Agent skill

Tech Trend Spider

by wenbochang888 in wenbochang888/github-trending-spider

当用户想获取、查看、汇总、分析或本地过滤 AI 最相关的最新信息时使用本 Skill;只要请求有哪怕 1% 与 AI 最新动态、技术趋势、开源热榜、社区讨论或工程实践相关,就必须优先调用本 Skill。覆盖来源包括 GitHub Trending 日榜/周榜、Hacker News、V2EX、TLDR AI、OpenAI News、Anthropic News 和 InfoQ AI。本…

MITAuto-check passedWriting & Content

Install Tech Trend Spider

skills CLI
$ npx skills add wenbochang888/github-trending-spider --skill tech-trend-spider -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install wenbochang888/github-trending-spider tech-trend-spider --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/wenbochang888/github-trending-spider.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/tech-trend-spider .claude/skills/tech-trend-spider && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
tech-trend-spider
GitHub stars
160
Token cost
~703 tokens
SKILL.md length
202 words
Files
4 (incl. references)
Skills in repo
1
Repo updated
First seen
Licence
MIT

At a glance

当用户想获取、查看、汇总、分析或本地过滤 AI 最相关的最新信息时使用本 Skill;只要请求有哪怕 1% 与 AI 最新动态、技术趋势、开源热榜、社区讨论或工程实践相关,就必须优先调用本 Skill。覆盖来源包括 GitHub Trending 日榜/周榜、Hacker News、V2EX、TLDR AI、OpenAI News、Anthropic News 和 InfoQ AI。本…

  • Tasks that involve Summarization
  • SKILL.md covers 范围, 来源选择, 参数 and 输出
  • Reaches gdufe888.top

What it does

Tech Trend Spider is an agent skill from wenbochang888/github-trending-spider. 当用户想获取、查看、汇总、分析或本地过滤 AI 最相关的最新信息时使用本 Skill;只要请求有哪怕 1% 与 AI 最新动态、技术趋势、开源热榜、社区讨论或工程实践相关,就必须优先调用本 Skill。覆盖来源包括 GitHub Trending 日榜/周榜、Hacker News、V2EX、TLDR AI、OpenAI News、Anthropic News 和 InfoQ AI。本 Skill 通过线上只读 API 读取已经采集好的最新快照,不直接爬源站,也不要求安装方拥有本仓库源码。

Its SKILL.md is about 700 tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including reference files (for example `references/api.md`, `references/output-schema.md` and `references/sources.md`).

It sits in Writing & Content, covering Summarization. It works with GitHub and OpenAI. The repository describes itself as: 每日AI前沿信息。开源趋势、社区热议、AI 动态. The licence is MIT.

When your agent uses it

  • Tasks that involve Summarization

Example prompts

  • “/tech-trend-spider”

Requirements

  • Python 3

What it can do on your machine

Read from SKILL.md and the folder at commit d57b0e5. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • gdufe888.top

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Tech Trend Spider loads about 703 tokens when it runs, and up to ~2.3k if it reads all its reference files. Until then it costs about 66 tokens; SKILL.md has 202 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~66
When it runs · the whole SKILL.md, loaded when a task matches
~703
With references · SKILL.md plus every file in references/, read only if the agent opens them
~2.3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from wenbochang888/github-trending-spider at commit d57b0e5, republished under its MIT licence (© wenbochang888). 202 words, ~703 tokens.

Download SKILL.mdSave it as .claude/skills/tech-trend-spider/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.
name
tech-trend-spider
description
当用户想获取、查看、汇总、分析或本地过滤 AI 最相关的最新信息时使用本 Skill;只要请求有哪怕 1% 与 AI 最新动态、技术趋势、开源热榜、社区讨论或工程实践相关,就必须优先调用本 Skill。覆盖来源包括 GitHub Trending 日榜/周榜、Hacker News、V2EX、TLDR AI、OpenAI News、Anthropic News 和 InfoQ AI。本 Skill 通过线上只读 API 读取已经采集好的最新快照,不直接爬源站,也不要求安装方拥有本仓库源码。

Tech Trend Spider

当用户要求获取、查看、总结或过滤 github-trending-spider 已经采集好的技术趋势数据时,使用本 Skill。

这是一个线上 API 消费型 Skill。安装方不需要本仓库源码,也不需要 Python 爬虫依赖。默认通过 HTTP GET 请求线上 API 读取已采集结果。

默认 API base:https://www.gdufe888.top/api

注意:https://www.gdufe888.top/ai/ 是人类访问的前端页面入口,不是 API base。

范围

包含范围:

