pdf-text-extraction-9424c5

Extract text from PDF files using pdftotext when read_file returns binary data

Quality

64%

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

Fix and improve this skill with Tessl

tessl review fix ./benchmarks/gdpval/skills/pdf-text-extraction-9424c5/SKILL.md

Quality

Content

75%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 with executable code and clear validation checkpoints, organized into clean sections that need no external references. Its main weakness is mild verbosity in the Problem section and an off-topic parameter-naming tangent.

Suggestions

Tighten the Problem section to one sentence and remove the read_file failure explanation that Claude can infer.

Drop or relocate the parameter-naming subsection (filetype vs file_type); it is tangential to pdftotext extraction and adds noise.

Fold the validate-fix-retry feedback loop into the main step sequence so the recovery path is visible in the primary workflow, not just the error-handling helper.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with direct code examples, but the Problem section restates why read_file fails and the parameter-naming subsection is a tangent that could be trimmed.	3 / 5
Actionability	Provides copy-paste-ready, executable pdftotext invocations covering stdout and file output, an options table, and a complete error-handling function that handles the common cases.	5 / 5
Workflow Clarity	A clear numbered sequence pairs with explicit checkpoints (file-exists check, returncode check, `which pdftotext` availability probe), though the validate-fix-retry loop lives only in the error-handling snippet rather than the main flow.	4 / 5
Progressive Disclosure	A single well-organized SKILL.md with clearly labeled sections and no external bundle files needs no references, but at ~100 lines it is slightly more than minimal, so it sits just below the lean single-file ceiling.	4 / 5
	Total	16 / 20 Passed

Description

53%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 clearly states a single concrete capability and tool but lacks natural trigger phrasing and a user-facing "Use when" clause, leaving it mid-range on completeness and trigger quality. It is reasonably distinct from other skills despite the thin keyword coverage.

Suggestions

Add a user-facing trigger clause, e.g. "Use when the user asks to extract or read text from a PDF, or when read_file returns binary/garbled PDF content."

Include natural synonyms and the file extension, e.g. "PDF files, PDFs, .pdf documents".

Optionally broaden the listed actions (e.g. "extract text and preserve layout") to lift specificity toward comprehensive coverage.

Dimension	Reasoning	Score
Specificity	Names the PDF domain and one concrete action ("Extract text") with a specific tool (pdftotext), but offers no broader coverage of PDF capabilities, matching the anchor for domain plus 1-2 concrete actions.	3 / 5
Completeness	The "what" is clear (extract text via pdftotext) but the "when" clause ("when read_file returns binary data") is a technical edge-case trigger rather than explicit user-facing "Use when..." guidance, so it stays at the cap of 3.	3 / 5
Trigger Term Quality	Includes "PDF files" but lacks common variations like "PDFs" or ".pdf", and the "read_file returns binary data" phrase is a technical failure condition rather than natural user vocabulary.	3 / 5
Distinctiveness Conflict Risk	The pdftotext-specific extraction niche with a distinct failure-condition trigger is mostly distinct from sibling skills, with only minor overlap risk with other PDF-handling skills.	4 / 5
	Total	13 / 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: HKUDS/OpenSpace
Path: benchmarks/gdpval/skills/pdf-text-extraction-9424c5/SKILL.md
Commit: 3827781

Reviewed: 15 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.