nano-banana-pro-prompts-recommend-skill
AI skill for OpenClaw & Claude Code — recommend from 10000+ Nano Banana Pro (Gemini) image prompts. Smart search by use case, content remix, sample images.
Personal CRM and relationship graph for OpenClaw. Tracks people, their connections to each other, and what you know about them. Stores everything as Obsidian-friendly Markdown + a JSON graph index. Use when you want to remember who knows who, prepare for meetings, or get nudged about stale relationships.
请根据来源仓库和你的 AI 工具说明安装此技能。先阅读技能文件和依赖要求,再添加到工作流。
SkillHub CLI
skillhub install gobiraj/people-relationship-map打开来源仓库,查看说明和兼容环境后,按来源提供的命令或步骤安装。
将来源链接提供给你的 Agent,让它先读取说明、核对依赖,并向你说明将执行的安装步骤。
A lightweight personal CRM that tracks people as nodes and their connections as edges. Everything is stored as Obsidian-compatible Markdown files (one per person) with a JSON graph index for fast querying.
<workspace>/people/
├── _graph.json # Node + edge index (source of truth for connections)
├── _alex-chen.md # One Markdown file per person
├── _jordan-lee.md
└── ...
Each person file uses this template:
# Alex Chen
- **Tags:** #colleague #engineering
- **Org:** Acme Corp
- **Role:** Staff Engineer
- **Met:** 2025-06-15
- **Last contact:** 2026-02-20
- **Tier:** close
## Notes
- 2026-02-20 — Mentioned looking for a new apartment in Brooklyn
- 2026-01-10 — Helped me debug the auth migration
## Connections
- [[Jordan Lee]] — same team at Acme
- [[Sam Patel]] — college roommates
The _graph.json file stores the machine-readable graph:
{
"nodes": {
"alex-chen": {
"displayName": "Alex Chen",
"tags": ["colleague", "engineering"],
"org": "Acme Corp",
"role": "Staff Engineer",
"met": "2025-06-15",
"lastContact": "2026-02-20",
"tier": "close",
"file": "_alex-chen.md"
}
},
"edges": [
{
"from": "alex-chen",
"to": "jordan-lee",
"label": "same team at Acme"
}
]
}
All commands go through the Python script. Run them via:
python3 {baseDir}/scripts/relmap.py <command> [options]
python3 {baseDir}/scripts/relmap.py add \
--name "Alex Chen" \
--tags colleague,engineering \
--org "Acme Corp" \
--role "Staff Engineer" \
--tier close \
--note "Met at the offsite in Denver"
Tiers: close, regular, acquaintance (default: acquaintance).
python3 {baseDir}/scripts/relmap.py link \
--from "Alex Chen" \
--to "Jordan Lee" \
--label "same team at Acme"
这些信息来自收录时的来源分析,可能滞后;使用前请核对最新来源文件。
A lightweight personal CRM that lives inside your OpenClaw workspace. Track people, their connections, and what you know about them — stored as Obsidian-friendly Markdown with a JSON graph index for fast querying.
Copy the skill folder into your OpenClaw workspace:
cp -r people-relationship-map ~/.openclaw/workspace/skills/people-relationship-map
Then ask your agent to "refresh skills" or restart the gateway.
Add this to your ~/.openclaw/openclaw.json under cron.jobs:
{
"name": "relationship-digest",
"schedule": "0 9 * * 0",
"command": "python3 skills/people-relationship-map/scripts/relmap.py stale --format message",
"channel": "whatsapp"
}
This sends you a staleness report every Sunday at 9 AM.
Once installed, just talk to your agent naturally:
Everything lives in <workspace>/people/:
| File | Purpose |
|---|---|
_graph.json |
Machine-readable node + edge index |
_<slug>.md |
One Markdown card per person |
The Markdown files use Obsidian-compatible [[wikilinks]] and #tags,
so you can symlink or sync the people/ folder into your vault.
# People Relationship Map
A lightweight personal CRM that tracks people as nodes and their connections
as edges. Everything is stored as Obsidian-compatible Markdown files (one per
person) with a JSON graph index for fast querying.
## Workspace layout
```
<workspace>/people/
├── _graph.json # Node + edge index (source of truth for connections)
├── _alex-chen.md # One Markdown file per person
├── _jordan-lee.md
└── ...
