CtrlK
BlogDocsLog inGet started
Tessl Logo

pdf-text-extraction-fallback-85d5ca

Fallback workflow for extracting text from PDFs when read_file returns binary data

57

Quality

65%

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 ./benchmarks/gdpval/skills/pdf-text-extraction-fallback-85d5ca/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

67%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 content is a well-structured, actionable fallback workflow with explicit validation and error-recovery steps. Its main weaknesses are redundancy between the step list and the Code Example and the absence of a re-validation step after fallback retries.

Suggestions

Collapse the 'When to Use' list and the Code Example into the step flow to remove duplication and tighten conciseness.

After a pdfplumber/OCR fallback in Step 4, explicitly re-run the Step 3 validation before proceeding, closing the workflow_clarity gap.

Replace <filename.pdf> placeholders with a concrete example filename (as already used for Move_Out_Inspection_Tracker.pdf) and clarify the shell_agent return shape so the code is fully copy-paste ready.

DimensionReasoningScore

Conciseness

The body is mostly efficient but carries clear redundancy: the 'When to Use' section restates the frontmatter description, and the 'Code Example' section re-derives the same five steps already given as numbered instructions, so it could be tightened.

3 / 5

Actionability

Concrete shell_agent task strings and an executable Python validation function give mostly copy-paste-ready guidance; it stays at 4 rather than 5 because of filename placeholders (<filename.pdf>) and an assumed shell_agent/read_file API surface with minor gaps.

4 / 5

Workflow Clarity

The five steps are clearly sequenced with an explicit validation checkpoint (Step 3) and an error-recovery feedback loop (Step 4 listing pdfplumber then OCR), but it never re-validates after a fallback retry, the minor gap that keeps it below 5.

4 / 5

Progressive Disclosure

The ~135-line single-file skill is well organized with clear section headers (When to Use, Steps, Code Example, Tips) and no nested or buried references; it is not 5 because, beyond the under-50-line exception, no content is split out and the inlined Code Example/Tips could be separated.

4 / 5

Total

15

/

20

Passed

Description

62%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 concise and explicitly pairs a what with a specific when-trigger, giving it solid completeness and distinctiveness. Its weaknesses are limited action coverage and missing natural keyword variations, which keep specificity and trigger_term_quality at the midpoint.

Suggestions

Broaden the action list beyond a single verb, e.g. 'Extract text and tables from PDFs, try pdftotext then OCR fallback' to lift specificity.

Add natural trigger synonyms users would say, such as 'PDF files', '.pdf', or 'garbled/unreadable PDF content', to improve trigger_term_quality.

Expand the when clause to cover the failure modes the body actually addresses (binary data, garbled content, or errors) rather than only 'binary data'.

DimensionReasoningScore

Specificity

Names the domain and one concrete action ("extracting text from PDFs") plus a specific trigger condition, but does not list several distinct capabilities — matching the '1-2 concrete actions, not comprehensive' anchor rather than 4's 'several specific actions'.

3 / 5

Completeness

It explicitly answers both what ("Fallback workflow for extracting text from PDFs") and when ("when read_file returns binary data"), satisfying the anchor for 4; not 5 because the when covers only one narrow trigger condition without the broader concrete trigger phrases.

4 / 5

Trigger Term Quality

It contains relevant keywords ("PDFs", "extracting text") but misses common variations/synonyms (PDF files, .pdf, document, forms), and "read_file returns binary data" reads as technical API jargon rather than natural user phrasing.

3 / 5

Distinctiveness Conflict Risk

The PDF-specific, condition-specific trigger (read_file returning binary data) carves a clear niche with minimal conflict risk, but it still overlaps slightly with general PDF text-extraction skills, so it is mostly distinct rather than fully.

4 / 5

Total

14

/

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
HKUDS/OpenSpace
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.