openclaw 网盘下载
OpenClaw

技能详情(站内镜像,无评论)

首页 > 技能库 > PikaBoard

Interact with PikaBoard task management API. Use when creating, updating, listing, or managing tasks. Agent-first kanban for AI teams. Triggers on: tasks, kanban, board, todo, backlog, sprint.

开发与 DevOps

许可证:MIT-0

MIT-0 ·免费使用、修改和重新分发。无需归因。

版本:v1.0.3

统计:⭐ 1 · 1.5k · 1 current installs · 1 all-time installs

1

安装量(当前) 1

🛡 VirusTotal :良性 · OpenClaw :良性

Package:angelstreet/pikaboard

安全扫描(ClawHub)

  • VirusTotal :良性
  • OpenClaw :良性

OpenClaw 评估

The skill's files, instructions, and requirements line up with a self-hosted PikaBoard integration — nothing requested is disproportionate to its purpose, though it does clone and build third‑party code (expected for this skill).

目的

Name/description (PikaBoard API / kanban) match the actual requirements: node/npm, cloning a GitHub repo, building backend/frontend, and using a local API token. There are no unrelated credentials or binaries requested.

说明范围

SKILL.md and helper scripts focus on installing/running the PikaBoard server, configuring PIKABOARD_TOKEN, and mapping an agent to a board. The scripts only read/write the repo, .env, optional BOARD_ENV_FILE, and call the PikaBoard API. They do not attempt to read unrelated system files or exfiltrate other secrets.

安装机制

Installation is instruction-driven and clones https://github.com/angelstreet/pikaboard then runs npm install / build. Cloning from GitHub is expected, but running npm install/build can execute arbitrary install/build scripts from dependencies — this is normal for Node projects but is a point of execution risk that users should accept consciously.

证书

The only secrets in play are the PIKABOARD_TOKEN (API auth) and local DB path, which are appropriate for a self-hosted API. The skill does not request unrelated cloud credentials or other tokens.

持久

The skill is not always-enabled and does not request elevated system-wide privileges. It may write an optional BOARD_ENV_FILE (to a user-specified path) and its own backend/.env; this is reasonable for onboarding agents to boards.

综合结论

This skill appears to be what it says: a self-hosted PikaBoard integration. Before installing, verify you trust the GitHub repository since the install steps clone it and run npm install/build (npm scripts can run arbitrary code). Running the backend will open a local server (default port 3001) protected by PIKABOARD_TOKEN — treat that token as a secret. Consider running the service in an isolated environment/container, review the repo code if…

安装(复制给龙虾 AI)

将下方整段复制到龙虾中文库对话中,由龙虾按 SKILL.md 完成安装。

请把本段交给龙虾中文库(龙虾 AI)执行:为本机安装 OpenClaw 技能「PikaBoard」。简介:Interact with PikaBoard task management API. Use when creating, updating, listi…。
请 fetch 以下地址读取 SKILL.md 并按文档完成安装:https://raw.githubusercontent.com/openclaw/skills/refs/heads/main/skills/angelstreet/pikaboard/SKILL.md
(来源:yingzhi8.cn 技能库)

SKILL.md

打开原始 SKILL.md(GitHub raw)

---
name: pikaboard
description: "Interact with PikaBoard task management API. Use when creating, updating, listing, or managing tasks. Agent-first kanban for AI teams. Triggers on: tasks, kanban, board, todo, backlog, sprint."
metadata:
  openclaw:
    emoji: "📋"
    requires:
      bins: ["node", "npm"]
    install:
      - id: clone
        kind: git
        repo: https://github.com/angelstreet/pikaboard
        branch: main
        label: "Clone PikaBoard repository"
      - id: backend
        kind: script
        cwd: "pikaboard/backend"
        run: "npm install && npm run build"
        label: "Install backend dependencies"
      - id: frontend
        kind: script
        cwd: "pikaboard/frontend"
        run: "npm install && npm run build"
        label: "Build frontend"
      - id: env
        kind: prompt
        message: "Create .env with DATABASE_PATH and PIKABOARD_TOKEN"
        label: "Configure environment"
---

