What makes Piccc AI Skills notable?

1.2K downloads. Trust evidence available

How should Piccc AI Skills be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

Piccc AI Skills

Generate images, videos, and audio with Piccc AI (皮可AI), or query and download existing media tasks. Use when the user asks to create visual or audio media with Piccc AI, discover its current models or voices, check an asynchronous task, or download completed results. Do not use for editing existing

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

1.2k

Updated

Oct 10, 2026

Version

0.1.4

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 1.2K downloads reported by the source. Last updated 10/10/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 10, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 10, 2026
Adoption signal: 1.2K downloadsadoption · observed Oct 10, 2026
Latest release: 0.1.4release · observed Jul 28, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s17d4nz97fhj3qj7erq9pnpe9d86hwph:piccc-ai-skills

Install using `clawhub skill install s17d4nz97fhj3qj7erq9pnpe9d86hwph:piccc-ai-skills` in an isolated environment before connecting it to live workloads.
No published capability contract is available yet, so validate auth and request/response behavior manually.
Review the upstream CLAWHUB listing at https://clawhub.ai/xiaoyaocz/piccc-ai-skills before using production credentials.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-xiaoyaocz-piccc-ai-skills/snapshot"

Documentation

CLAWHUB

54,467 characters of source documentation, loaded on request.

Extracted files

5 files captured from the source.

SKILL.md

---
name: piccc-ai
description: Generate images, videos, and audio with Piccc AI (皮可AI), or query and download existing media tasks. Use when the user asks to create visual or audio media with Piccc AI, discover its current models or voices, check an asynchronous task, or download completed results. Do not use for editing existing local media.
---

# Piccc AI (皮可AI)

Use `{baseDir}/scripts/piccc.mjs` for every Piccc AI request. `{baseDir}` is the directory containing this file.

## Language

- Reply in the user's current language.
- Do not mix translated Chinese and English phrases in one response. The product name `Piccc AI (皮可AI)` is the only intentional bilingual form.
- Treat CLI output as internal data and explain it naturally in the user's language.

## Installation and first authorization

When the skill has just been installed, tell the user in their current language that installation is complete, browser authorization is required, and the available credit balance will be reported afterward.

Before the first request, run `node {baseDir}/scripts/piccc.mjs auth status`. If it reports `authenticated: false`:

1. Explain that the user must sign in and approve access in the browser.
2. Run `node {baseDir}/scripts/piccc.mjs auth login` and wait for it to finish. The command opens the authorization page, receives the local callback, saves the API key, and queries the available balance. Do not ask the user to report completion.
3. If the browser cannot be opened, share the displayed link and verification code while the command keeps waiting. Never ask the user to create, copy, or paste an API key.
4. After authorization, read `available_credits` from the result and report the balance in the user's current language.
5. If `available_credits` is unavailable, run `node {baseDir}/scripts/piccc.mjs credits` and then report the returned balance.

## Workflow

1. Unless the user names a model or asks for higher quality, run `models TYPE --economy` and use its selected model and defaults. Prefer lower cost over speed or quality.
2. Let explicit user requirements override economy defaults. Otherwise use one output, the lowest supported resolution and quality, the shortest supported video duration, no audio or web search, and the lowest supported audio sample rate.
3. If `special_offer` is true, warn the user in their current language before submission that special-offer models may be slower and less reliable.
4. Select only values advertised by the live model response. Never invent model IDs, voice IDs, formats, ratios, resolutions, modes, or durations.
5. Put long or multiline prompts in a UTF-8 file and use `--prompt-file`.
6. When the user expects a finished file, use `--wait --output-dir DIR` in the initial request. Do not create another task while waiting.
7. On timeout, return the task ID and latest status so the same task can be resumed. Treat `completed`, `failed`, and `cancelled` as terminal.
8. For audio, call the initial 10 credits a precharge

README.md

# Piccc AI（皮可AI）技能

[![皮可AI，让创意一键成型](assets/piccc-ai-banner.png)](https://picccai.cn)