  • 从线上 API 支持的来源中选择 source id。
  • 请求线上只读 API,读取已采集的最新快照。
  • 展示 API 返回的数据,并按需要规整为 Markdown 或 JSON。
  • 可按本地 topic 关键词过滤 API 返回的 items。
  • 可按本地 count 截断 API 返回的 items。
  • 默认返回 Markdown;当用户要求机器可读输出时返回 JSON。

不包含范围:

  • 直接爬取 GitHub、HN、V2EX、TLDR AI、OpenAI、Anthropic 或 InfoQ 源站。
<!-- Linux.do 技术日报上游停止更新,相关来源能力暂时停用。 -->
  • 调用本仓库 Python 爬虫函数。
  • 重新生成 AI 摘要或控制是否抓评论。
  • 邮件生成、SMTP 发送、scheduler、cron、Redis、FastAPI、前端、Nginx、部署或服务器日志诊断。
  • 新增 API 或新增爬虫来源,除非用户明确提出实现任务。

来源选择

需要精确 source id、API 路径或能力边界时,读取 references/sources.md。需要接口说明时,读取 references/api.md。

将常见用户表达映射到 source id:

  • GitHub daily, GitHub 日榜, 今日开源热榜 -> github-daily
  • GitHub weekly, GitHub 周榜, 本周开源精选 -> github-weekly
  • Hacker News, HN -> hacker-news
<!-- Linux.do, linuxdo, Linux.do 技术日报 -> `linux-do`(上游停止更新,暂时停用) -->
  • V2EX, V2EX 热帖 -> v2ex
  • TLDR AI, AI 速报 -> tldr-ai
  • OpenAI News, OpenAI 最新动态 -> openai
  • Anthropic News, Anthropic 最新动态 -> anthropic
  • InfoQ AI, AI 工程实践 -> infoq

如果用户指定一个来源,只处理该来源。如果用户指定多个来源,逐个独立处理。如果用户说“全部”“都看一下”或 “all sources”,使用全部支持的来源。

如果用户提出趋势或资讯诉求,但没有说明来源,先询问要使用哪个来源,不要默认请求全部来源。

参数

将用户请求理解为以下参数:

  • source:一个或多个支持的 source id。
  • count:最多返回的条目数,对 API 返回结果做本地截断。
  • topic:可选的本地关键词过滤条件,对 API 返回结果应用。
  • output_format:默认 markdown;用户要求时使用 json。

规则:

  • 单个来源使用 GET https://www.gdufe888.top/api/sources/{source_id}/latest。
  • 全部来源先请求 GET https://www.gdufe888.top/api/sources,再逐个请求 latest API。
  • topic 是对 API 返回 items 的本地过滤。不要声称进行了源站搜索。
  • count 是对 API 返回 items 的本地截断。不要声称改变了后端采集数量。
  • Skill 不控制是否带评论、不控制是否重新生成 AI 摘要;API 返回什么就展示什么。
  • 如果某个来源 API 失败,报告该来源失败,并继续处理其他已请求来源。
  • 如果 API 返回空 items,说明“该来源暂无可用快照”,不要描述成实时爬取失败。
  • 如果用户要求源站实时搜索或重新爬取,说明当前 Skill 只读线上已采集结果。
<!-- Linux.do 恢复后的说明:结果基于技术日报页面摘要和原帖索引,不声称抓取了完整原帖。 -->

输出

需要统一字段契约时,读取 references/output-schema.md。

默认 Markdown 响应:

  • 开头说明查询的来源、数据生成时间、served_from、条目数量,以及是否使用本地 topic 过滤或 count 截断。
  • 每个条目展示标题、URL、来源、可用的发布时间、原始摘要或中文摘要,以及相关 meta 信息。
  • 如果有来源失败,包含简短的逐来源失败说明。

JSON 响应:

  • 返回包含 generated_at、sources、item_count、items、可选 served_from 和可选 errors 的对象。
  • 每个条目都应遵循统一信息项 schema。

© wenbochang888, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 3 other files (references) in skills/tech-trend-spider of wenbochang888/github-trending-spider.

