MCP App StoreMCP App Store
Répondez à des questions à partir d'un wiki Obsidian : cache chaud → index → pages ; synthétisez les réponses avec des citations et archivez éventuellement les résultats.
Lit un wiki Obsidian (cache chaud, index et pages) et répond aux questions de l'utilisateur avec des citations au niveau du bloc. Prend en charge trois modes : Rapide (hot.md + index.md), Standard (hot + index + plusieurs pages) et Profond (synthèse complète du wiki). Utilise un sélecteur de transport pour privilégier les lectures cli/mcp-obsidian/filesystem et peut s'intégrer à un pipeline de récupération optionnel (scripts/retrieve.py) lorsqu'il est disponible. Propose d'archiver les réponses solides dans le wiki sous forme de nouvelles pages et consigne les lacunes lorsque la couverture est insuffisante. Inclut des directives claires sur la discipline des tokens, le style de citation et le moment de revenir aux flux de travail hérités.
Caractéristiques :
retrieve.py pour la récupération BM25/rerankCas d'utilisation :
Wiki Query is an Obsidian vault querying skill that retrieves and synthesizes answers from an Obsidian wiki with citations. It features strong security posture with explicit instructions to treat vault content as untrusted and ignore embedded commands. Well-structured SKILL.md with clear depth levels (quick/standard/deep), provenance rules, and citation requirements. No bundled scripts to test. Niche but well-executed for Obsidian+Claude Code users.
Exemplary security-aware design: explicitly instructs ignoring embedded commands, fake role messages, requests for secrets, and egress attempts. Read-only by design. Clear provenance and evidence assessment rules.
Cost Tracker
Monitor agent session costs, set budget alerts, and get actionable token-spend optimizations to keep multi-session workflows within budget.
Audit Agents/Skills/Commands
Run a quantitative quality audit on agents, skills, and commands to check production readiness and get prioritized recommendations.
NotebookLM Research Agent
End-to-end research-to-content pipeline: ingest sources into Google NotebookLM, run deep cited research, generate downloadable artifacts, and produce polished c
Forcemanager Automation (Rube MCP)
Automate Forcemanager tasks via Rube MCP (Composio); discovers tools, ensures active connections, and runs toolkit workflows safely.
Confluence Expert
Manage Confluence spaces, templates, permissions and documentation workflows; create page hierarchies, macros and governance for team knowledge bases.
Learn: From Raw Materials to Published Output
Run a disciplined six-phase research-to-publish workflow (collect, digest, outline, fill, refine, publish) for deep domain research and article preparation.
draw.io Diagram Skill
Create, edit, lint, and export draw.io diagrams; includes export helpers, SVG linting, and repository QA for clean architecture and icon-based diagrams.
GitHub Explorer
Deep-dive, multi-source analysis of GitHub projects—architecture, community health, issues, commits, and competitive landscape.