MCP App StoreMCP App Store
Operate an Obsidian vault as a self-rewriting, AI-first knowledge base that saves, reconciles, and propagates insights across notes with a suite of automated co
Operates an Obsidian vault as a living, self-rewriting second brain. This skill provides a comprehensive set of commands and scripts to read, write, reconcile, synthesize, and maintain a vault in an AI-first format: notes are saved with rich frontmatter, changes propagate across indexes and kanban boards, contradictions are detected and reconciled, and nightly/weekly agents can consolidate and synthesize knowledge automatically. The repo also includes a research toolkit (X/Grok, Perplexity, NotebookLM, YouTube, podcasts) to ingest external sources into the vault.
Use this skill whenever the agent needs to manage or maintain an Obsidian vault: saving conversation insights, creating daily notes, bootstrapping a new vault, running health checks, ingesting research, exporting snapshots, or running scheduled consolidation and syntheses. It triggers on explicit slash commands (e.g. /obsidian-save, /obsidian-daily, /obsidian-health) or when the user asks Claude to read, write, search, or reconcile vault content.
_CLAUDE.md and other canonical files.Designed primarily for Claude/Claude Code surfaces and Claude-headless automation patterns, but the commands and scripts are platform-agnostic and can be used with other agent CLIs that support hook scripts and file I/O.
Comprehensive Obsidian vault management skill with 20 scripts covering bootstrapping, health checks, link triage, research toolkit integration, and more. Scripts are well-structured with argparse CLI interfaces. 6 of 20 scripts succeeded; most failures are due to missing required --path arguments (expected in DRY_RUN mode) or inter-script import issues in the isolated test environment. The skill provides a rich second-brain workflow for Obsidian users.
curl|bash pattern only appears in a comment (documentation), not executed by the script itself. git pull --ff-only auto-update is a design choice for keeping the skill updated. triage_links.py's Anthropic API call uses env var for the key, which is standard. No hardcoded credentials, no exfiltration, no malicious instructions. Build failures are expected in DRY_RUN mode since scripts need a vault path.
Development Worktree
Create an isolated git worktree for feature work, auto-run project setup, and verify a clean test baseline before development.
WRDS Query & ETL Enforcement
Standards and enforcement guidance for querying WRDS data and running SAS/ETL on the WRDS grid—includes query validation, SGE submission patterns, and performan
Academic Research Search
Search academic literature across multiple sources, deduplicate results, resolve DOIs, and surface trusted papers with concise takeaways.
Readwise Reader Document Management
Manage Readwise Reader documents: list, save, search, move, tag, highlight, export and bulk-edit via official and custom CLIs.
Bounty Hunter — Atlas
Persona skill: 'Atlas' — a profit-focused developer persona for discovering, evaluating and executing paid bounties or freelance tasks with ROI-aware workflows.
Junshi — Research Advisor
Daily strategic research advisor that scans arXiv/venues, digests papers, and proposes bold, ranked research ideas tailored to the user's profile.
Full Stack Builder
End-to-end builder that scaffolds, implements, tests, and optionally deploys web and API applications from a natural-language specification.
ezBookkeeping API Tools
Command-line API tools for ezBookkeeping: record and query transactions, retrieve accounts/categories/tags, and fetch exchange rates for self-hosted personal fi