← 返回 Skills 市场
636
总下载
0
收藏
7
当前安装
6
版本数
在 OpenClaw 中安装
/install skill-feed
功能描述
Scenario-driven skill recommendation engine for ClawHub. Detects failed or stuck workflows, builds targeted search queries, and returns ranked skill recommen...
安全使用建议
This skill appears internally consistent, but before installing: 1) confirm your agent runtime enforces the SKILL.md sanitization rules (prevent raw logs, env values, API keys, PII from being sent); 2) verify the agent only sends sanitized, generic queries to https://clawhub.ai and does not leak internal URLs or tokens; 3) test the skill using synthetic failures (no real secrets) to validate outputs; 4) ensure the skill will not auto-execute external high-risk remediation steps without explicit user confirmation. If you need stronger guarantees, ask the skill author to provide a deterministic sanitization routine and clearer limits on which logs/contexts the skill may read.
功能分析
Type: OpenClaw Skill
Name: skill-feed
Version: 0.2.1
The skill-feed bundle is a recommendation engine designed to help users recover from failed workflows by searching for relevant skills on ClawHub. While it involves sending data to an external endpoint (clawhub.ai), the SKILL.md file contains extensive and explicit 'Data Sanitization' instructions to strip secrets, API keys, and PII before any external search occurs. The logic is transparent, well-documented, and lacks any indicators of malicious intent, such as unauthorized execution or data exfiltration.
能力评估
Purpose & Capability
The name/description (recommend skills to recover failed workflows) matches the instructions: classify failures, build sanitized queries, search ClawHub, rank candidates, and return recovery steps. No unrelated env vars, binaries, or install steps are requested.
Instruction Scope
Instructions stay within the stated purpose (capture failure context, sanitize, construct queries, call ClawHub search, rank results). However, sanitization is delegated to the agent and the SKILL.md does not define precise sanitization implementation or explicit limits on which runtime sources to read — e.g., it says "latest action log summary" but doesn't restrict reading broader logs or environment variables. The effectiveness of data protection depends on the agent enforcing the sanitization rules.
Install Mechanism
Instruction-only skill with no install spec or downloaded code — lowest risk. The skill expects to perform live web searches (https://clawhub.ai/skills?focus=search) at runtime, which is appropriate for its function.
Credentials
The skill requests no environment variables, credentials, or config paths. It uses generic network access to query ClawHub, which is proportionate to its purpose.
Persistence & Privilege
No elevated persistence requested (always: false). The skill does not request or document modifying other skills or system-wide settings.
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 skill-feed - 安装完成后，直接呼叫该 Skill 的名称或使用
/skill-feed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
v0.2.1
Add data sanitization rules: strip secrets, credentials, PII from search queries to resolve security scan finding
v0.2.0
Add proactive triggers, 5 new query templates, scoring example, live-search-first strategy, session-level dedup, single-provider output
v0.1.3
Improve description for recommendation use cases
v0.1.2
README upgrade with clearer usage and output guidance
v0.1.1
Add README and docs polishing
v0.1.0
Initial release
元数据
常见问题
Skill Feed 是什么？
Scenario-driven skill recommendation engine for ClawHub. Detects failed or stuck workflows, builds targeted search queries, and returns ranked skill recommen... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 636 次。
如何安装 Skill Feed？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install skill-feed」即可一键安装，无需额外配置。
Skill Feed 是免费的吗？
是的，Skill Feed 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Skill Feed 支持哪些平台？
Skill Feed 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 Skill Feed？
由 Jack Lee（@jackleeio）开发并维护，当前版本 v0.2.1。
推荐 Skills