让 Codex、OpenClaw 和其他兼容智能体技能标准的工具调用 Piccc AI（皮可AI），生成图片、视频和音频，并自动等待、下载生成结果。

## 快速安装

把下面这句话发给智能体：

```text
安装技能 https://github.com/xiaoyaocz/piccc-ai-skills
```

也可以使用 Skills 命令行工具：

```bash
npx skills add xiaoyaocz/piccc-ai-skills
```

安装程序会识别仓库中的 `piccc-ai` 技能，并让你选择 Codex、OpenClaw 或其他已支持的智能体。

## 连接皮可AI账号

安装完成后，智能体应主动提示你完成账号授权。也可以直接告诉智能体：

```text
连接我的皮可AI账号
```

智能体会自动打开授权页面。登录 Piccc AI（皮可AI）并确认授权后，页面会跳转到本地完成连接，智能体会自动继续、查询当前可用积分并告诉你；API 密钥会创建并保存在本机，不需要复制密钥、配置环境变量或再回复“已经完成”。

如果浏览器无法自动打开，命令仍会显示授权链接和验证码，手动打开链接即可。也可以使用 `node scripts/piccc.mjs auth login --no-browser` 明确启用原来的手动授权方式。

## 使用

安装后直接告诉智能体你要生成什么，例如：

```text
用皮可AI生成一张 16:9 的电影感雪山日出图，完成后下载到 output/sunrise。
```

```text
用皮可AI把这段产品介绍生成中文旁白，先列出可用音色让我选择。
```

```text
查询皮可AI任务 task_xxx，完成后把结果下载到 output/piccc。
```

技能会先读取后台当前可用的模型和参数，不会固定模型名称。未指定规格时默认优先选择更优惠的模型和低分辨率、低质量配置；使用特价模型前会提示生成可能较慢、不稳定。

查看当前授权状态：

```bash
node scripts/piccc.mjs auth status
```

取消本机授权：

```bash
node scripts/piccc.mjs auth logout
```

## 手动安装

下载仓库后，把根目录中的 `SKILL.md`、`agents`、`references` 和 `scripts` 复制到对应的 `piccc-ai` 目录：

| 智能体 | 当前项目 | 全局使用 |
| --- | --- | --- |
| Codex | `.agents/skills/piccc-ai` | `~/.codex/skills/piccc-ai` |
| OpenClaw | `<workspace>/skills/piccc-ai` | `~/.openclaw/skills/piccc-ai` |

OpenClaw 也可以直接安装本地目录：

```bash
openclaw skills install ./piccc-ai-skills
```

脚本需要 Node.js 20 或更高版本，不需要安装 npm 依赖。

## 本地检查

```bash
npm run check
```

查看脚本支持的命令：

```bash
node scripts/piccc.mjs --help
```

_meta.json

{
  "ownerId": "kn797z5rnyaaady2chsrh164ws86gp7h",
  "slug": "piccc-ai-skills",
  "version": "0.1.4",
  "publishedAt": 1785230989290
}

references/api.md

# Piccc AI 媒体接口

## 连接账号

首次使用时运行：

```bash
node scripts/piccc.mjs auth login
```

命令会自动打开授权页面。登录 Piccc AI（皮可AI）并确认授权后，页面会跳转到本机回调页，脚本随后自动创建并保存 API 密钥、查询当前可用积分。命令会一直等待授权结果，不要让用户在对话中发送密钥，也不要要求用户另行回复“已完成”。浏览器无法打开时，使用命令显示的链接和验证码；`auth login --no-browser` 可保留纯手动流程。

## 模型接口

| 类型 | 接口 | 主要能力字段 |
| --- | --- | --- |
| 图片 | `GET /v1/images/models` | 比例、分辨率、质量、生成数量 |
| 视频 | `GET /v1/videos/models` | 分辨率、比例、时长、生成模式、参考模式 |
| 音频 | `GET /v1/audio/models` | 格式、采样率、参数范围、参考模式、音色 |

