liteparse

Local document and PDF parsing with spatial text and bounding boxes. Use for extracting text from PDFs, DOCX, Office files, and images; OCR on scans; layout-preserved JSON for RAG; batch-ingesting paper folders; or page screenshots for multimodal agents — even when the user does not name liteparse. Prefer over MarkItDown when you need bboxes, fast local parsing, or PNG page renders; prefer over the pdf skill for merge/split/forms.

Quality

93%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Quality

Content

87%

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

A well-structured, actionable skill body with executable examples and clean progressive disclosure to real reference files. The main gap is the absence of explicit validation/retry feedback loops for batch and conversion-failure workflows.

Suggestions

Add an explicit validate->fix->retry loop to the batch-parse workflow, e.g. check the parsed output / error log per file and re-run failed conversions after installing the missing dependency.

Expand the 'If conversion tools are missing, parsing fails' note into a small checkpoint: detect the missing tool, install it, then re-run rather than a single retry hint.

For the screenshot + JSON combined workflow, include a brief verification step confirming the screenshot page set matches the JSON page set before proceeding.

Dimension	Reasoning	Score
Conciseness	Lean and efficient — it assumes Claude's competence with no 'what is a PDF' filler, and sections like Quick Start and Core Workflows are tight; not score 2 because there is no unnecessary concept explanation despite the version-specific note.	3 / 3
Actionability	Fully executable Python and `lit` CLI examples throughout (e.g. `parser.parse("paper.pdf")`, `lit parse document.pdf --format json -o document.json`) that are copy-paste ready with concrete flags, matching the 'fully executable' anchor.	3 / 3
Workflow Clarity	Workflows are clearly numbered and sequenced, but the batch-parse workflow and the 'files are converted to PDF internally, then parsed... parsing fails' note lack an explicit validate/fix/retry feedback loop; per the rubric, missing validation in batch operations caps this at 2 rather than 3.	2 / 3
Progressive Disclosure	Clear overview body with a Reference Files table; all referenced files (choosing_a_parser, api_reference, cli_reference, output_formats, ocr_and_formats) plus scripts/batch_parse_dir.py are real and one level deep, matching the 'well-signaled one-level-deep references' anchor.	3 / 3
	Total	11 / 12 Passed

Description

100%

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, third-person description that names concrete capabilities, supplies natural trigger terms, explicitly states when to use the skill (including the user-not-naming-it case), and resolves conflicts with sibling skills. No meaningful weaknesses.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'extracting text from PDFs', 'OCR on scans', 'layout-preserved JSON for RAG', 'batch-ingesting paper folders', and 'page screenshots for multimodal agents' — matching the 'multiple specific concrete actions' anchor.	3 / 3
Completeness	Explicitly answers what ('Local document and PDF parsing with spatial text and bounding boxes') and when (an explicit 'Use for...' clause plus 'even when the user does not name liteparse'), matching the 'both what AND when with explicit triggers' anchor.	3 / 3
Trigger Term Quality	Strong coverage of natural user terms ('PDFs, DOCX, Office files, images, scans, RAG, page screenshots') that a user would plausibly say, fitting the 'good coverage of natural terms' anchor.	3 / 3
Distinctiveness Conflict Risk	Explicit disambiguation ('Prefer over MarkItDown...', 'prefer over the pdf skill for merge/split/forms') carves a clear niche, fitting the 'clear niche with distinct triggers' anchor; not score 2 because the overlap is actively resolved.	3 / 3
	Total	12 / 12 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: 757b63b

Reviewed: about 12 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.