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

87%

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 excellent multi-language reference skill: fully executable examples, deep coverage of language-specific quirks, and a clean overview-plus-references structure with all bundle files present and one level deep. The only notable improvements are trimming the inline full-extension table (duplicated in supported-formats.md) and adding an explicit retry/verification loop for batch failures.

DimensionReasoningScore

Conciseness

The body is efficient and library-specific with no concept-explaining padding, but a few things could be trimmed: the inline Supported Formats table enumerates all ~140 extensions despite "references/supported-formats.md" holding the full reference, and pinned versions ("xberg-cli@1.3.10", "uvx --from xberg-cli==1.3.8") add time-sensitive detail. Not 3 because there is no unnecessary explanation of things Claude already knows; not 5 because of the duplicated extension list and version pins.

4 / 5

Actionability

Every section provides copy-paste-ready, complete examples across Python, Node.js, Rust, and CLI — imports, asyncio wrappers, error handling, and exact flag values ("--format json", "--content-format markdown") are all shown. Edge cases are documented concretely, e.g. "The single-string shorthand (\"eng+deu\") is only accepted in config files / --config-json, not in the OcrConfig constructor", fully covering the common cases per anchor 5.

5 / 5

Workflow Clarity

The skill's single action (build an ExtractInput, call extract, read the envelope) is unambiguous and reinforced by pitfall #1 and the result-fields table, and batch error checkpoints are explicit ("Per-input failures ... are reported non-fatally in result.errors" with inspection code in all three languages). It falls short of anchor 5 because no explicit fix-and-retry loop or output verification (e.g. checking for empty content) is given — error detection is shown but not remediation.

4 / 5

Progressive Disclosure

The SKILL.md is a clear overview with well-signaled, one-level-deep references: the Additional Resources section lists all 8 reference files with one-line descriptions, and every linked file (python-api.md, nodejs-api.md, rust-api.md, cli-reference.md, configuration.md, supported-formats.md, advanced-features.md, other-bindings.md) exists in references/. Content is appropriately split — quick-start and pitfalls inline, exhaustive API/config/format detail external — matching anchor 5.

5 / 5

Total

18

/

20

Passed

Description

83%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 comprehensive, concrete action coverage and clear distinctiveness from the named library. Its main weakness is the when-clause being phrased around calling Xberg APIs rather than natural user tasks, and the absence of file extensions or task synonyms among trigger terms.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — "Extract text, tables, metadata, and images" plus "batch processing", "configuration (OCR, chunking, output format)", and "plugins" — giving comprehensive coverage of the library's surface. Anchor 4 would require minor gaps in the action list, but the extraction targets and operational tasks are all enumerated specifically.

5 / 5

Completeness

Both parts are present: a clear "what" ("Extract text, tables, metadata, and images from 107 document formats ... using Xberg") and an explicit "Use when writing code that calls Xberg APIs in Python, Node.js/TypeScript, Rust, or CLI" clause. The when-clause is library-centric rather than user-task-oriented — a user asking to "extract text from a PDF" without naming Xberg is not directly covered — so it fits anchor 4 ("'when' could be more explicit or specific") rather than anchor 5's concrete user-mention triggers.

4 / 5

Trigger Term Quality

Good keyword coverage with natural format terms ("PDF, Office, images, HTML, email, archives") and task words ("OCR", "batch processing", "chunking"), but no file extensions (.pdf, .docx) or common synonyms like "document extraction" or "parse documents". Not 5 because the anchor-5 example includes extensions and synonyms; not 3 because coverage goes well beyond "some relevant keywords".

4 / 5

Distinctiveness Conflict Risk

The description is pinned to the named library Xberg with a specific niche (107 formats, four language surfaces), giving a clear distinct trigger surface with minimal conflict risk against generic document skills. It matches anchor 5 exactly; anchor 4 would require minor overlap risk with closely related skills, which the library naming eliminates.

5 / 5

Total

18

/

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/plugins/xberg/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.