CtrlK
BlogDocsLog inGet started
Tessl Logo

liteparse

Use this skill when the user asks to parse, perform multi-format document conversion or spatially extract text from an unstructured file (PDF, DOCX, PPTX, XLSX, images, etc.) locally without cloud dependencies.

66

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./backend/cli/skills/document-parsing/liteparse/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

76%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.

The body is highly actionable with executable CLI examples and clean reference tables, but workflow clarity is capped because batch operations lack validation/verification steps. Organization is good but everything is inlined in one file rather than split into references.

Suggestions

Add an explicit validation/verification step after batch-parse (e.g., check the output directory file count and spot-check a parsed result) to lift workflow clarity above the batch-operation cap of 3.

Fix the step-numbering gap (the body jumps from Step 1 to Step 3) so the sequence is coherent.

Move the HTTP OCR server API spec and the full config-file schema into a separate reference file, linking from the body, to improve progressive disclosure.

DimensionReasoningScore

Conciseness

The body is mostly lean command tables and executable examples with no concept-explaining fluff, though the "I'm ready" confirmation preamble and repeated install instructions add minor redundancy.

4 / 5

Actionability

Provides copy-paste-ready `lit` CLI commands across single-file, batch, and screenshot flows, plus concrete config JSON and an HTTP OCR API spec covering the common cases.

5 / 5

Workflow Clarity

Steps are listed but batch-parse is a batch operation with no validation/verification checkpoint, which the rubric caps at 3; the step numbering also skips Step 2.

3 / 5

Progressive Disclosure

Content is well-organized into clear sections within a single file with no nested references; absence of bundle files means structure alone suffices, though some reference material (OCR server API, config schema) could be split out.

4 / 5

Total

16

/

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 that clearly states capabilities and an explicit trigger condition with concrete file-format keywords. It is distinctive and well-targeted, with only minor coverage gaps in trigger synonyms and action enumeration.

DimensionReasoningScore

Specificity

Names the domain and several concrete actions ("parse", "perform multi-format document conversion", "spatially extract text") with minor gaps in coverage rather than a fully exhaustive action list.

4 / 5

Completeness

Explicitly answers both what ("parse, perform multi-format document conversion or spatially extract text") and when ("Use this skill when the user asks to...") with concrete trigger phrases.

5 / 5

Trigger Term Quality

Includes natural user phrases ("user asks to parse", "document conversion", "extract text") and many file extensions (PDF, DOCX, PPTX, XLSX, images), but a few common synonyms are missing.

4 / 5

Distinctiveness Conflict Risk

The local/no-cloud multi-format parsing niche has distinct triggers, with only minor overlap risk against generic single-format PDF or office 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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
synthetic-sciences/openscience
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.