← 返回 Skills 市场
pgomes13

DriftaBot

作者 Pascoal Gomes · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ 安全检测通过
137
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install driftabot
功能描述
Query the DriftaBot Registry for API spec drifts, breaking changes, and provider information. Use when the user asks about API changes, breaking changes, pro...
使用说明 (SKILL.md)

DriftaBot Registry Skill

DriftaBot Registry (https://github.com/DriftaBot/registry) is a public registry that:

  • Tracks 59+ API providers (Stripe, GitHub, Twilio, Slack, Shopify, and many more)
  • Crawls specs daily from each provider's canonical GitHub repository
  • Generates markdown drift reports when breaking changes are detected

When to use this skill

  • User asks "did X API change?", "what broke in Y's API?", "show me drift for Z"
  • User wants to know which providers are tracked in the registry
  • User asks about current API spec versions or types (OpenAPI, GraphQL, gRPC)

How to query the registry

Base URL: https://raw.githubusercontent.com/DriftaBot/registry/main

1. List all providers

Fetch {BASE}/provider.companies.yaml and parse the YAML. Each entry has: name (slug), display_name, specs[].type, specs[].repo.

2. Get a drift report for a provider

Fetch {BASE}/drifts/{org}/{repo}/result.md

  • Find org/repo from the provider's specs[].repo field in provider.companies.yaml
  • Example: stripe → repo stripe/openapi → fetch drifts/stripe/openapi/result.md
  • If the file returns 404 or empty, no breaking changes were detected for that provider.

3. Get the current spec file

Fetch {BASE}/companies/providers/{name}/{type}/{filename}

  • Example: companies/providers/stripe/openapi/stripe.openapi.json

Example queries and responses

"Did Stripe's API break anything?" → Fetch drifts/stripe/openapi/result.md and summarize the breaking changes.

"What API providers are tracked?" → Fetch provider.companies.yaml, list all company names and their spec types.

"What type of spec does Shopify use?" → Find shopify in provider.companies.yaml, return specs[].type (graphql).

Tool usage

Use the web tool (or bash with curl) to fetch URLs. Parse YAML with available tools. Always look up the repo from provider.companies.yaml before constructing drift URLs.

安全使用建议
This skill is low-risk and coherent: it only asks the agent to fetch public files from a DriftaBot GitHub registry and summarize them, and it does not request secrets or install software. Before enabling, consider: (1) confirm you trust the registry GitHub repo (https://github.com/DriftaBot/registry or the metadata homepage) because the agent will fetch and summarize whatever is hosted there; (2) if you require offline or air-gapped operation, do not enable network access; (3) if you rely on these summaries for security- or production-critical decisions, spot-check the raw result.md/spec files yourself to ensure the registry hasn't been tampered with. Otherwise, the skill's scope and requirements are proportional to its stated purpose.
功能分析
Type: OpenClaw Skill Name: driftabot Version: 1.0.0 The driftabot skill is designed to query a public GitHub repository (DriftaBot/registry) for API breaking changes and specifications. The instructions in SKILL.md guide the agent to fetch YAML and Markdown files from raw.githubusercontent.com to provide information to the user. There is no evidence of data exfiltration, malicious execution, or prompt injection; the behavior is entirely consistent with the stated purpose of tracking API drifts.
能力评估
Purpose & Capability
The name/description say the skill queries a public DriftaBot registry for API drifts; the SKILL.md only requires fetching files from that registry and parsing YAML/markdown — nothing requested is unrelated to that purpose.
Instruction Scope
Runtime instructions are narrowly scoped: fetch provider.companies.yaml, locate repo entries, fetch drift/result.md and spec files from the stated raw.githubusercontent.com base. It only instructs network fetches and YAML/markdown parsing and does not ask to read local files or other env vars. Note: the agent will perform outbound web requests to public GitHub raw URLs, so fetched content is external and should be treated as untrusted.
Install Mechanism
No install spec and no code files — instruction-only skill; nothing is written to disk by an installer.
Credentials
The skill declares no required environment variables, binaries, or credentials. That is proportionate to fetching and summarizing public registry files.
Persistence & Privilege
always is false and there is no install/persistence behavior. The skill does not request elevated or persistent privileges.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install driftabot
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /driftabot 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.0.0
Initial release of driftabot skill. - Query the DriftaBot Registry for API spec drifts, breaking changes, and provider info. - Supports questions about tracked providers, API changes, and spec types (OpenAPI, GraphQL, gRPC). - Instructions included for listing providers, retrieving drift reports, and getting current API specs. - Usage guidance and example queries provided for clarity.
元数据
Slug driftabot
版本 1.0.0
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 1
常见问题

DriftaBot 是什么?

Query the DriftaBot Registry for API spec drifts, breaking changes, and provider information. Use when the user asks about API changes, breaking changes, pro... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 137 次。

如何安装 DriftaBot?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install driftabot」即可一键安装,无需额外配置。

DriftaBot 是免费的吗?

是的,DriftaBot 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

DriftaBot 支持哪些平台?

DriftaBot 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 DriftaBot?

由 Pascoal Gomes(@pgomes13)开发并维护,当前版本 v1.0.0。

💬 留言讨论