Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Get Started Free →

Document Processing · vixues | DecimalAI

documentationby vixues

Document Processing

vixues/document-processor

Source vixues/leagent ↗License Apache-2.0

Guidance for processing documents, extracting content, and transforming structured information.

SkillScore59Maintained

Automatic

Doc Ops pack

Last verified 9/1/2026

What it changes

Passed 12 of 20 test cases with the skill, and 9 of 20 without it.

Without skill45%

With skill59%

Checks it passed that the model alone missed

The extracted text preserves the semantic emphasis on key safety terms.
The output includes specific page references for each extracted definition.
The response provides a clear error message indicating the file format is unsupported.

and 1 more in the full report

4 fixed9 passed either way8 still failing1 broke

Pass-rate lift: +14 pp
Tokens: +12%
Agent turns: 0%
Response time: +8%

Model gemini-3.6-flashMeasured 9/1/2026v113 of 22 cases passed with skill · 20 comparable

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/vixues-document-processor/SKILL.md https://app.decimal.ai/s/vixues-document-processor/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add vixues-document-processor, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/vixues-document-processor/ and pins it in .decimal/skills.lock

decimalai skills add vixues-document-processor

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/vixues-document-processor/SKILL.md https://app.decimal.ai/s/vixues-document-processor/SKILL.md

Raw file: /s/vixues-document-processor/SKILL.md ↗ · machine-readable summary at /s/vixues-document-processor.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 3 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 3

Prompt

Extract all definitions of 'Force Majeure' from the 50-page Master_Service_Agreement.pdf. When extracting excerpts from large documents, standard LLMs quote text without location markers; include citations indicating where each excerpt appears.

What was checked, without and with the skill
Checked	Without skill	With skill
The output includes specific page references for each extracted definition.	Missed	Passed

case-07 · gemini-3.6-flash · 9/1/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md51 linessingle file

Document Processing

You are assisting with document processing tasks. Follow these guidelines.

Document Analysis Workflow

Identify the document type: PDF, DOCX, XLSX, TXT, Markdown, HTML.
Assess document structure: headers, sections, tables, images, metadata.
Extract relevant content based on the user's request.
Transform extracted content to the requested format.
Validate accuracy, structure, and completeness.

Common Operations

Text Extraction

Preserve document structure (headers, paragraphs, lists).
Keep formatting where semantically meaningful (bold terms, emphasis).
Extract metadata (author, creation date, document properties) when relevant.

Table Extraction

Identify table boundaries and column headers.
Preserve row/column relationships when exporting to CSV or JSON.
Handle merged cells, nested tables, and multi-page tables carefully.

Information Extraction

Extract specific fields (names, dates, amounts, addresses) with high precision.
Use structured output (JSON, YAML) when returning multiple fields.
Report confidence when extraction is ambiguous.

Format Conversion

PDF ↔ Text/Markdown
DOCX ↔ Markdown/HTML
XLSX ↔ CSV/JSON
HTML ↔ Markdown

Quality Guidelines

Track record

Benchmark

12 / 20

test cases passed, vs 9 / 20 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/10/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

vixues / leagent

backend/leagent/skills/builtin/document-processor/SKILL.md

View on GitHub ↗

License Apache-2.0Imported 8/10/2026Version v1

Other skills for the same job

Published skills whose descriptions closely match this one, with their headline benchmark lift.

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

Document Processing

Document Analysis Workflow

Common Operations

Text Extraction

Table Extraction

Information Extraction

Format Conversion

Quality Guidelines

Track record

Benchmark

Adoption

SkillSafety

Source

Other skills for the same job

Related skills