菜单
Search PubMed via NCBI E-utilities (esearch + efetch) and return a normalised list of articles with title, URL, abstract, and PMID. Use in research-stage directives that need biomedical literature — clinical-researcher, universal-researcher, any health/biotech project.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Thin shell wrapper over the Linear GraphQL API for use from agent directives. Reads Linear projects + issues, creates/updates issues, resolves viewers/cycles/labels/project IDs. Replaces the legacy src/linear/*.ts; orchestration logic now lives in vault directives (linear-import.md, linear-uplink.md), this skill only owns the HTTP boundary.
Multi-reference image composition via fal-ai/nano-banana/edit. Use when a directive needs to combine 2+ reference images into a single composed output (character + location, brand sigil + character, multi-character ensemble shot, etc.). Sister tool: bible-to-prompt assembles a canonical prompt from a character/location bible MD before calling nano-compose.
Fire a single openclaw notification per runtime contract (notifications). Always echoes to stdout in §15.4 format; also dispatches via openclaw CLI if OPENCLAW_NOTIFY_TARGET is set. Replaces src/notify/notify.ts (99 LOC); batching responsibility shifts to callers.
Fetch project-scoped context from Notion using the official REST API for use in <workplace>ProjectSync and other orchestrators.
Read, write, and search Obsidian vault markdown files
Spawn a Claude Code or Cursor agent in non-interactive mode (`--print` style) with a prompt + repo workspace. Replaces src/agents/{claudeCodeSpawn,cursorSpawn,spawnAgent}.ts (179 LOC).
| name | pubmed-search |
| description | Search PubMed via NCBI E-utilities (esearch + efetch) and return a normalised list of articles with title, URL, abstract, and PMID. Use in research-stage directives that need biomedical literature — clinical-researcher, universal-researcher, any health/biotech project. |
| metadata | {"clawdbot":{"emoji":"🩺","requires":["node"],"credentials":"optional — PUBMED_API_KEY env var or --api-key flag bumps NCBI rate limit from 3/s to 10/s"}} |
General-purpose PubMed search. Deduplicates PMIDs across multiple queries in a single call.
cd ~/clawd/skills/pubmed-search
pnpm install
pnpm run build
# One query
pubmed-search --query "dialysis elderly outcomes" --max 20 --output results.json
# Multiple queries (dedup across queries)
pubmed-search --query "dialysis" --query "kidney transplant" --output results.json
# Queries from a JSON file
pubmed-search --queries-file ./research/queries.json --output results.json
Without --output, articles are included inline in the stdout JSON. Output shape:
{
"ok": true,
"queries": 2,
"count": 14,
"articles": [
{ "title": "…", "url": "https://pubmed.ncbi.nlm.nih.gov/12345678/", "content": "Abstract…", "source": "pubmed", "pmid": "12345678" }
]
}
| Flag | Default | Notes |
|---|---|---|
--query <term> | — | Repeatable. At least one required. |
--queries-file <path> | — | JSON array of query strings. Additive with --query. |
--max <n> | 10 | Per-query cap |
--api-key <key> | $PUBMED_API_KEY | Optional NCBI API key |
--output <path> | — | Write articles to this file |
error | Meaning |
|---|---|
config | Missing queries / bad args |
rate_limit | 429 from NCBI — back off and retry |
auth | 401/403 — check API key |
upstream | 5xx |
timeout | Request exceeded the per-query timeout |
clinical-researcher directive — replace inline curl snippets with this skillpubmed-fetcher.tsrss-fetch — companion skill for blog/news feed research08 - System/Agent Skills/pubmed-search - Skill Overview.md