Token导航 LogoToken导航

Agent Skill · 研究检索

happenstance(happenstance 搜索)

happenstance 用于查找、检索和筛选相关信息,适合在 OpenClaw 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

happenstance 是研究检索类 Agent Skill,可用宿主为 OpenClaw,通过ClawHub获取,权限为接触敏感数据;许可证为 MIT-0,第三方扫描已通过,按安装量在研究检索类的 73,675 个 Skill 里排第 6,899。

总安装 20,580周安装 875GitHub Stars 8下载 7,210核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
MIT-0
版本
1.0.0

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:happenstance(happenstance 搜索)
来源仓库:https://github.com/dgoss28/happenstance
安装命令:
openclaw skills install happenstance
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 OpenClaw 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

ClawHubOpenClaw
openclaw skills install happenstance

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

用于查找、检索和筛选相关信息,支持关键词和任务场景快速定位。适合在 OpenClaw 中根据来源线索快速定位候选结果。可结合来源仓库和原始 README 核验具体用法。安装前建议确认权限范围和维护状态,以及是否会触发联网或文件读写。注意维护状态和实际功能是否与描述一致。

happenstance 属于研究检索类 Skill,可作为该场景下的辅助能力补充。

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 OpenClaw;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 openclaw skills install happenstance;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要接触敏感数据,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

happenstance 怎么安装?

在终端执行 openclaw skills install happenstance。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

happenstance 支持哪些 AI 工具?

公开资料标注支持 OpenClaw。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

happenstance 需要什么权限?

权限级别是接触敏感数据。该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

happenstance 是免费的吗?

来源标注的许可证是 MIT-0。本站不代收任何费用,也不托管安装包;能否商用、要不要署名,以许可证原文为准。

happenstance 用的人多吗?

公开数据是累计安装 20,580 次,近一周安装 875 次,下载 7,210 次,GitHub 8 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

happenstance 安全吗?

第三方扫描结果为通过,但这只覆盖已知的静态检查项,不能替代自己读一遍源码和安装命令。

值得选的地方和要先想清楚的地方

值得选的地方

  • 专注 OpenClaw 一种宿主,触发方式和使用习惯不用来回切换。
  • 许可证明确为 MIT-0,商用和分发边界好判断。
  • 第三方扫描已通过,常见的高风险行为没有命中。

先想清楚的地方

  • 需要接触敏感数据,装到常用环境前要先评估影响面。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 OpenClaw,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。
  • 需要许可证清楚、并且有第三方扫描结果的团队项目。

不太适合

  • 环境里有大量密钥、凭证,不方便给第三方 Skill 读取的人。
  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
happenstance

happenstance 搜索 · 本页

20,5808接触敏感数据MIT-0通过

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

name
happenstance
description
Search your professional network and research people using the Happenstance API.
metadata
openclaw
requires
env
bins
primaryEnv
HAPPENSTANCE_API_KEY

Happenstance

Search your network and get detailed research profiles on people using the Happenstance API.

Documentation: https://developer.happenstance.ai

Authentication

All requests require the HAPPENSTANCE_API_KEY environment variable. Pass it as a Bearer token:

Authorization: Bearer $HAPPENSTANCE_API_KEY

Base URL: https://api.happenstance.ai

Billing

  • Search: 2 credits per search (including find-more)
  • Research: 1 credit per completed research
  • Check balance with GET /v1/usage
  • Purchase credits at https://happenstance.ai/settings/api

Available Operations

1. Search Your Network

Search for people across groups and connections. Searches run asynchronously.

Start a search:

curl -s -X POST https://api.happenstance.ai/v1/search \
  -H "Authorization: Bearer $HAPPENSTANCE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "text": "engineers who have worked on AI infrastructure",
    "include_my_connections": true,
    "include_friends_connections": true
  }'

You can also search within specific groups by adding "group_ids": ["uuid1", "uuid2"]. Get group IDs from GET /v1/groups.

At least one search source is required: group_ids, include_my_connections: true, or include_friends_connections: true.

