What makes CamScanner Official Skill notable?

1.7K downloads. Trust evidence available

How should CamScanner Official Skill 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

CamScanner Official Skill

CamScanner Official Skill — intelligent document conversion and processing. Use when the user mentions CamScanner, format conversion (image/PDF to Word/Excel/Markdown, Word/Excel/PPT to PDF, Office document format conversion, images to PDF), image enhancement/upscaling/restoration, OCR, image translation, formula extraction, watermark add/remove, multi-image merge, document scanning/editing, invoice/receipt recognition, or cloud document search/download/move/folder management. Does not support merging existing PDFs into one file.

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

1.7k

Updated

Oct 10, 2026

Version

1.1.8

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 1.7K 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: 1.7K downloadsadoption · observed Oct 10, 2026
Latest release: 1.1.8release · observed Sep 17, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s173fgwczhaenp3btzq1h17qss84dnaa:cs-cli

Install using `clawhub skill install s173fgwczhaenp3btzq1h17qss84dnaa:cs-cli` 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/camscanner-ai/cs-cli before using production credentials.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-camscanner-ai-cs-cli/snapshot"

Documentation

CLAWHUB

148,116 characters of source documentation, loaded on request.

Extracted files

5 files captured from the source.

SKILL.md

---
name: "camscanner"
display_name: "CamScanner Official Skill"
display_name_en: "camscanner"
description: "CamScanner Official Skill — intelligent document conversion and processing. Use when the user mentions CamScanner, format conversion (image/PDF to Word/Excel/Markdown, Word/Excel/PPT to PDF, Office document format conversion, images to PDF), image enhancement/upscaling/restoration, OCR, image translation, formula extraction, watermark add/remove, multi-image merge, document scanning/editing, invoice/receipt recognition, or cloud document search/download/move/folder management. Does not support merging existing PDFs into one file."
description_en: "CamScanner Official Skill — intelligent document conversion and processing. Use when the user mentions CamScanner, format conversion (image/PDF to Word/Excel/Markdown, Word/Excel/PPT to PDF, Office document format conversion, images to PDF), image enhancement/upscaling/restoration, OCR, image translation, formula extraction, watermark add/remove, multi-image merge, document scanning/editing, invoice/receipt recognition, or cloud document search/download/move/folder management. Does not support merging existing PDFs into one file."
homepage: "https://www.camscanner.com"
version: "1.1.8"
category: "productivity"
author: "CamScanner"
---
# CamScanner CLI Skill Guide

The CamScanner CLI Skill provides a complete document processing toolkit through the `camscanner-cli` command-line tool and the CamScanner AI Tools API. It supports image enhancement, OCR, format conversion, Office document conversion (Word/Excel/PPT to PDF or format upgrade), watermarking, translation, restoration, multi-image conversion to PDF/Word/Excel, receipt recognition, and other image/PDF processing operations, as well as cloud document search, download, move, and folder management.

## Check Capability Before Execution

1. Use the request, existing attachments, paths, and context to determine input types, count, order, and final artifacts. Ask only for missing information that affects the result; do not request files or an order already provided.
2. **The current CLI cannot merge existing PDFs into one file.** `image merge-pdf` accepts images only, up to 100. For PDF merging, clearly state this limitation; do not collect paths, require login, or promise a merged file and cloud link. `pdf to-images` followed by `image merge-pdf` is lossy image reconstruction, not a supported PDF merge workaround in this Skill.
3. Once a complete supported execution path and the required inputs are available, complete the initial environment checks, read the relevant references, choose save options, and execute. Capability questions and known unsupported requests require no installation, upgrade, or authentication.
4. Apply the save policy only to final artifacts of supported operations; keep intermediate files locally as needed by the next step. Do not change the requested format, order, or number of artifacts to satisfy a save rule.
5. After e

_meta.json

{
  "ownerId": "kn7dkyvbm015dqjkd5jkytw21n835q3n",
  "slug": "cs-cli",
  "version": "1.1.8",
  "publishedAt": 1789627850847
}

references/batch-convert.md

# Batch Document Conversion Workflow

> **Preread**: `references/image-processing.md` for image command parameters, and `references/pdf-processing.md` for PDF command parameters.

## Scenario

The user has multiple files that need to be converted into a common format, such as a batch of scans converted to editable documents.

## Decision Flow

### 1. Confirm Input Files

- Reuse existing attachments and paths and verify the file list. Preserve explicit user order; otherwise use natural sorting. Ask only about unresolved ambiguity that affects the result.
- Confirm each file format and the target format.
- **Hard limit: multi-image merge commands (`merge-*`) accept at most 100 input images per command.**

### 2. Handling More Than 100 Images

When there are more than 100 input images:

- **Do not automatically split into batches**. The CLI has no PDF/Word/Excel document merge command, so batch outputs cannot be recombined into a single file.
- The agent **must** tell the user: "At most 100 images can currently be merged into one document. More than 100 images cannot be merged into a single file."
- If the user accepts multiple volumes, process batches of at most 100 images and clearly label each volume.
- If the user must have one single file, explain that this is not currently supported.

