Token导航 LogoToken导航TokenDH.com
研究检索需要联网clawhub未标认证来源可访问clear审计提醒

pop-obsidianPOP Obsidian 搜索

Agent Skill

pop-obsidian 用于查找、检索和筛选相关信息,适合在 OpenClaw 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

7,682

周安装

330

GitHub Stars

公开资料未说明

下载量

2,693
OpenClaw

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

MIT-0

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:pop-obsidian(POP Obsidian 搜索)
来源仓库:https://github.com/toolate28/pop-obsidian
安装命令:
openclaw skills install pop-obsidian
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 OpenClaw 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

ClawHubOpenClaw
openclaw skills install pop-obsidian

简介

Obsidian 插件编排协议 (POP) 集成,支持插件管理与管道自动化流程。

  • 适合 Obsidian 重度用户与知识工作者构建个性化工作流与自动化任务。
  • 通过 clawhub 安装于 OpenClaw,解析 POP 指令并协调多个插件协同运行。
  • 需确保 Obsidian 实例正常运行且插件兼容当前版本,避免冲突导致崩溃。
  • 建议备份配置文件后再进行复杂编排,防止意外损坏笔记库结构。

SKILL.md

name
pop-obsidian
description
>
version
1.0.0

POP Super-Obsidian — Plugin Orchestration Protocol

The POP protocol enables real-time orchestration of multi-step pipelines through Obsidian. It connects Claude (orchestrator), Obsidian (vault + UI), and the Rust TUI (monitoring dashboard) via JSON-RPC over WebSocket at ws://127.0.0.1:8088.

Protocol Overview

POP operates in 5 phases, each with specific JSON-RPC message types:

Phase 1: Discovery

Message: GET_PLUGIN_MANIFEST Purpose: Ask the Obsidian plugin what capabilities are installed.

{
  "jsonrpc": "2.0",
  "method": "GET_PLUGIN_MANIFEST",
  "id": 1
}

Response: Returns a manifest of all installed Obsidian plugins with their exposed actions. Use this to understand what the vault can do before constructing a pipeline.

Phase 2: Orchestration

Message: EXECUTE_PIPELINE Purpose: Send a named pipeline with steps to execute.

{
  "jsonrpc": "2.0",
  "method": "EXECUTE_PIPELINE",
  "params": {
    "pipeline": "idea-to-publish",
    "steps": [
      {"id": "spark", "action": "create_note", "params": {"title": "...", "content": "..."}},
      {"id": "expand", "action": "ai_expand", "params": {"note_id": "$spark.output.id"}},
      {"id": "visual", "action": "generate_figure", "params": {"note_id": "$expand.output.id"}},
      {"id": "verify", "action": "wave_check", "params": {"content": "$expand.output.content"}},
      {"id": "assemble", "action": "merge_notes", "params": {"ids": ["$spark", "$expand", "$visual"]}},
      {"id": "export", "action": "export_pdf", "params": {"note_id": "$assemble.output.id"}}
    ],
    "coherence_threshold": 0.85,
    "atom_token": "$ATOM_TOKEN_RESONANCE"
  },
  "id": 2
}

Step references: Use $step_id.output.field to reference outputs from previous steps. This creates a DAG of dependencies that the orchestrator resolves in topological order.

Phase 3: Progress

Message: STEP_COMPLETE Direction: Obsidian → Claude (notification)

{
  "jsonrpc": "2.0",
  "method": "STEP_COMPLETE",
  "params": {
    "pipeline_id": "...",
    "step_id": "expand",
    "status": "complete",
    "output": {"id": "note-abc", "content": "..."},
    "wave_score": 0.91,
    "duration_ms": 1250
  }
}

Each step completion is forwarded to the Rust TUI for real-time gauge updates.

Phase 4: Coherence

Message: COHERENCE_REPORT Purpose: Full pipeline coherence assessment after all steps complete.

{
  "jsonrpc": "2.0",
  "method": "COHERENCE_REPORT",
  "params": {
    "pipeline_id": "...",
    "overall_score": 0.89,
    "step_scores": {"spark": 0.92, "expand": 0.91, "visual": 0.87, "verify": 0.93},
    "conservation_check": {"alpha": 7, "omega": 8, "sum": 15, "valid": true},
    "atom_trail_id": "ATOM-2026-02-16-..."
  }
}

If overall_score < coherence_threshold, the pipeline is flagged for review.

Phase 5: Error

Message: PIPELINE_FAILED Direction: Either direction (any party can signal failure)

{
  "jsonrpc": "2.0",
  "method": "PIPELINE_FAILED",
  "params": {
    "pipeline_id": "...",
    "failed_step": "visual",
    "error": "Figure generation timed out",
    "partial_outputs": {"spark": "...", "expand": "..."},
    "recovery": "retry_step"
  }
}

Recovery options: retry_step, skip_step, abort, rollback

Built-in Pipelines

Read references/pipeline-templates.md for full pipeline definitions.

Quick Reference

PipelineTriggerSteps
idea-to-publish"idea to publish", "note to paper"Spark → Expand → Visual → Verify → Assemble → Export
research-digest"research digest", "literature summary"Fetch → Summarize → Score → Tag → Canvas
quantum-circuit"quantum circuit", "place redstone"Generate → Verify → Export mcfunction → Place
paper-draft"draft paper", "write paper"RAG → AI-Researcher → AutoFigure → WAVE → PDF

Connection Architecture

Claude (Orchestrator)
    ↓ JSON-RPC
ws://127.0.0.1:8088
    ↓
Rust WebSocket Bridge (crates/websocket-bridge)
    ├── → Obsidian Plugin (vault operations)
    ├── → Rust TUI (crates/tui — monitoring dashboard)
    └── → WAVE Scorer (coherence at each transition)

The Rust bridge is the central hub. It:

  1. Receives EXECUTE_PIPELINE from Claude
  2. Dispatches steps to Obsidian
  3. Receives STEP_COMPLETE from Obsidian
  4. Forwards telemetry to the TUI
  5. Runs WAVE checks at transitions
  6. Sends COHERENCE_REPORT back to Claude

Authentication

All POP messages include an ATOM token for authentication:

  • $ATOM_TOKEN_RESONANCE — generated via atom_tag_generate
  • Token encodes: session ID, agent identity, coherence threshold, conservation proof
  • Five-strand anyon braid topology (see docs/ATOM_AUTH.md)

Implementing the Obsidian Side

The Obsidian plugin needs to:

  1. Listen on ws://127.0.0.1:8088 for incoming connections
  2. Expose GET_PLUGIN_MANIFEST with all installed plugin actions
  3. Handle EXECUTE_PIPELINE by running steps against the vault
  4. Report STEP_COMPLETE after each step with outputs and timing
  5. Generate COHERENCE_REPORT using vault content analysis

For the TypeScript implementation details, read references/protocol-spec.md.

适合场景

01

OpenClaw 用户查找和安装 Skill 时

02

用户想查找某类 Agent Skill 时

03

需要根据任务场景推荐可安装能力包时

04

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

补充不同宿主或平台的使用分布数据

能力 5

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

OpenClaw

77.69%
按下载量换算2,092

安全审计

VirusTotal

可疑

ClawScan

可疑

Static analysis

通过

权限和风险

需要联网

该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在 warning/failed 结果,不能写成本站确认安全。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills