Token导航 LogoToken导航

Agent Skill · 研究检索

scoro(scoro 搜索)

scoro 用于记录任务执行中的错误、用户纠正、经验和能力缺口,适合在 OpenClaw 中希望让 Agent 持续沉淀问题、修正和最佳实践时使用。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。

scoro 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 19,436。

总安装 5,607周安装 236GitHub Stars 公开资料未说明下载 1,964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:scoro(scoro 搜索)
来源仓库:https://github.com/germainsafari/scoro
安装命令:
openclaw skills install scoro
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 scoro

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。

scoro 集成 Scoro API v2,支持时间跟踪、任务管理与团队利用率报告生成。适用于 OpenClaw 中对接项目管理平台、自动更新工时或生成计费报表。通过 API 调用同步任务状态与人员负载,提升团队协作透明度。需确认 API 密钥存储方式与请求频率限制,避免触发服务风控。

适用于远程团队或外包项目的进度监控场景。

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 scoro;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

scoro 怎么安装?

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

scoro 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。

scoro 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。

scoro 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。

scoro 用的人多吗?

公开数据是累计安装 5,607 次,近一周安装 236 次,下载 1,964 次。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。

scoro 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
scoro

scoro 搜索 · 本页

5,607—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
scoro
description
Scoro API v2 integration for time tracking, task management, utilization reporting, team status reports, and billable corrections. Use when: user asks about Scoro tasks, time entries, hours (billable/non-billable), utilization reports, team status, or any Scoro data.
homepage
https://api.scoro.com/api/v2
metadata

Scoro Integration

Full Scoro API v2 integration for OpenClaw. Provides task management, time tracking, hours calculation, utilization reports, team dashboards, and billable status corrections.

Setup

  1. Get your Scoro API key from Settings → External connections → API in your Scoro account.
  2. Set your company URL (e.g. https://yourcompany.scoro.com/api/v2).
  3. Add both to your OpenClaw config:
{
  "env": {
    "vars": {
      "SCORO_API_KEY": "ScoroAPI_your_key_here",
      "SCORO_COMPANY_URL": "https://yourcompany.scoro.com/api/v2"
    }
  }
}
  1. Add "scoro" to your agent's skills list in openclaw.json.

Standard Prompts

Users can trigger these capabilities with natural language:

Task Management

  • fetch my scoro tasks / show my tasks for this week
  • fetch tasks for <user email or name>
  • show overdue tasks

Hours & Time Entries

  • show my hours this week / how many hours have I logged?
  • calculate my billable hours / show billable vs non-billable hours
  • send me a report of my billable and non-billable hours
  • show time entries for <user> from <date> to <date>

Team & Manager Reports

  • show team status / team pulse
  • generate team hours report

Utilization Reporting

  • generate weekly utilization report
  • show billable ratio for <user>

Billable Corrections

  • find incorrect billable entries
  • fix billable status for entries <IDs>
  • adjust all logs on task X to be billable

Environment Variables

  • SCORO_COMPANY_URL — full base URL (e.g. https://yourcompany.scoro.com/api/v2)
  • SCORO_API_KEY — company API key (starts with ScoroAPI_)

Both must be set in openclaw.json under env.vars. They are available as shell environment variables. Do NOT use .env files.

API Basics

All Scoro API v2 requests are POST. Every request body must include apiKey and company_account_id.

The company_account_id is the subdomain from your Scoro URL. For https://yourcompany.scoro.com, it is yourcompany.

Example Request (curl)

curl -X POST "$SCORO_COMPANY_URL/timeEntries/list" \
  -H "Content-Type: application/json" \
  -d '{
    "apiKey": "'"$SCORO_API_KEY"'",
    "company_account_id": "yourcompany",
    "filter": {
      "time_entry_date": {
        "from": "2026-03-10",
        "to": "2026-03-16"
      },
      "user_ids": [123]
    },
    "per_page": 100,
    "page": 1,
    "detailed_response": true
  }'

Example Request (PowerShell / Windows)

$body = @{
    apiKey = $env:SCORO_API_KEY
    company_account_id = 'yourcompany'
    filter = @{
        time_entry_date = @{ from = '2026-03-10'; to = '2026-03-16' }
        user_ids = @(123)
    }
    per_page = 100
    page = 1
    detailed_response = $true
} | ConvertTo-Json -Depth 10

$response = Invoke-RestMethod -Method Post `
    -Uri "$env:SCORO_COMPANY_URL/timeEntries/list" `
    -ContentType 'application/json' -Body $body

