SKILLS & AGENTS/Skill 与 Agent·COLLECTION
RConsortium/pharma-skills
A collection of agent skills for BioPharma use cases GSDBench Intake https://rconsortium.github.io/pharma-skills/gsdbench-intake/
怎么装:Install: npx skills add RConsortium/pharma-skills --list
02 / 现在的位置02 / Why now
首次发现FIRST SEEN
03 OCT 202603 OCT 2026
增长GROWTH
+0.0%+0.0%
117 → 117 stars · 2 个快照117 → 117 stars · 2 snapshots
状态STATUS
持续活跃Active
03 / 它能帮你做什么03 / What it helps you do
04 / 安装04 / Install
$ README 里给出的安装方式。The installation method given in the README.
$ README 里给出的安装方式。The installation method given in the README.
两种装法选一个即可 —— 上面那条给命令行用户,下面那条给写代码的用户。Pick one of the two — the first is for command-line users, the second for people writing code.
05 / 限制与风险05 / Limits and risk
风险不是警告,是可信度的一部分。以下结论只基于文档静态扫描,我们不会执行项目里的任何代码。Risk here is evidence, not an alarm. These findings come from static scanning of the docs; we never execute a project’s code.
限制LIMITS
未知Unknown
静态扫描STATIC SCAN
在 README、SKILL.md 和依赖清单中没有匹配到已知风险模式。No known risk patterns matched in the README, SKILL.md or dependency list.这不等于安全that does not mean it is safe,只能说明文档里没写。 — only that the docs do not mention it.
这里只做静态扫描:读 README、SKILL.md 和依赖清单,不执行代码。没有命中不代表安全。This is static scanning only: we read the README, SKILL.md and dependency list, and never execute code. No findings does not mean safe.
{
"agents": [
{
"agent": "claude-code",
"evidence": "tree: .claude/"
},
{
"agent": "cursor",
"evidence": "readme: …ur configuration files (like `.cursorrules`, `AGENTS.md`, or `llms.txt`)…"
},
{
"agent": "windsurf",
"evidence": "readme: …llation (Claude Code, Cursor, Windsurf, Copilot, etc.) 1. Clone thi…"
},
{
"agent": "cline",
"evidence": "readme: …(Claude Code, Codex, Cursor, Cline, Copilot, and [many more](htt…"
},
{
"agent": "claude-ai",
"evidence": "_automation/benchmark-runner/SKILL.md: …Create a single routine at [claude.ai/code/routines](https://claude…"
}
],
"apiKey": "I via `curl` | Anywhere with `GH_TOKEN` / `GITHUB_TOKEN` set | Universal fallb",
"docker": null,
"taxonomy": {
"scores": {
"design": 0,
"ai-tools": 1,
"dev-tools": 1,
"indie-web": 0,
"skill-agent": 3,
"productivity": 0
},
"primary": "skill-agent",
"secondary": "collection"
},
"localRuntime": null,
"skillMdTotal": 16,
"skillMdErrors": [],
"treeTruncated": false,
"categoryScores": {
"data": 1,
"agent": 0,
"media": 0,
"design": 1,
"browser": 0,
"devtool": 1,
"security": 0,
"marketing": 0,
"productivity": 0
},
"classification": [
{
"signal": "16 SKILL.md with name + description",
"weight": 0.95
},
{
"signal": "README describes a Claude / Agent Skill",
"weight": 0.7
},
{
"signal": "name contains 'skill'",
"weight": 0.4
},
{
"signal": "description mentions AI",
"weight": 0.2
}
],
"scannedSources": [
"readme",
"_automation/benchmark-runner/SKILL.md",
"_automation/benchmark-summary/SKILL.md",
"_automation/issue-to-eval/SKILL.md",
"_automation/weekly-summary/SKILL.md",
"admiral/SKILL.md",
"admiral/admiral-adae/SKILL.md",
"admiral/admiral-adrs/SKILL.md",
"admiral/admiral-adsl/SKILL.md",
"admiral/admiral-adtte/SKILL.md",
"admiral/admiral-bds/SKILL.md",
"clinical-trial-ipd-sim/SKILL.md",
"clinical-trial-simulation/SKILL.md",
"group-sequential-design/SKILL.md",
"rounding/SKILL.md",
"sdtm-oak/SKILL.md",
"statistical-reviewer/SKILL.md"
],
"skillMdFetched": 16
}