菜单
Fetch one or more RSS 2.0 or Atom feeds in parallel and return a normalised list of items (title, URL, content, source, published). Use in research-stage directives that need to ingest blog/news feeds.
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 | rss-fetch |
| description | Fetch one or more RSS 2.0 or Atom feeds in parallel and return a normalised list of items (title, URL, content, source, published). Use in research-stage directives that need to ingest blog/news feeds. |
| metadata | {"clawdbot":{"emoji":"📰","requires":["node"],"credentials":"none — reads public feeds"}} |
General-purpose RSS/Atom feed fetcher. Parses both RSS 2.0 and Atom; errors on individual feeds are collected into an errors array rather than failing the whole call.
cd ~/clawd/skills/rss-fetch
pnpm install
pnpm run build
# One feed
rss-fetch --url "https://example.com/feed.xml" --output items.json
# Multiple feeds
rss-fetch \
--url "https://nephjc.com/feed.rss" \
--url "https://www.medscape.com/rss/nephrology" \
--output items.json
# Feeds from a JSON file
rss-fetch --urls-file ./research/feeds.json --output items.json
Without --output, items are included inline in the stdout JSON. Output shape:
{
"ok": true,
"feeds": 2,
"count": 23,
"errors": [],
"items": [
{ "title": "…", "url": "https://…", "content": "…", "source": "https://feed.xml", "published": "2026-04-10T00:00:00.000Z" }
]
}
| Flag | Default | Notes |
|---|---|---|
--url <url> | — | Repeatable. At least one required. |
--urls-file <path> | — | JSON array of URLs. Additive with --url. |
--output <path> | — | Write items to this file |
--timeout-ms <n> | 15000 | Per-feed timeout |
error | Meaning |
|---|---|
config | Missing URLs / bad args |
unknown | Unexpected error reading inputs/outputs |
Individual feed failures (HTTP errors, timeouts, malformed XML) are surfaced in the top-level errors array and do not abort the call.
rss-fetcher.tspubmed-search — companion skill for peer-reviewed biomedical literature08 - System/Agent Skills/rss-fetch - Skill Overview.md