← 返回 Skills 市场
Resend CLI Skill
作者
Tristan Manchester
· GitHub ↗
· v1.0.2
· MIT-0
289
总下载
0
收藏
0
当前安装
3
版本数
在 OpenClaw 中安装
/install resending-emails
功能描述
Use this skill when the task is specifically about operating Resend from an AI agent, terminal session, or CI job via the official resend CLI: installing/aut...
安全使用建议
This skill is intended to act as a CLI-first operator for Resend and includes a Python wrapper that probes the environment, scaffolds files, lints batch JSON, and executes the official 'resend' CLI. Before installing or running it: 1) expect to provide a RESEND_API_KEY or pre-seeded profile and to have the 'resend' binary available — the package metadata does not declare these but the skill will rely on them; 2) review scripts/resend_cli.py yourself (it runs subprocesses based on input and can execute arbitrary 'resend' commands you or an agent supplies); 3) do not run suggested install curl|bash commands blindly — inspect the install script at the referenced URL first; 4) in CI, use a least-privileged API key (e.g., domain-scoped sending_access) rather than a full account key; 5) if you need the agent to operate autonomously, be aware the helper reads env and config paths (e.g., ~/.config/resend/credentials.json) and will probe environment state — only grant the minimum secrets and run in an isolated environment or sandbox. If the publisher can update the registry metadata to declare the 'resend' binary as a required dependency and RESEND_API_KEY (or explain why none is required), that would resolve the primary inconsistency.
功能分析
Type: OpenClaw Skill
Name: resending-emails
Version: 1.0.2
The skill bundle is a well-documented and functionally appropriate toolkit for enabling an AI agent to operate the Resend email service via its official CLI. It includes a Python helper script (scripts/resend_cli.py) designed to wrap CLI calls with deterministic flags, parse JSON/NDJSON output from both stdout and stderr, and provide diagnostic 'doctor' and 'lint-batch' utilities. The instructions in SKILL.md and the extensive reference documentation (references/agent-operating-model.md, etc.) focus on operational safety, such as recommending environment variables over command-line secrets and identifying known CLI coverage gaps. No evidence of malicious intent, data exfiltration, or harmful prompt injection was found; the use of subprocess execution is strictly aligned with the stated purpose of CLI automation.
能力评估
Purpose & Capability
The SKILL.md and bundled helper clearly expect the official 'resend' CLI to be present and for the agent/CI to supply RESEND_API_KEY or profiles. But registry metadata declares no required binaries and no required environment variables. That is an incoherence: someone installing this skill should expect to provide an API key and possibly install the 'resend' CLI.
Instruction Scope
The runtime instructions direct the agent to run many Resend CLI commands, probe CLI availability, read local help, and inspect config paths (e.g., ~/.config/resend/credentials.json). Those actions are reasonable for a CLI operator skill, but they go beyond the skill's declared requirements (they read environment and local config). The instructions do not instruct exfiltration to third-party endpoints beyond official install URLs; they do tell the agent to run long-running 'listen' processes and to manage scaffolds/files.
Install Mechanism
There is no install spec in the registry (instruction-only), but SKILL.md recommends installing the CLI via curl|bash, npm, or brew and points to official domains and the GitHub repo. Suggesting curl|bash is common for CLI installs but carries risk if blindly executed; the referenced URLs appear to be official (resend.com / github.com/resend/resend-cli). The skill itself bundles a Python helper (scripts/resend_cli.py) that will be written to disk when the package is unpacked — the bundle includes assets and scaffolds that can be written to the filesystem.
Credentials
The skill uses and recommends RESEND_API_KEY and RESEND_PROFILE in both SKILL.md and scripts/resend_cli.py but the registry metadata lists no required env vars or primary credential. The helper probes and reports whether RESEND_API_KEY is present and will use environment variables for auth. Sensitive variables (API keys) are required in practice but not declared, which is a transparency and least-privilege concern.
Persistence & Privilege
The skill is not marked always:true and does not claim to change other skills or global agent config. It can scaffold files and run subprocesses, but that behavior is scoped to its own helper and included assets, which is expected for a CLI wrapper.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install resending-emails - 安装完成后，直接呼叫该 Skill 的名称或使用
/resending-emails触发 - 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
v1.0.2
**Major update: Shifted focus from Resend API/SDK to the official Resend CLI, with new assets, guides, and an agent-optimized helper.**
- Rebranded and refactored skill for Resend CLI usage, prioritizing terminal, agent, and CI workflows.
- Added new reference docs and assets for CLI installation, command selection, subprocess handling, diagnostics, and identifying CLI coverage gaps.
- Bundled a new `scripts/resend_cli.py` tool for agent-friendly probing, scaffolding, batch linting, command routing, and safe subprocess execution.
- Removed previous API/SDK workflow files and references to streamline for CLI-first tasks.
- Updated SKILL.md to clarify preferred agent operating order, CLI quirks, and fallback scenarios.
- Asset set and documentation now focuses on practical command-line automation and agent guidance.
v1.0.1
Major refactor and content update for Resend integration guidance.
- Added new references for endpoint selection, agent operating model, marketing model, and debugging.
- Expanded asset catalog: now includes detailed JSON payload templates, error mappings, task router, and testing/attachment guides.
- Revised skill guardrails and output expectations for clearer operational procedures.
- Introduced agent-oriented helper script commands: recommend, lint, scaffold, doctor.
- Improved guidance for choosing between batch, broadcast, template, and inbound primitives.
- Retired deprecated references in favor of updated, scenario-driven docs.
v1.0.0
Initial release of the resend-api skill with comprehensive Resend API coverage:
- Adds endpoint catalog, reference docs, OpenAPI snapshot, and JSON payload templates for core operations.
- Supports transactional emails, batch sends, templates, domains, API keys, contacts, segments, broadcasts, webhooks, inbound email, and workflows.
- Includes agent-oriented helper script (`scripts/resend_api.py`) for endpoint introspection and live API calls using Python standard library.
- Guides users through best practices, operational caveats, and debugging Resend API integrations.
- Replaces the previous "resend" skill with a full-featured, detailed Resend-specific skillset.
元数据
常见问题
Resend CLI Skill 是什么？
Use this skill when the task is specifically about operating Resend from an AI agent, terminal session, or CI job via the official resend CLI: installing/aut... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 289 次。
如何安装 Resend CLI Skill？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install resending-emails」即可一键安装，无需额外配置。
Resend CLI Skill 是免费的吗？
是的，Resend CLI Skill 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Resend CLI Skill 支持哪些平台？
Resend CLI Skill 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 Resend CLI Skill？
由 Tristan Manchester（@tristanmanchester）开发并维护，当前版本 v1.0.2。
推荐 Skills