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

The canonical home for this skill is xberg in xberg-io/xberg

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 exemplary API-overview skill: fully executable multi-language examples, a high-value pitfalls section, and clean progressive disclosure to real, one-level-deep reference files. The only friction points are stale-prone pinned versions and the absence of an explicit batch error-recovery loop.

Suggestions

Drop hard-pinned CLI versions (use @xberg-io/xberg-cli and xberg-cli unpinned, or move version pins to a changelog/reference) so the quick-install commands do not go stale.

Add a short retry/skip pattern for batch failures (e.g. collect result.errors indices, re-extract failed inputs with adjusted config) to close the feedback loop in the Batch Processing section.

DimensionReasoningScore

Conciseness

Nearly all content is executable code, tables, and pitfalls with zero explanation of concepts Claude already knows, but pinned version numbers ("npx @xberg-io/xberg-cli@1.3.10", "uvx --from xberg-cli==1.3.8", Cargo "version = \"1.1.0\"") are time-sensitive and the 100+ row extension table duplicates the supported-formats reference, keeping it below the lean 5 anchor.

4 / 5

Actionability

Copy-paste-ready, complete examples in Python, Node, Rust, and CLI spanning install, extraction, configuration (including TOML config files and --config-json), batch, and typed error handling, plus pitfalls with exact field names and signatures ("extract(input, &config) — the config is a reference"); specific examples cover the common cases.

5 / 5

Workflow Clarity

Sections are logically sequenced (Install → Quick Start → Configuration → Batch → OCR → Result fields → Error Handling → Pitfalls) and batch verification is explicitly shown (inspecting result.errors in Python and Node), but there is no validate→fix→retry feedback loop for failed batch inputs (recovery is deferred to a sibling skill), matching 4's "minor validation gaps" rather than 5's feedback loops.

4 / 5

Progressive Disclosure

The overview keeps key examples inline while eight well-labeled, one-level-deep references (e.g. "All functions, config classes, plugin protocols, exact signatures") hold the bulk detail; every referenced file exists in the bundle and no reference file chains onward to another, so navigation is easy and content is appropriately split.

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 capabilities, an explicit 'Use when' clause, third-person voice, and a clearly named tool. Its main weakness is a library-centric trigger that misses natural document-extraction phrasing and file extensions users would actually say.

Suggestions

Broaden the 'Use when' clause to include task-based triggers, e.g. "Use when the user mentions PDFs, document extraction, OCR, or parsing Office/HTML/email files, or when writing code that calls Xberg APIs".

Add a few file extensions or synonyms (e.g. ".pdf", ".docx", ".xlsx", "PDFs") to the format list so natural user phrasing matches the trigger terms.

Signal that task-specific siblings exist (OCR, tables, chunking, batch) so this umbrella skill is preferred for general/API usage rather than deep single-topic work.

DimensionReasoningScore

Specificity

"Extract text, tables, metadata, and images" plus "installation, extraction (sync/async), configuration (OCR, chunking, output format), batch processing, error handling, and plugins" lists multiple concrete actions covering the tool's full surface, matching the comprehensive-coverage anchor rather than the 4 anchor's "minor gaps".

5 / 5

Completeness

Both parts are present: what ("Extract text, tables, metadata, and images from 107 document formats") and when ("Use when writing code that calls Xberg APIs"), but the trigger is library-centric and would not fire on natural requests like "extract the text from this PDF", so it fits 4's "'when' could be more explicit or specific" rather than 5's concrete trigger phrases.

4 / 5

Trigger Term Quality

Good natural keyword coverage ("extract text", "PDF", "Office", "OCR", "tables", "batch", language names), but no file extensions (".pdf", ".docx") or synonyms ("PDFs"), falling short of the 5 anchor's "including synonyms and file extensions"; well above the 3 anchor's partial coverage.

4 / 5

Distinctiveness Conflict Risk

"using Xberg" and the explicit language list carve a clear niche with minimal conflict against unrelated skills, but the description claims OCR, chunking, and batch territory also covered by closely related Xberg sibling skills, matching 4's "minor overlap risk with 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/.hermes/package/src/xberg_hermes_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.