CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

xberg

Extract text, tables, metadata, and images from 107 document formats (PDF, Office, images, HTML, email, archives, academic) using Xberg. Use when writing code that calls Xberg APIs in Python, Node.js/TypeScript, Rust, or CLI. Covers installation, extraction (sync/async), configuration (OCR, chunking, output format), batch processing, error handling, and plugins.

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

86%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

An excellent API-oriented skill body: executable multi-language examples throughout, a valuable pitfalls section, and clean one-level-deep progressive disclosure into real reference files. The only improvements are trimming the duplicated formats table and handling pinned version numbers, which will age.

DimensionReasoningScore

Conciseness

The body is code-first with no explanations of concepts Claude already knows — every section leads with executable examples and dense, useful tables. Minor trims are possible: the ~18-line Supported Formats summary table duplicates content already in references/supported-formats.md, and pinned version numbers ("@xberg-io/xberg-cli@1.3.10", "xberg-cli==1.3.8") are time-sensitive. This is efficient-with-minor-trimmable-instances, not the every-token-earns-its-place level.

4 / 5

Actionability

Fully executable, copy-paste-ready code for Python, Node.js, Rust, and CLI across installation, extraction, configuration, batch processing, OCR, and error handling. The per-language result-field table (content/mimeType/tables/chunks naming per binding) and the Common Pitfalls section cover the common cases and likely failure modes exactly as the top anchor requires.

5 / 5

Workflow Clarity

The body progresses logically from installation through quick start, configuration, batch, OCR, results, and error handling, and batch validation is present — per-input failures are surfaced in result.errors with an explicit inspection pattern in each language, so the batch-operation cap does not bind. It stops short of the top anchor's full feedback loops (e.g., no retry-with-adjusted-config guidance), fitting the clear-sequence-with-minor-gaps anchor.

4 / 5

Progressive Disclosure

The body is a genuine overview: all 8 referenced files (python-api.md, nodejs-api.md, rust-api.md, cli-reference.md, configuration.md, supported-formats.md, advanced-features.md, other-bindings.md) exist, contain substantive content, and are referenced with one-line descriptive summaries in a clear index. References are exactly one level deep — no reference file chains into another — and content is appropriately split between overview and detail.

5 / 5

Total

18

/

20

Passed

Description

80%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description with concrete, comprehensive capability statements and an explicit use-when clause. Its main weaknesses are the narrow tool-centric trigger (missing task-centric phrases like extracting from a PDF the user hands over) and the absence of file-extension synonyms in the trigger terms.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions — "Extract text, tables, metadata, and images" — plus batch processing, OCR, chunking, configuration, error handling, and plugins, matching the comprehensive-coverage anchor. It is not merely naming the domain; every clause describes a specific capability.

5 / 5

Completeness

Both parts are present: a clear "what" (extraction capabilities across 107 formats) and an explicit "Use when writing code that calls Xberg APIs in Python, Node.js/TypeScript, Rust, or CLI." However, the trigger is tool-centric — a user asking to extract tables from a PDF without knowing Xberg would not obviously match it — so the "when" could be broader and more task-specific, fitting the anchor-4 example.

4 / 5

Trigger Term Quality

Natural format keywords like "PDF, Office, images, HTML, email, archives" plus task verbs ("OCR", "batch") give good coverage, but no file extensions (.pdf, .docx) or common synonyms ("Word", "spreadsheets", "presentations") appear. This fits the good-coverage-with-a-few-missing-terms anchor rather than the comprehensive one.

4 / 5

Distinctiveness Conflict Risk

Tying the description to the named library ("using Xberg", "calls Xberg APIs") gives it a clear niche, but its broad scope (OCR, chunking, batch processing, plugins) overlaps with the specialized sibling skills it lists. Mostly distinct with minor overlap risk against closely related skills.

4 / 5

Total

17

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

xberg-io/xberg

Path

plugin/.cursor-plugin/skills/xberg/SKILL.md

Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.