### 3. Select a Conversion Strategy

| Input | Target | Strategy | Command |
|-------|--------|----------|---------|
| Multiple images, <=100 -> one document | Word/PDF/Excel | Merge | `image merge-word/pdf/excel` |
| Multiple PDFs -> one file | Any | Unsupported; tell the user | No PDF merge command |
| One PDF -> editable format | Word/Excel/MD | Convert | `pdf convert --format xx` |
| One Office document -> PDF or format upgrade | PDF/DOCX/XLSX/PPTX | Convert | `office convert` |
| Multiple independent files -> separate outputs | Mixed | Process one by one | Invoke the corresponding command for each file |

### 4. Execute and Confirm

- Apply the final-artifact save policy in `SKILL.md`: without a save preference use `-o path -s` (`-d dir -s` for PDF-to-images), with `--save-title` when saving to cloud.
- Verify artifact count, page count, and order. Report local files and actual returned cloud links by successful stage; a missing link means incomplete results.
- Record failures on independent files. Continue with others only until the main guide's attempt or cumulative failure limit is reached; report successful, failed, and unprocessed items.

references/cloud-documents.md

# Cloud Document Management Reference

### doc search — Search Cloud Documents

Search the user's CamScanner cloud documents. Supports keyword search, time range filtering, and document type filtering, which can be combined.

```bash
camscanner-cli doc search [keyword] [flags]
```

| Parameter/Flag | Description |
|----------------|-------------|
| `keyword` (positional) | Search keywords (multiple words separated by spaces; any match counts — OR semantics) |
| `-f, --filter` | Document type filter: pdf/word/excel/ppt/image/markdown/html |
| `-n, --limit` | Maximum number of results (default 5, max 50) |
| `-a, --after` | Start time (supports `2006-01-02`, `2006-01-02 15:04:05`, or unix timestamp) |
| `-b, --before` | End time (same formats as above) |
| `-s, --scope` | Search scope: `title` (default — title + page title + notes) or `full` (includes OCR full text) |

**Usage examples**:

```bash
# Search for documents containing "contract"
camscanner-cli doc search "contract"

# Search recent PDF documents
camscanner-cli doc search -f pdf -n 10

# Search documents within a time range
camscanner-cli doc search --after 2026-08-01 --before 2026-08-31

# Keyword + type + time combined search
camscanner-cli doc search "report" -f word --after 2026-08-01

# Full-text search (including OCR content)
camscanner-cli doc search "invoice number" -s full -n 20
```

**Output format**: The CLI displays search results in a table.

**Agent display rules (mandatory)**: When presenting search results to the user, the agent **must** include at least the following four columns:

| Column | Source | Description |
|--------|--------|-------------|
| Title | CLI output "标题" column | Document title |
| Type | Inferred from link URL path (see rules below) | Document type |
| Folder | CLI output "所在目录" column | Folder containing the document |
| Link | CLI output "链接" column | Clickable web page URL |

> **Type inference rules** (two-step):
> 1. **Prefer URL path inference**: `/pdfDetail` → PDF, `/markdownDetail` → Markdown, `/detail` → Scan/Image, `/htmlDetail` → HTML
> 2. **When the path is ambiguous, use cs_doc_id suffix**: `/officeDetail` covers Word, Excel, and PPT. Disambiguate using the Document ID suffix: `_word1` → Word, `_exce1` → Excel, `_pptx1` → PPT
>
> The agent must not omit the Type column or show only title and link.

> **cs_doc_id (internal use)**: The CLI output "文档ID" column contains the `cs_doc_id`, which is the required parameter for `doc download` and `doc move`. The agent should capture this value from search results for subsequent operations, but it **does not need to be displayed to the user**.

**Agent behavior rules**:
- When the user says "find/search/look up my documents", use `doc search` — **do not** enter the image/pdf processing flow.
- Multiple keywords are separated by spaces and use OR semantics (any match counts).
- When no keyword is provided, returns the most recent document list.
- Default returns 5 results; increase `-n` when the u

references/image-enhance.md

# Image Enhancement and Restoration Workflow

> **Preread**: `references/image-processing.md` for the enhance mode list and the `hd`/`restore` parameters.

## Scenario

The user has blurry, dark, shadowed, or scratched photos that need restoration or enhancement.

## Decision Tree

| User Description | Route To |
|------------------|----------|
| "The photo is too blurry" | `image hd` |
| "The photo is too dark" | `image enhance --mode 1` |
| "There are shadows" | `image enhance --mode 5` |
| "The old photo has scratches" | `image restore` |
| "A screen photo has patterns" | `image enhance --mode 8` |
| "I want a black-and-white effect" | `image enhance --mode 3` |
| "Remove handwritten annotations" | `image enhance --mode 9` |
| "Remove the watermark" | `image enhance --mode 10` |

## Multi-Step Combination

If one pass is not good enough, chain operations by writing an intermediate local output and processing it again:

```text
camscanner-cli image enhance input.jpg --mode 5 -o temp.jpg
# Continue only after the preceding step succeeds and temp.jpg is usable.
camscanner-cli image hd temp.jpg -o enhanced.jpg -s --save-title "Enhanced image"
```

Keep intermediate artifacts local. The example saves the final artifact to both destinations by default; adjust for explicit preferences using `SKILL.md` and avoid overwriting existing files.

Github ReposUpdated 12h 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.