data-extraction-matrix
Use when extracting structured evidence from papers into a matrix for synthesis, comparison, or review writing.
- License 许可
- MIT
- 最近更新
- 2026-11-02
- Stars
- ★ 0
- Forks
- 0
01 前言 Front Matter
- name
- data-extraction-matrix
- description
- Use when extracting structured evidence from papers into a matrix for synthesis, comparison, or review writing.
02 资源文件 10
- 参考文档resources/common-patterns.md8.2 KB
- 参考文档resources/complete-examples.md23.9 KB
- 参考文档resources/component-patterns.md10.6 KB
- 参考文档resources/data-fetching.md19.4 KB
- 参考文档resources/file-organization.md11.6 KB
- 参考文档resources/loading-and-error-states.md11.8 KB
- 参考文档resources/performance.md9.4 KB
- 参考文档resources/routing-guide.md7.0 KB
- 参考文档resources/styling-guide.md7.7 KB
- 参考文档resources/typescript-standards.md8.2 KB
03 SKILL.md 正文
data-extraction-matrix
This skill converts messy papers into comparable evidence rows. It is designed for extraction tables that can survive later audit and synthesis.
When to use
- The user needs a study matrix, extraction sheet, or comparison table.
- Multiple papers must be aligned across participants, methods, interventions, outcomes, and limitations.
Workflow
- Define the extraction schema from the review question.
- Pull only fields that matter to later synthesis.
- Separate reported values from analyst comments.
- Normalize units, terminology, and missing-value notation.
- Return the matrix plus a list of fields that were difficult or ambiguous to extract.
Configuration and access
- Use stable identifiers for each study row.
- If a spreadsheet or database target exists, reference the target label only.
Output standard
- Produce structured rows first, prose interpretation second.
- Keep comments in a separate analyst field.
Guardrails
- Do not fill blanks with assumptions.
- Do not merge distinct outcomes into one convenience column.
04 同仓库更多 Skills
clarify-requirements
Resolve genuine pre-execution ambiguity by scanning repo context, generating 1-6 grounded options, and asking 1-3 focused questions via AskUserQuestion. NOT for mid-task use (injection risk); NOT when the goal is already unambiguous; use to disambiguate vague prompts before any file edits.
openmm-md
Run FREE, open-source, Windows-native GPU molecular dynamics via the openmm-md MCP (OpenMM + CUDA on the local NVIDIA GPU). Use for protein / protein-ligand MD when you want a free stack or are on Windows without a Schrodinger license. Covers the full workflow (prepare, solvate, minimize, equilibrate, production, analyze, mmgbsa) AND an honest decision guide vs Schrodinger Desmond, including how to run Desmond legitimately on Linux or a cloud GPU with a real license. This is a deliberately LESSER free alternative and does NOT replace the schrodinger MCP tools. Do NOT use it to pick a free tool when a validated FEP+, WaterMap, IFD-MD, or Prime MM-GBSA result is actually required.
visual-review
Take screenshots of web pages and UI using Playwright for visual review and iteration
status
Diagnostic status report — shows metaswarm installation state, project setup, and potential issues
start
Use when starting work on any task, when the user mentions metaswarm, or when the user wants to begin tracked development work
setup
Interactive project setup — detects your project, configures metaswarm, writes project-local files