Smart Poller

Periodically polls a Feishu task board to auto-detect and execute tasks assigned to the current AI agent with optional silent mode and feedback.

Security Scan

The skill's code and instructions match its stated purpose (polling a Feishu doc, detecting assigned tasks, executing simple handlers, and writing feedback); required secrets are stored in a local config file rather than environment variables and there are no unexpected network endpoints or installer downloads.

Purpose & Capability

The name/description (Feishu task-board poller) aligns with the included files (Python and Node.js pollers, README, SKILL.md). The code uses Feishu's open.feishu.cn APIs, reads a local config.json for app_id/app_secret/doc_token/assignee, parses tasks, executes simple keyword-based handlers, and writes feedback — all consistent with the declared purpose. Minor note: the registry metadata lists no required binaries, but the skill actually requires a Python (or Node.js) runtime to run the provided scripts.

Instruction Scope

SKILL.md instructs the agent to read a config.json, run the poller scripts, and write feedback to the Feishu document. The runtime instructions request 'exec', 'file_read', and 'file_write' which are appropriate for running a local poller. The code only reads config.json, interacts with open.feishu.cn, and writes feedback back to the document — it does not read other system files, call unknown external endpoints, or exfiltrate data to third-party servers.

Install Mechanism

There is no installer that downloads remote archives or executes arbitrary installers. This is instruction-only (files are bundled with the skill). No install URLs, package downloads, or extract steps are present. The only missing declaration is that a Python (or Node) interpreter is required; the skill bundle itself contains runnable scripts but relies on an existing runtime.

Credentials

The skill requires Feishu credentials (app_id and app_secret) and a doc_token — these are necessary for Feishu API access and are stored in config.json rather than as environment variables. That is proportionate to the task. NOTE: app_secret is a sensitive credential saved to disk in config.json; the skill does not declare required env vars in registry metadata, so users should be aware credentials are provided via a local file, not a platform secret store.

Persistence & Privilege

always:false and normal autonomous invocation settings. The skill writes feedback only to the configured Feishu document and does not modify other skill or agent configurations. Continuous polling is implemented by running the script (or via cron); no elevated or persistent platform-level privileges are requested.

Assessment

This skill appears to do what it says, but review and run it cautiously: - Provide a Feishu App (app_id/app_secret) with the minimal scopes required for reading/writing the target document; avoid using org-wide/high-privilege credentials. - Be aware credentials are stored in a local config.json file; keep that file protected (filesystem permissions) or adapt the code to use your platform's secret store if preferred. - Ensure your runtime (python3 or node) is available and run the Python single-run mode first (python3 poller.py config.json --once) or test with test.py to verify parsing behavior. - Inspect the code yourself (it's included) and, if deploying long-term, run the poller in an isolated environment/network and restrict outbound access to open.feishu.cn only. - If you need the skill declared to the platform as requiring specific runtimes or secret-handling, request the author update registry metadata to list Python/Node requirements and to document how secrets should be supplied.

Smart Poller Skill

Smart Polling Skill — Periodically polls a Feishu task board and auto-executes tasks assigned to the current AI agent.

📖 中文文档

---

🎯 Features

• ✅ Scheduled polling of Feishu task board (configurable interval)
• ✅ Auto-detect tasks assigned to the current AI agent
• ✅ Silent mode (no notification when idle; saves ~95% Token usage)
• ✅ Auto-write completion feedback to the task board
• ✅ Node.js and Python dual runtime support

---

📦 Installation

clawhub install smart-poller

---

🔧 Configuration

Copy the config template and fill in your values:

cp config.example.json config.json

Required fields:

• app_id: Feishu App ID
• app_secret: Feishu App Secret
• doc_token: Task board document ID
• assignee: Current agent identifier

---

🚀 Usage

# Run once (testing)
python3 poller.py config.json --once

# Continuous polling (production)
python3 poller.py config.json

# Cron (recommended)
*/15 * * * * python3 poller.py config.json --once

---

🛠️ Required Tools

• exec: Run Python/Node.js scripts
• file_read: Read config file
• file_write: Write config and logs

---

📝 Changelog

v1.0.0 (2026-03-17)

• ✅ Initial release
• ✅ Full Feishu API integration
• ✅ Silent mode optimization
• ✅ Dual runtime support

---

🤝 Contributing

GitHub: https://github.com/openclaw/skills

---

📄 License

MIT License

---

Author: socneo
Last updated: 2026-03-18