Response:

{"id": "search-uuid", "url": "https://happenstance.ai/search/search-uuid"}

Poll for results (every 5-10 seconds until status is COMPLETED or FAILED):

curl -s https://api.happenstance.ai/v1/search/SEARCH_ID \
  -H "Authorization: Bearer $HAPPENSTANCE_API_KEY"

Completed response includes:

  • status: RUNNING, COMPLETED, or FAILED
  • results: array of people, each with id, name, current_title, current_company, summary, weighted_traits_score, socials (with happenstance_url, linkedin_url, twitter_url), mutuals, and traits
  • has_more: boolean indicating if more results are available
  • mutuals: top-level array of mutual connections (results reference these by index)
  • traits: top-level array of trait definitions (results reference these by index)

2. Find More Results

When has_more is true on a completed search, get additional results that exclude all previously returned people. Costs 2 credits.

curl -s -X POST https://api.happenstance.ai/v1/search/SEARCH_ID/find-more \
  -H "Authorization: Bearer $HAPPENSTANCE_API_KEY"

Response:

{"page_id": "page-uuid", "parent_search_id": "search-uuid"}

Then poll with the page_id:

curl -s "https://api.happenstance.ai/v1/search/SEARCH_ID?page_id=PAGE_ID" \
  -H "Authorization: Bearer $HAPPENSTANCE_API_KEY"

3. Research a Person

Get a detailed professional profile for a specific person. Runs asynchronously.

Start research:

curl -s -X POST https://api.happenstance.ai/v1/research \
  -H "Authorization: Bearer $HAPPENSTANCE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"description": "Garry Tan, CEO of Y Combinator, @garrytan on Twitter"}'

Include as many details as possible (full name, company, title, location, social handles) for best results.

Response:

{"id": "research-uuid"}

Poll for results (every 5-10 seconds until status is COMPLETED, FAILED, or FAILED_AMBIGUOUS):

curl -s https://api.happenstance.ai/v1/research/RESEARCH_ID \
  -H "Authorization: Bearer $HAPPENSTANCE_API_KEY"

Completed response includes a profile object with:

  • person_metadata: full_name, alternate_names, profile_urls, current_locations, tagline
  • employment: array of jobs with company_name, job_title, start_date, end_date, description
  • education: array with university_name, degree, start_date, end_date
  • projects: array with title, description, urls
  • writings: array of publications with title, description, date, urls
  • hobbies: array with description
  • summary: overall text summary with supporting urls

4. List Groups

Get the groups you can search within:

curl -s https://api.happenstance.ai/v1/groups \
  -H "Authorization: Bearer $HAPPENSTANCE_API_KEY"

Returns {"groups": [{"id": "uuid", "name": "Group Name"}, ...]}.

5. Check Credits and Usage

curl -s https://api.happenstance.ai/v1/usage \
  -H "Authorization: Bearer $HAPPENSTANCE_API_KEY"

Returns balance_credits, has_credits, purchases, usage history, and auto_reload settings.

Error Handling

Errors use RFC 7807 format:

{"type": "about:blank", "title": "Bad Request", "status": 400, "detail": "Description must not be empty", "instance": "/v1/research"}

Key status codes:

  • 401: Invalid or missing API key
  • 402: Insufficient credits
  • 429: Too many concurrent requests (max 10 running searches or research requests)
  • 500/503: Server error, retry with backoff

Tips

  • Always check credits before starting multiple searches or research requests.
  • Search typically completes in 30-60 seconds. Research takes 1-3 minutes.
  • Each search returns up to 30 results. Use find-more for additional pages.
  • When presenting search results, include the person's name, title, company, summary, and Happenstance profile link.
  • When presenting research, summarize the profile and link to sources.
  • The more data sources the user connects, the better the search results.

平台分布

OpenClaw

80.1%
按下载量换算5,775

安全审计

VirusTotal

通过

ClawScan

通过

Static analysis

未展示

权限和风险

接触敏感数据

该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills