MCP App StoreMCP App Store
from reaper8
Provide structured critique of investigation results via human feedback, Codex consultation, or agent self-review to uncover gaps, alternative hypotheses, and n
Critique adds a dedicated review layer to a research investigation pipeline. It accepts human feedback, consults an external AI (Codex) as a devil's advocate or inspiration, or performs an automated self-review. The skill classifies feedback, logs consultation results, and creates actionable hypotheses or workflow signals that can trigger further investigation cycles.
Use Critique after an investigation run has produced findings and you want: to refine conclusions with human input, obtain an independent AI second opinion, or have the agent check its own work for weak claims and untested assumptions. It's appropriate when you need targeted follow-up (deepen/explore), formal re-framing (scope), or purely editorial improvements (rewrite).
Designed for multi-agent research pipelines and MCP-capable hosts. The repo reports compatibility with Codex CLI, Cursor, Claude Code, Gemini CLI and other research tools (MCP tooling) for Codex consultations.
The reaper-critique skill provides structured critique of investigation results through three modes: human feedback, Codex (external AI) consultation, and self-review. No bundled scripts — purely instruction-based. SKILL.md is well-documented with clear mode separation, feedback categorization, and quality criteria. Tightly coupled to the reaper workspace structure, limiting reuse outside that ecosystem.
No security concerns. Pure instruction skill with no executable scripts. Niche utility as it's specific to the reaper investigation framework.
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
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
Codex Collab
Bridge Claude and Codex to run tasks, perform code reviews, and run background jobs for research or implementation workflows.
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.