← 返回 Skills 市场
🔌

Graincrawl

作者 OpenClaw · GitHub ↗ · v1.0.1 · MIT-0
cross-platform ✓ 安全检测通过
103
总下载
0
收藏
0
当前安装
2
版本数
在 OpenClaw 中安装
/install graincrawl
功能描述
Granola archive: search, sync freshness, notes, transcripts, panels, SQL counts, and Graincrawl repo work.
使用说明 (SKILL.md)

Graincrawl

Use local Granola archive data first. Check freshness for recent/current questions:

graincrawl doctor --json
graincrawl status --json

Refresh only when stale or asked:

graincrawl sync --source private-api
graincrawl sync --source desktop-cache

Query with bounded reads:

graincrawl search "query"
graincrawl notes --json
graincrawl note get \x3Cid>
graincrawl transcripts get \x3Cid>
graincrawl panels get \x3Cid>
graincrawl --json sql "select count(*) as notes from notes;"

Report absolute date spans, note titles, source gaps, and transcript/panel availability. Use read-only SQL for exact counts/rankings. Before encrypted source debugging, run explicit unlock/secrets checks; do not surprise-prompt Keychain.

安全使用建议
Install Graincrawl only if you want your agent to access local Granola notes, transcripts, panels, and freshness data. Be cautious with private API syncs, Keychain prompts, and SQL queries, and prefer a pinned or reviewed CLI version if supply-chain assurance matters.
功能分析
Type: OpenClaw Skill Name: graincrawl Version: 1.0.1 The skill bundle provides a CLI interface for managing and searching local Granola archive data via the `graincrawl` tool. The instructions in SKILL.md are task-oriented, focusing on data freshness, local searching, and SQL querying, and even include a safety-conscious note regarding Keychain access. No indicators of malicious intent, data exfiltration, or harmful prompt injection were found in the code or documentation.
能力评估
Purpose & Capability
The stated purpose matches the documented commands for searching Granola notes, transcripts, panels, freshness, and counts; the data involved may be private meeting or note content.
Instruction Scope
The instructions include useful bounds such as local data first, refresh only when stale or asked, bounded reads, and read-only SQL, but the SQL and archive reads can still expose sensitive local content to the agent context.
Install Mechanism
The skill installs a Go CLI from github.com/openclaw/graincrawl using @latest, and no CLI source code was included in the reviewed artifact set.
Credentials
Local Granola archive, desktop cache, and private API access are proportionate to the purpose, but users should expect access to personal Granola data.
Persistence & Privilege
No background persistence or self-propagation is described; however, private API sync and Keychain/secrets checks may cross account or credential boundaries and should be user-approved.
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 graincrawl
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /graincrawl 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
v1.0.1
Point stock skill metadata at the OpenClaw repository and Go module.
v1.0.0
Publish stock OpenClaw skill with compact CLI metadata.
元数据
Slug graincrawl
版本 1.0.1
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 2
常见问题

Graincrawl 是什么?

Granola archive: search, sync freshness, notes, transcripts, panels, SQL counts, and Graincrawl repo work. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 103 次。

如何安装 Graincrawl?

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

Graincrawl 是免费的吗?

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

Graincrawl 支持哪些平台?

Graincrawl 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 Graincrawl?

由 OpenClaw(@openclaw)开发并维护,当前版本 v1.0.1。

💬 留言讨论