MCP App StoreMCP App Store
from tackline14
Run multi-step research and analysis chains (gather, distill, rank, verify, plan) automatically; choose and orchestrate primitives based on a user goal.
Tackline is a composable knowledge-work engine that maps a natural-language goal to a chain of operations (gather, distill, rank, filter, verify, plan, etc.) and executes them in order. It provides structured operations for research, comparison, planning, and verification with provenance and pipe-format outputs.
Use Tackline when a task requires multi-step reasoning or research — for example: compare approaches, gather and verify evidence, break down a project into MECE parts, or produce a prioritized plan. Prefer Tackline over invoking single primitive skills when you expect a sequence of operations.
Best for agents with code and agent-orchestration capabilities (multi-agent dispatch, code-reading assistants, Claude Code, Copilot-style orchestration). Tackline expects access to repo files for code-first research and can orchestrate parallel agents for fan-out tasks.
Tackline is a composable knowledge-work engine that chains 14 operations (gather, distill, rank, filter, verify, etc.) based on user goals. It's a pure prompt-engineering skill with no bundled scripts. The SKILL.md is well-structured with a clear decision tree for intent parsing and operation selection, though it references external rule files (pipe-format.md, fan-out-protocol.md) that aren't bundled.
No security concerns — no scripts, no network calls, no shell execution. Well-written prompt skill with good operation taxonomy. Missing referenced rule files means some functionality depends on external context not provided in the skill itself.
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.
ds-fix — data-science mid-analysis fixer
Orchestrates diagnosis and targeted fixes mid-analysis: diagnose root cause, apply fixes with output-first verification, and update project learnings.
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.