```
Each person file uses this template:
```markdown
# Alex Chen
- **Tags:** #colleague #engineering
- **Org:** Acme Corp
- **Role:** Staff Engineer
- **Met:** 2025-06-15
- **Last contact:** 2026-02-20
- **Tier:** close
## Notes
- 2026-02-20 — Mentioned looking for a new apartment in Brooklyn
- 2026-01-10 — Helped me debug the auth migration
## Connections
- [[Jordan Lee]] — same team at Acme
- [[Sam Patel]] — college roommates
```
The `_graph.json` file stores the machine-readable graph:
```json
{
"nodes": {
"alex-chen": {
"displayName": "Alex Chen",
"tags": ["colleague", "engineering"],
"org": "Acme Corp",
"role": "Staff Engineer",
"met": "2025-06-15",
"lastContact": "2026-02-20",
"tier": "close",
"file": "_alex-chen.md"
}
},
"edges": [
{
"from": "alex-chen",
"to": "jordan-lee",
"label": "same team at Acme"
}
]
}
```
## Commands
All commands go through the Python script. Run them via:
```bash
python3 {baseDir}/scripts/relmap.py <command> [options]
```
### Add a person
```bash
python3 {baseDir}/scripts/relmap.py add \
--name "Alex Chen" \
--tags colleague,engineering \
--org "Acme Corp" \
--role "Staff Engineer" \
--tier close \
--note "Met at the offsite in Denver"
```
Tiers: `close`, `regular`, `acquaintance` (default: `acquaintance`).
### Link two people
```bash
python3 {baseDir}/scripts/relmap.py link \
--from "Alex Chen" \
--to "Jordan Lee" \
--label "same team at Acme"
```
### Add a note to a person
```b...# People Relationship Map — OpenClaw Skill
A lightweight personal CRM that lives inside your OpenClaw workspace. Track
people, their connections, and what you know about them — stored as
**Obsidian-friendly Markdown** with a JSON graph index for fast querying.
## Features
- **Add & link people** — build a relationship graph through natural commands
- **Auto-capture** — the agent picks up people mentions from conversations
- **Query & search** — find people by org, tag, tier, or free-text notes
- **Obsidian-native** — each person gets a Markdown card with wikilinks and tags
- **Weekly digest** — cron job nudges you about relationships going stale
- **Mermaid export** — visualize your graph in any Markdown renderer
## Install
Copy the skill folder into your OpenClaw workspace:
```bash
cp -r people-relationship-map ~/.openclaw/workspace/skills/people-relationship-map
```
Then ask your agent to "refresh skills" or restart the gateway.
### Optional: enable the weekly digest cron
Add this to your `~/.openclaw/openclaw.json` under `cron.jobs`:
```json
{
"name": "relationship-digest",
"schedule": "0 9 * * 0",
"command": "python3 skills/people-relationship-map/scripts/relmap.py stale --format message",
"channel": "whatsapp"
}
```
This sends you a staleness report every Sunday at 9 AM.
## Quick start
Once installed, just talk to your agent naturally:
- "Add Alex Chen — he's an engineer at Acme, we met at the Denver offsite"
- "Alex and Jordan are on the same team"
- "I just had lunch with Sam"
- "Who do I know at Acme?"
- "Tell me about Alex"
- "Who is connected to Jordan?"
- "Show me my stale relationships"
## Storage
Everything lives in `<workspace>/people/`:
| File | Purpose |
|------|---------|
| `_graph.json` | Machine-readable node + edge index |
| `_<slug>.md` | One Markdown card per person |
The Markdown files use Obsidian-compatible `[[wikilinks]]` and `#tags`,
so you can symlink or sync the `people/` folder into your vault.
## Tier system...AI skill for OpenClaw & Claude Code — recommend from 10000+ Nano Banana Pro (Gemini) image prompts. Smart search by use case, content remix, sample images.
AI Agent Orchestrator with Skills System - Give AI Agents superpowers: memory search, code graph queries, agent-to-agent messaging. Manage Claude, Codex or any AI Agent from one dashboard. Move Agents between c...
AI agent skills for the Universal Registry - search, chat, and register 72,000+ agents across 14+ protocols. Works with Claude, Codex, Cursor, OpenClaw, and any AI assistant.
A cross-platform skills manager for AI IDEs. Search marketplace, download locally, and install to Claude, Cursor, Windsurf, and more with one click.