CtrlK
BlogDocsLog inGet started
Tessl Logo

extraction-pipeline-patterns

Document extraction pipeline architecture and patterns

47

Quality

50%

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

Fix and improve this skill with Tessl

tessl review fix ./.ai-rulez/skills/extraction-pipeline-patterns/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

50%

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

The content is well-structured and information-rich with real paths and patterns, but it relies on pseudocode rather than executable examples, lacks explicit validation feedback loops, and keeps heavy tabular detail inline with no reference files. Replacing pseudocode with real code and splitting the format/feature tables into reference files would raise the weaker dimensions.

Suggestions

Replace the pseudocode blocks with executable Rust snippets (or explicitly justify why pseudocode is preferred) to improve actionability.

Add an explicit validate-and-retry checkpoint (e.g., verify extracted text meets minimum length before post-processing) to lift workflow clarity.

Move the 75-format table and feature-flag matrix into reference files under references/ and link to them, improving progressive disclosure.

DimensionReasoningScore

Conciseness

The body is dense and assumes Claude's competence with no basic-concept padding, but the ~120 lines of broad format/feature tables and illustrative pseudocode could be tightened further rather than every token earning its place.

2 / 3

Actionability

Concrete file paths and real function names are given throughout, but the code blocks are explicitly pseudocode ('Pseudocode: core/mime.rs') rather than executable code, with no justification for the flexibility.

2 / 3

Workflow Clarity

The 4-stage pipeline sequence and dispatcher ordering are clear with mandatory-step emphasis, but there are no explicit validation checkpoints or validate-fix-retry feedback loops for batch/large-file operations, capping the score at 2.

2 / 3

Progressive Disclosure

Sections are well-organized with headers and a one-level 'Related Skills' pointer, but no bundle files exist to offload the heavy 75-format and feature-flag tables, leaving detail inline that could be split into references.

2 / 3

Total

8

/

12

Passed

Description

50%

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 identifies a clear domain but reads as an internal architecture summary rather than user-facing trigger guidance; it lacks a 'Use when...' clause and concrete action verbs. Adding natural trigger terms and explicit usage conditions would lift all dimensions.

Suggestions

Add a 'Use when...' clause naming concrete triggers (e.g., when extracting text from PDF, DOCX, Excel, HTML, images, or archives).

Replace abstract nouns ('architecture and patterns') with concrete actions ('extract, route, and apply fallbacks for 75+ file formats').

Include natural user terms and format names (PDF, DOCX, .xlsx, OCR) to improve trigger-term coverage and distinctiveness.

DimensionReasoningScore

Specificity

Names a concrete domain ('Document extraction pipeline') but uses abstract nouns ('architecture and patterns') with no action verbs, sitting between the vague score-1 and the verb-rich score-3 anchors.

2 / 3

Completeness

The 'what' is stated but there is no 'Use when...' or equivalent trigger guidance, which per the rubric caps completeness at 2.

2 / 3

Trigger Term Quality

'Document extraction' is a natural user term, but 'pipeline architecture and patterns' is internal jargon and common format variations (PDF, DOCX, etc.) are absent.

2 / 3

Distinctiveness Conflict Risk

The extraction-pipeline niche is defined but 'document extraction' could overlap with generic document skills, and no distinct triggers differentiate it.

2 / 3

Total

8

/

12

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
xberg-io/xberg
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.