MCP App StoreMCP App Store
from edwinhu
Orchestrates diagnosis and targeted fixes mid-analysis: diagnose root cause, apply fixes with output-first verification, and update project learnings.
Provides a mid-analysis re-entry point for data science workflows. ds-fix enforces a strict diagnose-before-fix protocol: it loads workflow state, identifies the first step where outputs diverge, and delegates verified fixes while preserving LEARNINGS.md and PLAN.md. It includes gating and post-subagent constraints to ensure safe, auditable fixes.
Use when an ongoing analysis needs course-correction — e.g., runtime errors, wrong results, reviewer feedback, or data/schema changes. It is the re-entry midpoint (after /ds entry and before re-implement) designed for cases where you must resume, diagnose, and fix without losing context.
Designed for orchestrator-style agents used in data science workflows — agents that can read project files, spawn task subagents, and enforce hooks (notebook-debug, ds-review, ds-implement integrations).
ds-fix is a mid-analysis course-correction skill for data science workflows. It provides structured diagnosis routing (runtime errors, wrong results, unclear root cause, reviewer feedback, data/scope changes) with verification gates and a competing-hypothesis protocol. No bundled scripts to test — it relies on hooks pointing to external Python scripts via ${CLAUDE_PLUGIN_ROOT}. Heavily coupled to sibling skills (ds-implement, ds-review, ds-handoff, notebook-debug) limiting standalone utility.
Well-structured skill with strong emphasis on diagnose-before-fix discipline. The EXTREMELY-IMPORTANT blocks are good guardrails. Security is reasonable — hook commands use env vars that the framework controls. Main limitation is ecosystem dependency: it cannot function without the broader /ds workflow skills.
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.
DS Plan (Data Science Planning)
Data profiling and task breakdown phase of the data science workflow.
Monad Development
Practical developer skill for deploying and verifying smart contracts, configuring Foundry projects, and integrating frontends (viem/wagmi) on the Monad blockch
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
Ip2Location IO Automation (Composio)
Automate Ip2location IO tasks via Composio's Rube MCP toolkit — discover tools, verify connections, and execute schema-compliant workflows safely.
Overnight — Autonomous Long-Running Coding
Orchestrates long-running coding goals: decomposes objectives into atomic tasks, dispatches isolated worktree workers, verifies acceptance criteria, and merges
tmux Remote Control
Control tmux sessions for interactive TTYs: send keystrokes, capture panes, orchestrate parallel coding agents, and monitor output safely.
PPT as Code
Creator-first workflow to plan and build HTML-first presentations with staged modes (quick/basic/advanced), optional PPTX export, and clear QA and image plannin