MCP App StoreMCP App Store
from deep-recon35
Orchestrate parallel multi-agent reconnaissance rounds to explore a topic deeply and produce a structured recon document (vault/Obsidian friendly).
What it does: Deep Recon orchestrates multi-round, multi-agent reconnaissance sessions (Explorer/Associator/Critic/Synthesizer), persists agent outputs and metrics to disk, and produces a final recon document. When to use it: for thorough exploration, literature-style reconnaissance, or generating an Obsidian-friendly report. What's included: input parsing, vault scanning, parallel round dispatch, metrics persistence, cross-pollination rules, and final document production by the Synthesizer.
Deep Recon is a multi-agent reconnaissance skill for Obsidian vaults. It orchestrates 4 subagent roles (Explorer, Associator, Critic, Synthesizer) across 2-3 rounds to deeply explore a topic and produce a structured recon document. No scripts bundled — it's purely instruction-based, relying on the host agent's Task tool for subagent dispatch. Well-written SKILL.md with clear steps, good compaction resilience via disk persistence, and proper frontmatter.
Pure instruction skill with no bundled scripts. Security is very high as a result. Architecture is solid with good separation between orchestrator and agent roles. Usefulness is moderate — the multi-agent research pattern is valuable but niche to Obsidian/power-users. Several similar skills exist in the ecosystem.
Starlark Dev
Create, debug, and test Kurtosis Starlark packages — write package structure, run dry-runs, and inspect plan execution for reliable orchestration.
Maestro Orchestrate
Orchestrates complex engineering workflows with enforced design and approval gates, child-agent delegation, and session state management.
Run Execute
Orchestrates execution of work items across modes (autopilot, confirm, validate) with scripted init/complete tooling, plan/test/report artifacts and strict gati
Cost Tracker
Monitor agent session costs, set budget alerts, and get actionable token-spend optimizations to keep multi-session workflows within budget.
arxiv2md
Convert arXiv papers into clean, LLM-ready Markdown via a REST API or CLI for fast reading, summarization, and downstream processing.
Overnight — Autonomous Long-Running Coding
Orchestrates long-running coding goals: decomposes objectives into atomic tasks, dispatches isolated worktree workers, verifies acceptance criteria, and merges
Scite Database (Smart Citations)
Query Scite.ai Smart Citations by DOI to report supporting, contrasting, and mentioning citation counts and help assess a paper's reliability.
Writing Implementation Plans
Generate detailed, engineer-ready implementation plans from design docs: file paths, step-by-step tasks, tests, and verification instructions.