科研 Skill

科研环境依赖诊断

setup-medsci

Diagnoses Python, R, Node, Git, Zotero and configured MCP servers with a pass/fail table. Use when a skill fails for a missing tool or the environment needs checking.

发布者 Codar安全审核通过v0.1.0更新于 2026-11-18

SKILL.md

Setup-MedSci Skill

Diagnose only. Never install, upgrade or configure anything — no brew install, winget install, pip install, Rscript -e 'install.packages(...)', and no edits to ~/.claude.json or any MCP configuration (read claude mcp list only) — because auto-installers for system Python and R are a support nightmare for non-developer users. If a tool is missing, the user follows the setup doc themselves. Skill versions and content are out of scope (validate_skills.sh, /manage-project status).

The diagnostic table is in English so it can be pasted into a GitHub issue. Remediation links point to the docs/setup/ guides in the upstream medsci-skills repository (see the source: URL in this skill's frontmatter), and only these five exist: docs/setup/README.md, docs/setup/mac.md, docs/setup/windows.md, docs/setup/mcp-setup.md, docs/setup/common-issues.md. These docs and the ~/medsci-skills/demo/ folder referenced below are not shipped with this plugin — they live only in the upstream GitHub repository, so fetch them from there (or tell the user to) before pointing someone at a link.

Prerequisites and Limitations

  • The "Claude Code CLI" row (R5, command -v claude) is specific to the Claude Code agent. When this skill is run from a different coding agent (Codex, Copilot, or another Codar-compatible host), skip that row or replace it with the equivalent CLI for the host agent, and do not report it as a blocking ❌ for a non-Claude host.
  • docs/setup/*.md and the cd ~/medsci-skills/demo/... command in Phase 4 point to the upstream GitHub repository, not to files included in this plugin; treat them as external links to share with the user rather than local files to open.

Workflow

Phase 1: Detect OS

uname -s
  • Darwin → macOS → docs/setup/mac.md
  • Linux → Linux (similar tooling to Mac) → docs/setup/mac.md
  • MINGW*, MSYS*, CYGWIN*, or detection failure on Windows → docs/setup/windows.md

Phase 2: Run Diagnostic Commands

Read references/setup-checklist.md and run every check in it — R1-R5 required, O1-O5 optional — with its detect command, version command, minimum version and status rule. Use command -v <tool> first to detect presence without running it (avoids triggering long initialization). Capture the version output and the exit code, and report the version exactly as printed: if a command fails, report the failure verbatim rather than a version that is "probably" installed. If command -v finds the tool but the version command or its parse fails, mark the row ❌ and report the failing command — the install is broken, not just outdated. An MCP server is ✅ only when claude mcp list shows it connected; configured-but-disconnected is ⚠️.

Phase 3: Emit Checklist Table

Print a single Markdown table to stdout in this exact format, one row per check, with the doc link from the reference for the detected OS:

## MedSci Skills Setup Diagnostic

OS detected: <macOS | Linux | Windows>
Date: <YYYY-MM-DD>

| Component | Status | Detected | Required | Action |
|---|:---:|---|---|---|
| Python 3.11+ | ✅ / ❌ | 3.11.9 | 3.11+ | OK / See docs/setup/mac.md Step 2 |
| MCP: zotero | ✅ / ❌ / ⚠️ | Connected | optional | OK / See docs/setup/mcp-setup.md |

Summary: <X required components passed, Y missing>
Next step: <one-sentence action>

Status legend:

  • ✅ Present and meets minimum version
  • ❌ Missing or below minimum version
  • ⚠️ Present but optional and not connected

Phase 4: Suggest Remediation

Use the reference's Summary Rules for the closing sentence.

  • Everything required ✅ → point to Demo 1: cd ~/medsci-skills/demo/01_wisconsin_bc && claude '/orchestrate --e2e'.
  • Any required row ❌ → print its doc link and tell them to follow that step. Do not offer to install; the doc tells them exactly what to copy-paste.
  • Only optional MCP rows ❌ → explain that MedSci Skills work without MCP servers, but lit-sync, verify-refs and write-paper are smoother with Zotero MCP; link docs/setup/mcp-setup.md.

Output

The diagnostic report goes to stdout. If the user asks for a copyable report (e.g. for a GitHub issue), also write it to ~/.medsci-skills/diagnostic-YYYY-MM-DD.md and tell them where it is.

示例提示词

帮我检查一下本机的Python、R和Zotero环境配置是否正常。

所属插件

临床医学与公共卫生面向临床与公卫研究:研究设计与方案、样本量、队列与 Meta 分析、报告规范核查、医学影像 AI 评估、流行病建模与卫生经济学评价、医学论文写作投稿。

安装该插件会一并获得同领域的 58 个 Skill / MCP。

同插件的其他科研 Skill

常见问题

科研环境依赖诊断能做什么?

Diagnoses Python, R, Node, Git, Zotero and configured MCP servers with a pass/fail table. Use when a skill fails for a missing tool or the environment needs checking。

如何安装科研环境依赖诊断?

在科搭 Codar 左侧点击「插件」,在「组件」页签搜索「科研环境依赖诊断」并安装;在 Claude Code 或 Codex 中可以发送本页的安装提示词,或下载 Skill 包后解压到 ~/.claude/skills 或 ~/.codex/skills。

科研环境依赖诊断需要哪些权限?

该科研 Skill没有声明额外权限;执行具体操作时仍由 Agent 按自身规则请求确认。

科研环境依赖诊断经过官方审核吗?

是。SpeedSkills 收录的每个版本都会记录内容摘要与权限声明,当前版本已通过安全审核。