ClawHub

Akashic Doc Analyzer

v1.0.0

Parse, analyze, and extract content from documents (PDF, DOCX, PPTX, audio). Supports OCR, table extraction, and semantic chunking.

⭐ 0· 130·0 current·0 all-time
by@c7934597

Install

OpenClaw Prompt Flow

Install with OpenClaw

Best for remote or guided setup. Copy the exact prompt, then paste it into OpenClaw for c7934597/akashic-doc-analyzer.

Previewing Install & Setup.
Prompt PreviewInstall & Setup
Install the skill "Akashic Doc Analyzer" (c7934597/akashic-doc-analyzer) from ClawHub.
Skill page: https://clawhub.ai/c7934597/akashic-doc-analyzer
Keep the work scoped to this skill only.
After install, inspect the skill metadata and help me finish setup.
Use only the metadata you can verify from ClawHub; do not invent missing requirements.
Ask before making any broader environment changes.

Command Line

CLI Commands

Use the direct CLI path if you want to install manually and keep every step visible.

OpenClaw CLI

Bare skill slug

openclaw skills install akashic-doc-analyzer

ClawHub CLI

Package manager switcher

npx clawhub@latest install akashic-doc-analyzer
Security Scan
VirusTotalVirusTotal
Pending
View report →
OpenClawOpenClaw
Benign
high confidence
✓
Purpose & Capability
Name/description (document parsing, OCR, table extraction, audio transcription) align with the declared tools (mcp:akashic:process_document, chat_completion, translate_content) and the instructions. There are no unrelated binaries or environment variables requested.
ℹ
Instruction Scope
SKILL.md stays focused on document analysis. It explicitly asks for a file path or uploaded file and instructs using the process_document and chat_completion tools. Note: asking for a local file path is expected for this purpose, but it means the agent will attempt to access that file; users should avoid supplying paths to system or sensitive files they do not want processed or uploaded.
✓
Install Mechanism
No install spec or code files — instruction-only, so nothing is written to disk or fetched during install. This is the lowest-risk install model.
✓
Credentials
The skill declares no environment variables, credentials, or config paths. It depends on an 'mcp: akashic' connector which is consistent with pushing processing to a managed platform; there is no disproportionate credential request in the skill manifest. Users should confirm how the platform connector is authenticated/managed by the agent runtime before sending sensitive documents.
✓
Persistence & Privilege
always is false and the skill does not request persistent system modifications. Default autonomous invocation is allowed (platform default) but is not combined with elevated privileges or broad credentials.
Assessment
This skill appears to do what it says: it asks you for a file (path or upload) and delegates processing to the Akashic connector. Before using it, confirm where processing happens (local vs. remote), how the Akashic connector transmits and stores documents, and whether the platform retains copies. Do not provide paths to system files or other sensitive files you don't want processed or uploaded. If you need to process highly sensitive documents, verify the connector's authentication and data-retention/privacy policy with your platform administrator.

Like a lobster shell, security has layers — review code before you run it.

documentvk972t7r04apmn8g73b02racv8983n31blatestvk972t7r04apmn8g73b02racv8983n31bocrvk972t7r04apmn8g73b02racv8983n31bparsingvk972t7r04apmn8g73b02racv8983n31bpdfvk972t7r04apmn8g73b02racv8983n31b
130downloads
0stars
1versions
Updated 1mo ago
v1.0.0
MIT-0
@c7934597
documentlatestocrparsingpdf
Download

Akashic Document Analyzer

You are a document analysis assistant powered by the Akashic platform. You help users extract, analyze, and summarize content from various document formats.

Supported Formats

  • PDF: Text extraction, table recognition, image OCR (Chinese/English)
  • DOCX: Paragraph and table extraction, heading-based chunking
  • PPTX: Slide-by-slide extraction
  • Audio: Transcription with auto-segmentation (MP3, WAV, etc.)

Workflow

  1. Get the file: Ask the user for the file path or accept the uploaded file
  2. Process the document: Use process_document with appropriate settings:
    • For dense documents: increase chunk_size (e.g., 800)
    • For documents with images: enable OCR (default on)
    • For structured documents: enable use_semantic_chunking (default on)
  3. Analyze content: Use chat_completion to summarize or answer questions about the extracted content
  4. Translate (if needed): Use translate_content for multilingual documents

Rules

  • Always confirm the file path is accessible before processing
  • For large documents, inform the user processing may take a moment
  • Present extracted content in organized sections
  • When summarizing, focus on key points and actionable insights
  • If OCR quality is poor, suggest the user provide a higher-resolution scan

Examples

User: "Analyze this PDF and give me the key points" (with file path) → Use process_document with the file path, then use chat_completion to summarize the chunks

User: "Extract all tables from this Word document" → Use process_document with word_chunk_by_heading=true, focus on table content in results

User: "Transcribe this meeting recording" → Use process_document with the audio file path, audio_chunk_duration=120

Comments

Loading comments...