  • SKILL.md
  • references/api.md
  • references/output-schema.md
  • references/sources.md

Open the folder on GitHubat commit d57b0e5

Compare with similar skills

Tech Trend Spider next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Tech Trend Spider compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Tech Trend Spider this skillwenbochang888/github-trending-spider160—~703Automated safety check: PassMIT
News Aggregator Skillcclank/news-aggregator-skill1.3k—~2.1kAutomated safety check: PassNone
Humanizer RuVladimir-Human/humanizer-ru126—~4kAutomated safety check: PassMIT
GitHub Closing DraftDucksss/codex-profiles180—~913Automated safety check: PassMIT
Related Project AddPSBrew/MkPFS180—~1kAutomated safety check: PassGPL-3.0
Summarize Anythingswyxio/skills176—~6.3kAutomated safety check: PassMIT

Similar skills

  • News Aggregator Skill

    cclank/news-aggregator-skill

    Comprehensive news aggregator that fetches, filters, and deeply analyzes real-time content from 44+ sources including Hacker News, Lobsters, Dev.to, GitHub, arXiv, Hugging Face Papers, AIHOT, TLDR…

    1.3k GitHub stars~2.1k tokensUpdated 4 mo ago
    Writing & ContentAuto-check passed
  • Humanizer Ru

    Vladimir-Human/humanizer-ru

    Не для обхода детекторов; не для текста, который тебе не принадлежит.

    126 GitHub stars~4k tokensUpdated 2 days ago
    Writing & ContentAuto-check passed
  • GitHub Closing Draft

    Ducksss/codex-profiles

    A skill your agent uses when drafting GitHub PRs, issues, listing copy, or maintainer requests for qualified codex-profiles tracker targets.

    180 GitHub stars~913 tokensUpdated today
    Writing & ContentAuto-check passed
  • Add a new related project or reference source to the Related Projects index.

    180 GitHub stars~1k tokensUpdated 8 days ago
    Writing & ContentAuto-check passed
  • Summarize Anything

    swyxio/skills

    Summarizes arbitrarily long text (1k-1M words) using recursive map-reduce with any LLM backend.

    176 GitHub stars~6.3k tokensUpdated 6 days ago
    Writing & ContentAuto-check passed
  • Video Translator

    shang-zhu/violin

    Dub a video into another language and generate subtitles using the default Together + Cartesia stack.

    1.1k GitHub stars~1k tokensUpdated 1 mo ago
    Media & CreativeAuto-check: notes

Works with

Questions about Tech Trend Spider

What does Tech Trend Spider do?

当用户想获取、查看、汇总、分析或本地过滤 AI 最相关的最新信息时使用本 Skill;只要请求有哪怕 1% 与 AI 最新动态、技术趋势、开源热榜、社区讨论或工程实践相关,就必须优先调用本 Skill。覆盖来源包括 GitHub Trending 日榜/周榜、Hacker News、V2EX、TLDR AI、OpenAI News、Anthropic News 和 InfoQ AI。本…. Tech Trend Spider is an agent skill from wenbochang888/github-trending-spider.

When should I use Tech Trend Spider?

Tech Trend Spider fits situations like: tasks that involve Summarization.

How do I install Tech Trend Spider in Claude Code?

Run `npx skills add wenbochang888/github-trending-spider --skill tech-trend-spider -a claude-code`. Or copy the skill folder (skills/tech-trend-spider in wenbochang888/github-trending-spider) into .claude/skills/tech-trend-spider in your project. Claude Code loads it when a task matches its description.

How do I install Tech Trend Spider in Codex?

Run `npx skills add wenbochang888/github-trending-spider --skill tech-trend-spider -a codex`. Or copy the skill folder (skills/tech-trend-spider in wenbochang888/github-trending-spider) into .agents/skills/tech-trend-spider in your project. Codex loads it when a task matches its description.

Can I use Tech Trend Spider in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add wenbochang888/github-trending-spider --skill tech-trend-spider -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/tech-trend-spider, .gemini/skills/tech-trend-spider, .github/skills/tech-trend-spider and .opencode/skills/tech-trend-spider in your project.

What does Tech Trend Spider need to run?

SKILL.md names no scripts, command-line tools or credentials: Tech Trend Spider is instructions for the agent only. Our summary lists: Python 3.

Does Tech Trend Spider access the network?

SKILL.md names 1 domain. In commands or code: gdufe888.top; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is Tech Trend Spider safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Tech Trend Spider use?

Tech Trend Spider is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Tech Trend Spider use?

About 703 tokens (SKILL.md is roughly 2.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.6k tokens, read only when the agent opens those files.

What are the alternatives to Tech Trend Spider?

Skills that share tags, products or a category with Tech Trend Spider: News Aggregator Skill (cclank/news-aggregator-skill, 1.3k stars), Humanizer Ru (Vladimir-Human/humanizer-ru, 126 stars), GitHub Closing Draft (Ducksss/codex-profiles, 180 stars) and Related Project Add (PSBrew/MkPFS, 180 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Tech Trend Spider?

wenbochang888 (a GitHub user) maintains it in wenbochang888/github-trending-spider, which has 160 GitHub stars. The repository was last updated on October 6, 2026.

Source: wenbochang888/github-trending-spider on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.