← 返回 Skills 市场
Trust Log
作者
BuiltByEcho
· GitHub ↗
· v0.2.1
· MIT-0
11
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install trustlog
功能描述
Create, summarize, or verify local human-readable receipts for AI agent work using the @builtbyecho/trustlog CLI. Use when a user asks for proof of what an a...
使用说明 (SKILL.md)
Trust Log Skill
Use trustlog to produce local JSON + Markdown receipts for agent work. Receipts should make it easy for a human or next agent to see what ran, what changed, what looked risky, and what was redacted.
Default workflow
- From the target project root, wrap meaningful verification commands:
npx @builtbyecho/trustlog run -- npm test
npx @builtbyecho/trustlog run -- npm run build
- Read the human summary:
cat .trustlog/latest.md
- Verify before sharing or using as final evidence:
npx @builtbyecho/trustlog verify .trustlog/latest.json
When to use
- Final proof after tests/builds/lints.
- Handoff evidence for another agent.
- User asks “what happened?” or “give me a receipt.”
- Risky commands where a durable local audit trail helps.
Safety
- Prefer non-destructive commands.
- Do not use this to justify commands you would not otherwise run.
- Receipts redact common secrets and strip thinking-looking blocks, but still inspect before posting publicly.
- If verification fails, do not share the receipt until the issue is fixed or clearly explained.
Useful commands
npx @builtbyecho/trustlog run -- \x3Ccommand> [args...]
npx @builtbyecho/trustlog summarize .trustlog/latest.json
npx @builtbyecho/trustlog verify .trustlog/latest.json
安全使用建议
This skill appears appropriate for creating local audit receipts. Before using it, be comfortable running the external npm package, approve only commands you actually want executed, and review generated .trustlog files before sharing them publicly.
能力评估
Purpose & Capability
The stated purpose—creating, summarizing, and verifying local receipts for agent work—matches the documented workflows.
Instruction Scope
The skill documents wrapping local commands, including arbitrary user-provided commands, but frames this as user-directed verification/audit work and includes safety guidance.
Install Mechanism
There is no install spec or reviewed code; the workflow relies on npx fetching/running @builtbyecho/trustlog from the npm ecosystem.
Credentials
The skill writes and reads local .trustlog receipts in the target project, which is proportionate to the purpose but may capture command outputs or change summaries.
Persistence & Privilege
The receipts are durable local files intended for later review or handoff; no elevated privileges, background persistence, or credential use are shown.
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 trustlog - 安装完成后，直接呼叫该 Skill 的名称或使用
/trustlog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
Initial ClawHub publish for the BuiltByEcho Trust Log agent receipt workflow.
元数据
常见问题
Trust Log 是什么？
Create, summarize, or verify local human-readable receipts for AI agent work using the @builtbyecho/trustlog CLI. Use when a user asks for proof of what an a... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 11 次。
如何安装 Trust Log？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install trustlog」即可一键安装，无需额外配置。
Trust Log 是免费的吗？
是的，Trust Log 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Trust Log 支持哪些平台？
Trust Log 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 Trust Log？
由 BuiltByEcho（@builtbyecho）开发并维护，当前版本 v0.2.1。
推荐 Skills