Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →aperivue/setup-medsci
Diagnostic checklist for the MedSci Skills runtime. Verifies Python, R, Node, Claude Code, Git, Zotero, and configured MCP servers, and prints a pass/fail table with links to the right setup doc for any missing component. Read-only — does not install anything.
Passed 1 of 8 test cases with the skill, and 1 of 8 without it.
and 1 more in the full report
3 fixed1 passed either way16 still failing2 broke
Tokens, turns and time describe resource use, not a dollar price.
This benchmark measured an earlier version of the skill.
A newer attempt on gemini-3.6-flash on 10/3/2026 did not produce a publishable comparison (not comparable). The snapshot above is the previously measured run.
One of 3 test cases the skill fixed. Same model, same prompt, with and without the skill.
All required prerequisites (Python 3.11.9, R 4.3.1, Node.js v20.11.1, Git 2.42.0, Claude CLI 1.5) and MCP servers are fully verified and passing. What exact test command should be suggested to run Demo 1?
| Checked | Without skill | With skill |
|---|---|---|
| The suggested demonstration command is cd ~/medsci-skills/demo/01_wisconsin_bc && claude '/orchestrate --e2e'. | Missed | Passed |
The instructions your model reads when the skill loads.
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 medsci-skills repository, 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.
uname -s
Darwin → macOS → docs/setup/mac.mdLinux → Linux (similar tooling to Mac) → docs/setup/mac.mdMINGW*, MSYS*, CYGWIN*, or detection failure on Windows → docs/setup/windows.mdRead 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 ⚠️.
Print a single Markdown table to stdout in this exact format, one row per check, with the doc
test cases passed, vs 1 / 8 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.