# PikaBoard

Agent-first task/kanban dashboard. **PikaBoard is the source of truth for tasks.**

## Quick Start

After install, start the server:
```bash
cd pikaboard/backend && npm start
```

Access dashboard at `http://localhost:3001`

## Configuration

Create `backend/.env`:
```env
DATABASE_PATH=./pikaboard.db
PIKABOARD_TOKEN=your-secret-token
PORT=3001
```

Add to your TOOLS.md:
```markdown
## PikaBoard
- **API:** http://localhost:3001/api/
- **Token:** your-secret-token
```

Agent runtime variables:
```bash
export PIKABOARD_API="http://localhost:3001/api"
export PIKABOARD_TOKEN="your-secret-token"
export AGENT_NAME="bulbi"
```

## Task Commands

Reference tasks by ID:
- `task 12` or `#12` → view task
- `move #12 to done` → status change
- `create task "Fix bug"` → new task

## API Reference

See `backend/API.md` for full endpoint documentation (single canonical doc).

### Common Operations

**List tasks:**
```bash
curl -H "Authorization: Bearer $PIKABOARD_TOKEN" "$PIKABOARD_API/tasks"
```

**Create task:**
```bash
curl -X POST -H "Authorization: Bearer $PIKABOARD_TOKEN" 
  -H "Content-Type: application/json" 
  -d '{"name":"Fix bug","status":"inbox","priority":"high","tags":["bug","backend"]}' 
  "$PIKABOARD_API/tasks"
```

**Update status:**
```bash
curl -X PATCH -H "Authorization: Bearer $PIKABOARD_TOKEN" 
  -H "Content-Type: application/json" 
  -d '{"status":"done"}' 
  "$PIKABOARD_API/tasks/123"
```

## Enums

| Field | Values |
|-------|--------|
| status | `inbox`, `up_next`, `in_progress`, `testing`, `in_review`, `done`, `rejected` |
| priority | `low`, `medium`, `high`, `urgent` |

## Agent Onboarding (Simple Path)

Use the helper to map each agent to a board automatically:

```bash
cd pikaboard
MY_BOARD_ID="$(
  ./skills/pikaboard/scripts/setup-agent-board.sh | sed -n 's/^MY_BOARD_ID=//p' | tail -n1
)"
export MY_BOARD_ID
```

What it does:
- Reads `PIKABOARD_API`, `PIKABOARD_TOKEN`, `AGENT_NAME`
- Finds board by `BOARD_NAME` (default: `AGENT_NAME`)
- Creates board if missing
- Prints `MY_BOARD_ID=<id>`
- Verifies `GET /api/tasks?board_id=<id>&status=up_next`

Optional:
```bash
export BOARD_NAME="Bulbi"
export BOARD_ENV_FILE="$HOME/.openclaw/agents/bulbi/.pikaboard.env"
./skills/pikaboard/scripts/setup-agent-board.sh
```

## Multi-Agent Setup

Each agent can have their own board. Use `board_id` parameter:
```bash
curl "$PIKABOARD_API/tasks?board_id=6" -H "Authorization: Bearer $PIKABOARD_TOKEN"
```

Board assignments:
- Board 1: Pika (main)
- Board 2: Tortoise (personal)
- Board 3: Sala (work)
- Board 4: Evoli (VirtualPyTest)
- Board 5: Psykokwak (EZPlanning)
- Board 6: Bulbi (PikaBoard)
- Board 7: Mew (Ideas)

## Validation Checklist

Run after setup:

```bash
# 1) API reachable
curl -s http://localhost:3001/health

# 2) Auth works
curl -s -H "Authorization: Bearer $PIKABOARD_TOKEN" "$PIKABOARD_API/boards"

# 3) Board mapping works
echo "$MY_BOARD_ID"

# 4) Agent can read own queue
curl -s -H "Authorization: Bearer $PIKABOARD_TOKEN" 
  "$PIKABOARD_API/tasks?board_id=$MY_BOARD_ID&status=up_next"
```