Key Endpoints

All endpoints: POST $SCORO_COMPANY_URL/{module}/{action}

EndpointPurpose
tasks/listFetch tasks with filters
tasks/view/IDView single task details
timeEntries/listFetch time entries (with date, user, billable filters)
timeEntries/modify/IDUpdate a time entry (e.g. fix billable status)
users/listFetch all users (includes reporting manager info)
projects/listFetch projects
contacts/listFetch contacts

Filtering

Tasks

{
  "filter": {
    "responsible_person_ids": [123],
    "deadline": { "from": "2026-03-16", "to": "2026-03-22" },
    "status": "in_progress"
  }
}
  • responsible_person_ids — array of assigned user IDs
  • deadline — {"from": "YYYY-MM-DD", "to": "YYYY-MM-DD"}
  • modified_date — {"from": "YYYY-MM-DD", "to": "YYYY-MM-DD"}

Time Entries

CRITICAL: The date filter field is time_entry_date with from/to keys. NOT start_date/end_date.

{
  "filter": {
    "time_entry_date": { "from": "2026-03-10", "to": "2026-03-16" },
    "user_ids": [123]
  }
}
  • user_ids — array of user IDs (not a single value)

Users

No specific filter needed. Returns all active users.

Response Fields

Task Fields

  • event_id — unique task ID
  • event_name — task name/title
  • datetime_due — deadline (ISO datetime)
  • is_completed — 0 or 1
  • activity_type — project/category name
  • responsible_person_id — assigned user ID
  • description — task description

Time Entry Fields

  • time_entry_id — unique ID
  • user_id — the user who logged it
  • duration — format "HH:MM:SS" (e.g. "01:30:00" = 1.5h)
  • title — task/event name
  • billable_time_type — "billable", "non_billable", or "custom"
  • time_entry_date — "YYYY-MM-DD"
  • event_id — the task/event this entry is for
  • is_billable — 0 or 1

User Fields

  • id — unique user ID
  • full_name — display name
  • email — email address
  • position — job title

Duration Parsing

Format is "HH:MM:SS". Convert to decimal hours: hours + minutes/60 + seconds/3600.

Pagination — CRITICAL

Scoro caps page size at 25 items regardless of per_page setting.

You MUST paginate through ALL pages for any list operation:

page = 1
all_results = []
loop:
  response = POST .../endpoint { per_page: 100, page: page }
  if length(response.data) == 0: break
  all_results += response.data
  page += 1
  sleep 1 second (rate limit)

Important: Do NOT use data.length < per_page as a stop condition — the API returns a max of 25 items per page even if you request 100. Stop when a page returns 0 results.

Calculating Hours

  1. Determine date range (default: this week Monday to today)
  2. Fetch all time entries for the date range and user(s), paginating all pages
  3. Calculate:
   total_hours = sum(duration)
   billable_hours = sum(duration where billable_time_type == "billable")
   non_billable_hours = sum(duration where billable_time_type == "non_billable")
   billable_ratio = (billable_hours / total_hours) * 100
  1. Present with 2 decimal places

Team Reports

Teams are organized by direct manager (reporting lines).

Workflow for Team Status

  1. Resolve user IDs for all team members (by email, from users/list, all pages)
  2. Fetch today's time entries for all team members at once
  3. Per member: total hours, billable split, latest task name
  4. Calculate team totals and billable ratio

Billable Status Correction

Detection

  1. Retrieve time entries for the period
  2. Retrieve task billing type for each task
  3. Flag mismatches: task is billable but time entry is non_billable

Correction

POST /timeEntries/modify/<ENTRY_ID>
{
  "apiKey": "...",
  "company_account_id": "yourcompany",
  "request": {
    "billable_time_type": "billable"
  }
}

Always confirm with the user before modifying entries.

Rate Limits

  • 2-second rate limit window
  • Add 1-second delay between paginated API calls
  • On 429 errors, wait and retry

Response Format

{
  "status": "OK",
  "statusCode": 200,
  "messages": null,
  "data": []
}

All Available Modules

tasks, timeEntries, users, projects, contacts, invoices, quotes, orders, bills, expenses, products, calendarEvents, bookings, purchaseOrders, tags, customModules, vatCodes, financeAccounts

Each module supports: list, view, modify, delete.

Use modify and delete only with explicit user permission.

Notes

  • All requests are POST (even "list" and "view")
  • Always include apiKey and company_account_id in the JSON body
  • Use detailed_response: true for full field data in list requests
  • Duration format: "HH:MM:SS" → convert to decimal hours for reporting
  • The lang parameter is optional (defaults to site language)
  • On Windows, prefer PowerShell Invoke-RestMethod over curl

平台分布

OpenClaw

76.7%
按下载量换算1,506

安全审计

VirusTotal

通过

ClawScan

通过

Static analysis

通过

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