每次创建任务前使用模型响应中的 `data[].id`。音色使用 `voice_presets[].id`，不要传显示名称。

## 经济规格

默认先运行：

```bash
node scripts/piccc.mjs models image --economy
```

将 `image` 换成 `video` 或 `audio`。命令会返回推荐模型、`defaults`、`special_offer` 和 `warning`。

- 用户没有指定时，使用 `defaults` 中的低分辨率、低质量、单个输出、最短视频时长和低采样率。
- 默认关闭视频音频、联网搜索和不必要的参考素材。
- 用户明确要求高清、高质量、更长时长或指定模型时，以用户要求为准。
- `special_offer=true` 时，创建任务前提示：“特价模型可能生成较慢、稳定性较差。”
- 即使没有运行 `--economy`，生成脚本也会为未传参数补上当前模型支持的经济规格。

## 创建任务

图片：`POST /v1/images/tasks`

- 必填：`model`、`prompt`
- 可选：`aspect_ratio`、`resolution`、`quality`、`n`、`web_search`、`external_id`

视频：`POST /v1/videos/tasks`

- 必填：`model`、`prompt`
- 可选：`route_mode`、`reference_mode`、`resolution`、`aspect_ratio`、`duration_seconds`、`audio`、`web_search`、`external_id`

音频：`POST /v1/audio/tasks`

- 必填：`model`、`prompt`
- 可选：`output_format`、`sample_rate`、`speech_rate`、`loudness_rate`、`pitch_rate`、`reference_mode`、`voice_id`、`audio_references`、`image_references`、`external_id`
- `reference_mode=audio` 时传 `voice_id` 或 `audio_references`
- `reference_mode=image` 时传 `image_references`
- 提交时预扣 10 积分，完成后的 `actual_cost` 是最终费用

## 查询任务

- `GET /v1/tasks/{task_id}`：查询单个图片、视频或音频任务。
- `GET /v1/tasks`：分页查询任务，可按 `type` 和 `status` 过滤。

任务状态包括 `queued`、`running`、`completed`、`failed`、`cancelled`。只有 `completed` 状态下的 `outputs[].url` 才是最终结果。

skill-card.md

## Description:

Generate images, videos, and audio with Piccc AI (皮可AI), and query or download completed media tasks.

This skill is ready for commercial/non-commercial use.

## Publisher:

[xiaoyaocz](https://clawhub.ai/user/xiaoyaocz)

### License/Terms of Use:

MIT-0

## Use Case:

Developers and agent users use this skill to authorize a Piccc AI account, discover available media models and voices, submit image, video, or audio generation tasks, and wait for or download completed outputs.

### Deployment Geography for Use:

Global

## Known Risks and Mitigations:

Risk: Linking a Piccc AI account and storing a local API key can expose account tokens on shared or untrusted machines.

Mitigation: Install only from a reviewed source, keep the credentials file private, and run auth logout when finished on shared machines.

Risk: Custom Piccc AI API or authorization base URLs can redirect credential or task traffic outside the intended service.

Mitigation: Avoid setting PICCC_API_BASE_URL or PICCC_AUTH_BASE_URL outside controlled testing.

Risk: Generated media downloads may place files in user-selected locations.

Mitigation: Review output directories before downloading completed image, video, or audio results.

## Reference(s):

- [Piccc AI media API reference](references/api.md)
- [Piccc AI website](https://picccai.cn)
- [ClawHub skill page](https://clawhub.ai/xiaoyaocz/skills/piccc-ai-skills)

## Skill Output:

**Output Type(s):** [text, markdown, shell commands, files, guidance]

**Output Format:** [Markdown responses with shell commands and downloaded media files when tasks complete]

**Output Parameters:** [1D]

**Other Properties Related to Output:** [May produce downloaded image, video, or audio files after asynchronous Piccc AI tasks complete.]

## Skill Version(s):

0.1.4 (source: server release evidence; package.json reports 0.1.0)

## Ethical Considerations:

Users should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.

Github ReposUpdated 1d agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.