extracting-with-ocr

Use when extracting text from scanned PDFs, photographed pages, or images that have no embedded text layer. Covers OCR backends, language packs, force-OCR, and performance tuning.

Quality

85%

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

82%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.

A well-structured, highly actionable single-purpose skill with dense executable examples and a useful failure-mode recovery section. The main gaps are minor conciseness redundancy and the lack of an explicit validation checkpoint for batch OCR.

Suggestions

Trim the opening paragraph and the 'Useful flags' list where they duplicate the frontmatter and the backends table to tighten conciseness.

Add a brief validation step for batch OCR (e.g. verifying output is non-empty per file before declaring success) to satisfy the batch-operation feedback-loop expectation.

Either move the full flag reference into a local `references/cli-reference.md` in this skill's bundle or drop the reference to the sibling skill's files so navigation targets actually resolve.

Dimension	Reasoning	Score
Conciseness	The body is lean, assumes Claude knows what OCR/PDFs are, and leads with executable commands, but the opening paragraph repeats the frontmatter trigger and the 'Useful flags' section re-lists flags already shown in the backends table, so it is not maximally tight.	4 / 5
Actionability	Copy-paste-ready commands throughout — `xberg extract scan.pdf --force-ocr=true`, `--ocr-language "eng+deu"`, brew/apt install lines, a complete xberg.toml block — cover the common cases (force-OCR, languages, backends, batch, performance) with fully executable guidance.	5 / 5
Workflow Clarity	Decision criteria ('When to force OCR'), a backend selection sequence ('Pick Tesseract first. Switch only when accuracy is unacceptable'), and an error-recovery 'Common failure modes' section provide clear sequencing with feedback loops, but there is no explicit validation checkpoint for the batch operation, leaving a minor gap.	4 / 5
Progressive Disclosure	Content is well-organized into clearly headed sections with no nested references, but the referenced `references/cli-reference.md` and `references/configuration.md` live in a sibling skill rather than this skill's own (absent) bundle, and the inlined flag list is borderline material that could be split out.	4 / 5
	Total	17 / 20 Passed

Description

87%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, third-person description that pairs an explicit 'Use when' trigger with concrete capability coverage and a well-scoped niche. Its only weakness is that the underlying action is essentially one (extract text) rather than multiple distinct operations, and it omits file-extension triggers.

Dimension	Reasoning	Score
Specificity	Lists the concrete action 'extracting text from scanned PDFs, photographed pages, or images' plus specific coverage areas ('OCR backends, language packs, force-OCR, and performance tuning'), but the core action is singular so it stops short of the multi-action comprehensiveness of a 5.	4 / 5
Completeness	Explicitly answers 'when' via 'Use when extracting text from scanned PDFs, photographed pages, or images that have no embedded text layer' and 'what' via 'Covers OCR backends, language packs, force-OCR, and performance tuning' with concrete trigger phrases.	5 / 5
Trigger Term Quality	Natural terms like 'scanned PDFs', 'photographed pages', 'images', and 'OCR' give good keyword coverage with synonyms, but file extensions (e.g. .jpg, .png, .pdf) are absent, leaving it just below the comprehensive 5 anchor.	4 / 5
Distinctiveness Conflict Risk	The narrow OCR-on-image-based-documents niche with distinct triggers (scanned PDFs, photographed pages, no embedded text layer) gives it a clear niche with minimal conflict risk against other skills.	5 / 5
	Total	18 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
referenced_paths_exist	Referenced path issues: 2 missing	Warning

	Total	15 / 16 Passed

Repository: xberg-io/xberg
Path: plugin/.ai-rulez/skills/extracting-with-ocr/SKILL.md
Commit: 92b4f95

Reviewed: 5 days 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.