four operations: slug lookup, frontmatter filter (with `where`…
Automates HashiCorp Vault secret rotation using the Vault HTTP API and dynamic secrets engines. Manages database credential leases, PKI certificate renewal, and AWS STS token…
Interactive Obsidian vault configurator. USE WHEN setting up obsidian vault, creating second brain, initializing knowledge base, new vault, vault bootstrap, configure obsidian,…
Show status of all LLM Wiki vaults — page counts, source counts, last activity, and git status. Use when user wants to see vault status, list vaults, or check wiki health.
Validates vault frontmatter (Zod schema) and wiki-link integrity. Phase 1: hard gate at session-end. Used by session-end skill to block close on invalid vault state.
Use when maintaining the vault ITSELF as a system, not its content: knowledge-graph build/rebuild/query (graphify), second-brain mapping, vault diagnose/audit/hygiene, drift…
Safely connects Gmail, Calendar, Drive, Atlassian (Jira/Confluence), Notion, GitHub, Salesforce, and dozens of other enterprise tools via a single MCP endpoint.
Use when VibePro work needs codebase-memory-mcp impact context for changed files, call paths, routes, symbols, or risk hints without treating topology as correctness evidence.
Maintainer-only skill for refreshing VitaeContext wiki knowledge from official sources. Use only from a local repository clone when a maintainer asks to refresh one module, audit…
GPU VRAM management patterns for sharing memory across services (Ollama, Whisper, ComfyUI). OOM retry logic, auto-unload on idle, and service signaling protocol.
Reward and motivation system for AI agents. Dopamine-like wanting, not just doing. Part of the AI Brain series. — from majiayu000/claude-skill-registry
Erstellt hochwertige deutsche Wikipedia-Artikel aus anderssprachigem (meist englischem) Wikitext. Verwende diesen Skill immer, wenn der Nutzer einen Wikipedia-Artikel auf Deutsch…
Crea una nuova wiki tecnica LLM-mantenuta da zero al pattern Karpathy esteso. Genera struttura cartelle (raw/inbox/wiki) e CLAUDE.md/index.md/log.md/tags.md adattati al dominio.
Use when building or maintaining a durable, compounding knowledge base queried by feeding markdown into a long-context model, with no RAG, chunking, or embeddings.
Generate structured changelogs from git history. Use when user asks \"what changed recently\", \"generate a changelog\", \"summarize commits\" or user wants to understand recent…
Default vault-mutation transport for claude-obsidian v1.7+. Wraps the Obsidian CLI (Obsidian 1.12+) as the preferred way to read, write, search, and modify vault notes from Claude…
Produce a token-bounded context pack from the Obsidian wiki — a compact, structured slice of the most relevant pages for a topic or recent activity, designed for downstream…
Claude™ is a trademark of Anthropic PBC. ClaudSkills (also referred to as Claude Skills or Claude Code Skills Catalog) is an independent community-curated registry of SKILL.md files, not affiliated with, endorsed by, or sponsored by Anthropic.
Install ClaudSkills — browse 70k+ skills offline, one tap from your home screen.