pdf-extract-shell-first

PDF text extraction with tool cascade prioritizing shell pdftotext before Python fallback

Quality

67%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./benchmarks/gdpval/skills/pdf-download-extract-fallback-enhanced-e27e0c/SKILL.md

Quality

Content

77%

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

The content is highly actionable and clearly sequenced with strong validation and fallback loops, making it easy for Claude to execute the cascade. Its main weaknesses are verbosity from triple-representing the same workflow and the absence of any progressive disclosure into separate reference files.

Suggestions

Collapse redundancy by keeping one canonical representation of the cascade (e.g. the stepped workflow) and trimming or short-referencing the ASCII decision tree and full bash script, which repeat the same logic.

Move the complete automated bash script and the failure-mode reference table into separate bundle files (e.g. scripts/pdf-extract-cascade.sh and references/failure-modes.md) referenced one level deep from SKILL.md, improving both conciseness and progressive_disclosure.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and free of basic-concept padding, but the same cascade is rendered three times (Steps 0-4 prose, an ASCII decision tree, and a complete bash script), which is redundancy that could be tightened — matching anchor 2 rather than the lean anchor 3.	2 / 3
Actionability	Provides concrete, copy-paste-ready commands and code (curl with user-agent, pdftotext, apt-get/brew install, PyMuPDF snippet, full bash script), matching anchor 3 for fully executable guidance.	3 / 3
Workflow Clarity	Steps 0-4 are clearly sequenced with per-step evaluation tables and explicit feedback loops (binary response -> Step 2, pdftotext missing -> install, garbled output -> Step 3, total failure -> documented degradation), matching anchor 3.	3 / 3
Progressive Disclosure	The skill is a monolithic ~300-line SKILL.md with no bundle files and everything inline; though internally well-sectioned, the full automated script and decision tree are content that could be split out, matching anchor 2 rather than the multi-file anchor 3.	2 / 3
	Total	10 / 12 Passed

Description

57%

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 conveys a specific, distinctive niche (shell-first PDF extraction cascade) but reads as a single capability statement rather than a trigger-rich description. Its main weakness is the absence of an explicit 'Use when...' clause, which caps completeness and limits natural triggering.

Suggestions

Add an explicit 'Use when...' clause naming natural triggers, e.g. 'Use when extracting text from PDF files or URLs, especially when read_file returns binary data or pdftotext reliability matters'.

Broaden trigger terms to include user-natural phrasing like 'PDFs', '.pdf files', and 'extract text from PDF' alongside the existing 'pdftotext' jargon.

Expand the action list beyond a single extraction step if the skill genuinely supports distinct actions (e.g. downloading PDFs from URLs, handling scanned/encrypted PDFs) to lift specificity to anchor 3.

Dimension	Reasoning	Score
Specificity	Names the domain ('PDF text extraction') and a concrete method ('tool cascade prioritizing shell pdftotext before Python fallback'), but describes a single extraction action with a sequencing strategy rather than multiple distinct capabilities, matching anchor 2.	2 / 3
Completeness	Clearly states what the skill does but has no 'Use when...' clause or equivalent explicit trigger guidance, which per the judging guidelines caps completeness at 2 rather than 3.	2 / 3
Trigger Term Quality	Includes relevant keywords ('PDF', 'pdftotext', 'text extraction') but misses common natural variations users would say ('PDFs', '.pdf', 'extract text from PDF'); not the level-3 broad coverage nor the level-1 jargon-only case.	2 / 3
Distinctiveness Conflict Risk	The shell-first cascade niche ('prioritizing shell pdftotext before Python fallback') is clearly distinguishable from generic PDF skills and unlikely to trigger for the wrong skill, matching anchor 3; not level 2 because it is not merely 'works with document files'.	3 / 3
	Total	9 / 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: HKUDS/OpenSpace
Path: benchmarks/gdpval/skills/pdf-download-extract-fallback-enhanced-e27e0c/SKILL.md
Commit: c5a9c4b

Reviewed: 2 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.