liteparse

Local document and PDF parsing that returns spatial text with bounding boxes. Use for extracting text from PDFs, DOCX, Office files, and images; running OCR on scans; producing layout-preserved JSON for RAG; batch-ingesting folders of papers; or rendering pages to PNG for multimodal agents. Distinguishing capabilities are per-token bounding boxes, page raster output, and fully local processing with no cloud API.

Quality

90%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

80%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 and well-structured with real reference files for progressive disclosure, but loses points on workflow clarity because batch and other operations omit validation/verification checkpoints, and carries minor conciseness cost from embedded version/date info.

Suggestions

Add an explicit validation/verification checkpoint to the batch-parse workflow (e.g., check a sample output JSON, report failed/empty parses, retry failures) so workflow_clarity can exceed the batch cap.

Move the "liteparse 2.0.0 (PyPI, May 2026)" version/date detail into a labeled compatibility or deprecation note to avoid the time-sensitive conciseness penalty.

Add a brief validate-then-proceed loop to at least one fragile workflow (e.g., verify JSON output parses and pages count matches input) to establish a feedback-loop pattern.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean and assumes competence, but the "Version note" pins a specific date/version ("liteparse 2.0.0 (PyPI, May 2026)") outside a deprecated section, which the guidelines penalize, and a few explanatory lines could be trimmed.	4 / 5
Actionability	Every workflow provides copy-paste-ready Python and CLI examples covering the common cases, matching the fully-executable anchor.	5 / 5
Workflow Clarity	Workflows are numbered and well-sequenced, but the batch-parse workflow (a batch operation) and others lack explicit validation/verification checkpoints, so workflow_clarity is capped at 3 per the batch-operation rule.	3 / 5
Progressive Disclosure	SKILL.md is a concise overview with a Reference Files table giving "Read when" guidance to real one-level-deep bundle files (api_reference, cli_reference, output_formats, ocr_and_formats, choosing_a_parser) plus the bundled script, with easy navigation.	5 / 5
	Total	17 / 20 Passed

Description

100%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.

The description is concrete, trigger-rich, and self-distinguishing, cleanly answering both what the skill does and when to use it. It avoids fluff and uses appropriate third-person voice.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "extracting text from PDFs, DOCX, Office files, and images; running OCR on scans; producing layout-preserved JSON for RAG; batch-ingesting folders of papers; or rendering pages to PNG" — with comprehensive coverage, matching the score-5 anchor.	5 / 5
Completeness	States what it does ("Local document and PDF parsing that returns spatial text with bounding boxes") and gives an explicit "Use for ..." when-clause with concrete trigger phrases, satisfying both requirements.	5 / 5
Trigger Term Quality	Covers natural user terms and synonyms across formats — "PDFs, DOCX, Office files, images, scans, OCR, RAG, papers, PNG, multimodal agents" — including file extensions, fitting the comprehensive-coverage anchor.	5 / 5
Distinctiveness Conflict Risk	Explicitly states "Distinguishing capabilities are per-token bounding boxes, page raster output, and fully local processing with no cloud API," carving a clear niche with minimal conflict risk.	5 / 5
	Total	20 / 20 Passed

Validation

100%

Warnings & errors only

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: K-Dense-AI/scientific-agent-skills
Path: skills/liteparse/SKILL.md
Commit: 1e5eeff

Reviewed: ~2 hours ago

Table of Contents

Discovery Implementation Validation

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.