菜单
Inspect the user's open GitHub PRs / failing CI / new issues via `gh`, summarize into 3 buckets (to-review / awaiting-me / CI-red), and persist follow-ups to memory.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
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。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/TokenRhythm/opensquilla --skill meta-github-pr-watch-digest命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
Query scholarly metadata and the web through Crossref, Brave, Tavily, and DuckDuckGo with a single CLI surface. Trigger when the user asks for research search, fact lookup, source discovery, or engine comparison. Results retain DOI, publication year, and authors when supplied by Crossref, then deduplicate by DOI, arXiv ID, or normalized URL. API-key engines gate themselves on the relevant environment variable; Crossref and DuckDuckGo need no key.
Deterministic OpenRouter image generation adapter for Nano Banana Pro / Gemini image models. Use as skill_exec when a meta-skill needs local image files and structured IMAGE_READY records without spawning an LLM agent.
Generate or edit a single image via OpenRouter (google/gemini-3.1-flash-image-preview by default). Accepts a text prompt and optional --input-image for image-to-image editing. Trigger when the user asks for an AI image, illustration, concept art, product render, or wants to modify an existing image.
基于 SOC 职业分类
正在显示 SKILL.md
| name | meta-github-pr-watch-digest |
| description | Inspect the user's open GitHub PRs / failing CI / new issues via `gh`, summarize into 3 buckets (to-review / awaiting-me / CI-red), and persist follow-ups to memory. |
| kind | meta |
| meta_priority | 45 |
| always | false |
| triggers | ["PR 巡检","PR digest","github 巡检","watch my prs"] |
| provenance | {"origin":"opensquilla-original","license":"Apache-2.0"} |
| composition | {"steps":[{"id":"pull_prs","skill":"github","with":"[Truncated]"},{"id":"digest","skill":"summarize","depends_on":"[Truncated]","with":"[Truncated]"},{"id":"memorize","kind":"tool_call","tool":"memory_save","tool_allowlist":"[Truncated]","depends_on":"[Truncated]","tool_args":"[Truncated]"}]} |
Daily PR-queue triage: pulls open PRs / failing CI / new comments via
the github skill (gh CLI), digests into three actionable buckets, and
records follow-ups to long-term memory.
LLM should manually call gh pr list, gh run list --status failure,
summarize, and memory_save.
