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审计通过

im-framework即时通讯框架

Agent Skill

im-framework 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

12,165

周安装

512

GitHub Stars

公开资料未说明

下载量

4,260
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:im-framework(即时通讯框架)
来源仓库:https://github.com/kapslap/im-framework
安装命令:
openclaw skills install im-framework
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 im-framework

简介

im-framework 参考 Forrest Landry 内在形而上学框架,提供结构化本体索引。

  • 适用于实时推理与知识组织,支持 767 个实体的结构化查询。
  • 通过自然语言输入触发,辅助复杂概念解释与应用。
  • 建议确认本体更新频率及是否依赖外部数据源。
  • 可结合来源仓库和 README 进一步核验使用限制。

SKILL.md

name
im-framework
version
1.5
description
|

Immanent Metaphysics Framework

Source: https://mflb.com/8192 — Forrest Landry's whitebook. This is the canonical text. The ontology in references/graph.jsonl is an index into it. Always fetch the source URL and quote exactly.

Reference Files

All files are in references/ (relative to this skill directory):

FileContents
graph.jsonl767 entities — Concepts, Axioms, Theorems, Aphorisms, Implications + relations
whitebook-map.jsonl73-entry structural map of whitebook chapters/sections with URLs
schema.yamlType definitions and relation types
section-anchors.jsonAnchor-level URL map for fine-grained source links

Workflow

  1. Search the graph — find the relevant entity in references/graph.jsonl
  2. Get the URL — use the location field from the entity's properties
  3. Fetch the sourceweb_fetch(location_url) to get exact text
  4. Quote verbatim — cite with URL

Graph Query Examples

# Set path relative to skill dir (resolve from dirname of SKILL.md)
GRAPH="$(dirname $(realpath ~/Tillerman/Eitan/skills/im-framework/SKILL.md))/references/graph.jsonl"

# Search by concept name
grep -i '"name": "symmetry"' "$GRAPH"

# Search by keyword across names and definitions
python3 << 'EOF'
import json
GRAPH = "/Users/Jared/Tillerman/Eitan/skills/im-framework/references/graph.jsonl"
TERM = "symmetry"  # change this
for line in open(GRAPH):
    d = json.loads(line)
    if d.get('op') != 'put':
        continue
    e = d.get('entity', {})
    p = e.get('properties', {})
    name = p.get('name', p.get('word', p.get('text', '')))
    defn = p.get('definition', '')
    loc = p.get('location', '')
    if TERM.lower() in (name + defn).lower():
        print(f"{e['type']}: {name}")
        print(f"  URL: {loc}")
        print(f"  Def: {defn[:300]}")
        print()
EOF

# List all entity types and counts
python3 << 'EOF'
import json
from collections import Counter
GRAPH = "/Users/Jared/Tillerman/Eitan/skills/im-framework/references/graph.jsonl"
types = Counter()
for line in open(GRAPH):
    d = json.loads(line)
    if d.get('op') == 'put':
        types[d['entity']['type']] += 1
print(types)
EOF

# Search section anchors for a chapter
python3 << 'EOF'
import json
ANCHORS = "/Users/Jared/Tillerman/Eitan/skills/im-framework/references/section-anchors.json"
anchors = json.load(open(ANCHORS))
# anchors is a dict of {anchor_id: {title, url, ...}}
TERM = "ethics"
for k, v in anchors.items():
    if TERM.lower() in str(v).lower():
        print(k, "->", v.get('url', ''), "|", v.get('title', ''))
EOF

Quoting Rules (MANDATORY)

  • Always use exact quotes from the source at mflb.com. Never paraphrase when the original is available.
  • Every quote must include the direct URL from the entity's location field.
  • Quote format:

> "[exact text from mflb.com]" > — *An Immanent Metaphysics*, [section], [URL]

  • If the exact wording isn't in the ontology: web_fetch the URL directly — get the real text.
  • Aphorisms: use the text field from graph.jsonl verbatim. Do not alter.
  • Definitions: use the definition field verbatim when citing what a term means.
  • Label synthesis clearly: if applying the framework to a new situation, say so — don't present inference as direct quote.

Ontology Contents (references/graph.jsonl)

767 entities across 5 types:

TypeCountDescription
Concept134Named ideas — modality, domain, definition, source URL
Axiom3Foundational axioms — statement, implications, source URL
Theorem11ICT, Symmetry Ethics, Continuity Ethics, Bell's/Godel mappings
Aphorism147From *Effective Choice* — exact text, themes, source URL
Implication4Cross-domain applications (physics, logic, ethics, consciousness)

Relations: implies, paired_with, contrasts_with, depends_on, has_modality, illuminates, defined_in

Chapter URLs

TopicURL
Entry pointhttps://mflb.com/8192
Three Modalitieshttps://mflb.com/dvol/control/pcore/own_books/white_1/wb_web_2/zout/upmp_ch1.htm#1_modalities
Axiomshttps://mflb.com/dvol/control/pcore/own_books/white_1/wb_web_2/zout/upmp_ch1.htm#1_axioms
ICThttps://mflb.com/dvol/control/pcore/own_books/white_1/wb_web_2/zout/upmp_ch3.htm#1_ict
Symmetry / Continuityhttps://mflb.com/dvol/control/pcore/own_books/white_1/wb_web_2/zout/upmp_ch3.htm#1_symmetry
Ethicshttps://mflb.com/dvol/control/pcore/own_books/white_1/wb_web_2/zout/upmp_ch6.htm
Path of Right Actionhttps://mflb.com/dvol/control/pcore/own_books/white_1/wb_web_2/zout/upmp_ch6.htm#2_path
Basal Motivationshttps://mflb.com/dvol/control/pcore/own_books/white_1/wb_web_2/zout/upmp_ch6.htm#2_basal
Aphorisms of Effective Choicehttps://mflb.com/dvol/control/pcore/own_books/white_1/wb_web_2/zout/upmp_ch5.htm
Mindhttps://mflb.com/dvol/control/pcore/own_books/white_1/wb_web_2/zout/upmp_ch8.htm

Attribution

Always attribute to Forrest Landry's *An Immanent Metaphysics*. Distinguish:

  1. Direct citation — exact quote with source URL
  2. Close paraphrase — labeled as paraphrase with source URL
  3. Agent synthesis — labeled as your own application

Do not invent positions. Do not imply Forrest's endorsement of claims not grounded in the source text.

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

88.99%
按下载量换算3,791

安全审计

VirusTotal

通过

ClawScan

通过

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。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