技能详情(站内镜像,无评论)
作者:savvysales.ai @dasonshi
许可证:MIT-0
MIT-0 ·免费使用、修改和重新分发。无需归因。
版本:v1.0.1
统计:⭐ 4 · 608 · 1 current installs · 1 all-time installs
⭐ 4
安装量(当前) 1
🛡 VirusTotal :良性 · OpenClaw :良性
Package:dasonshi/hylo-ghl
安全扫描(ClawHub)
- VirusTotal :良性
- OpenClaw :良性
OpenClaw 评估
The skill's requests and instructions match its stated purpose: it is an instruction-only Hylo (GHL) knowledge API wrapper that only requires a Hylo API key and calls api.hylo.pro for information.
目的
Name/description promise a Hylo/GHL knowledge API and the skill only requests HYLO_API_KEY and documents endpoints on api.hylo.pro. The declared credential and listed endpoints are coherent with the stated purpose.
说明范围
SKILL.md instructs the agent to call Hylo's API endpoints, handle common HTTP errors, and summarize JSON results. It does not instruct reading unrelated files or environment variables beyond HYLO_API_KEY. The only local file referenced is the included reference/endpoints.md, which is legitimate for offline reference.
安装机制
No install spec and no code files are present. This lowers risk because nothing will be written to disk or installed by the skill.
证书
Only HYLO_API_KEY is required (declared as primaryEnv) and is appropriate for a wrapper around Hylo's API. No unrelated secrets, config paths, or broad credential requests are present.
持久
always is false and there are no instructions to persist changes to agent/system configuration or to modify other skills. The skill does not request elevated or permanent privileges.
综合结论
This skill appears internally consistent, but consider these practical steps before installing: 1) Only provide a Hylo API key you control and preferably one scoped with least privilege (or a test account) so the key cannot be abused if leaked. 2) Be aware that any prompts or data the agent sends to the Hylo API will be transmitted to api.hylo.pro — review Hylo's privacy/security policies if you care about sensitive data. 3) Because this is in…
安装(复制给龙虾 AI)
将下方整段复制到龙虾中文库对话中,由龙虾按 SKILL.md 完成安装。
请把本段交给龙虾中文库(龙虾 AI)执行:为本机安装 OpenClaw 技能「Hylo — GHL Automation Expert」。简介:GoHighLevel (GHL) workflow automation expert with 102 verified actions, 70 trig…。
请 fetch 以下地址读取 SKILL.md 并按文档完成安装:https://raw.githubusercontent.com/openclaw/skills/refs/heads/main/skills/dasonshi/hylo-ghl/SKILL.md
(来源:yingzhi8.cn 技能库)
SKILL.md
---
name: hylo-ghl
description: GoHighLevel (GHL) workflow automation expert with 102 verified actions, 70 triggers, and 494 API schemas. Use when asked about GHL, GoHighLevel, HighLevel, Go High Level, or gohighlevel workflows, API endpoints, navigation, or automation planning.
homepage: https://hylo.pro
metadata: {"openclaw": {"emoji": "🦞", "requires": {"env": ["HYLO_API_KEY"]}, "primaryEnv": "HYLO_API_KEY"}}
---
You have access to the Hylo GHL knowledge API. Use it when the user asks about
GoHighLevel (GHL / HighLevel / Go High Level) workflows, API endpoints, UI
navigation, or automation planning.
## Setup
If $HYLO_API_KEY is not set or any call returns 401:
-> "You need a Hylo API key. Sign up at hylo.pro (7-day free trial)."
If 403: -> "Your trial has expired. Subscribe at hylo.pro/dashboard."
If 404: -> "I couldn't find that resource. Try a broader search term."
If 429: -> "Rate limit reached. Try again tomorrow or upgrade at hylo.pro/dashboard."
## API (bash + curl)
Base: `https://api.hylo.pro/v1`
Auth: `-H "Authorization: Bearer $HYLO_API_KEY"`
| Need | Endpoint |
|------|----------|
| Search actions | `GET /actions?q=KEYWORD` |
| Search triggers | `GET /triggers?q=KEYWORD` |
| Search API schemas | `GET /schemas?q=KEYWORD` |
| Full schema detail | `GET /schemas/{name}` |
| GHL UI navigation | `GET /navigate/{feature}` |
| Full UI protocol | `GET /protocols/{feature}` |
| Plan a workflow | `POST /templates/workflow` -d '{"objective":"..."}' |
| Validate workflow | `POST /validate` -d '{"trigger":"...","actions":[...]}' |
For category/feature lists: `cat {baseDir}/reference/endpoints.md`
## Rules
- ALWAYS call the API -- don't guess about GHL. Your knowledge may be outdated.
- Summarize JSON responses naturally -- never dump raw output.
- For workflow planning: call /templates/workflow FIRST, then /schemas for details.