pdf-extract-progressive-tools

Progressive tool-chain PDF extraction with explicit read_file, run_shell, and execute_code_sandbox sequencing

Quality

68%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Medium

Suggest reviewing before use

Fix and improve this skill with Tessl

tessl review fix ./benchmarks/gdpval/skills/pdf-download-extract-fallback-enhanced-899f5b/SKILL.md

Quality

Content

77%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 an explicit, well-validated workflow, but it is padded by repeated restatements of the same three-step pattern and inlines content (the orchestrator script, decision tree) that would be cleaner as a separate reference. Trimming redundancy and splitting out the script would lift both conciseness and progressive disclosure.

Suggestions

Consolidate the duplicated three-step progression: keep the step-by-step instructions and failure-mode table, and trim the redundant 'Best Practices' and 'Migration from Parent Skill' sections.

Move the full pdf-extract-orchestrator.py script and the ASCII decision tree into a referenced file (e.g. references/orchestrator.py) so the SKILL.md overview stays lean.

Cut generalities like 'regulatory/compliance documents' and 'document limitations clearly' that restate what the workflow already prescribes.

Dimension	Reasoning	Score
Conciseness	The step-by-step instructions are efficient, but the same three-step progression is re-stated across the orchestrator script, ASCII decision tree, best practices, failure-mode table, and migration section, adding substantial redundancy.	3 / 5
Actionability	Provides fully executable, copy-paste-ready commands and Python (including the poppler-utils install fallback and PyMuPDF script) that cover the common extraction cases.	5 / 5
Workflow Clarity	A clear five-step sequence with explicit binary/text/error checkpoints, a feedback loop into Step 4 quality verification, an entry-point scenario table, and a failure-mode table for error recovery.	5 / 5
Progressive Disclosure	No bundle files exist and the skill is a single monolithic document; the full orchestrator script and decision tree are inlined where a separate reference file would reduce the overview's bulk.	3 / 5
	Total	16 / 20 Passed

Description

58%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 specific and distinct but reads as an internal implementation summary rather than a user-facing trigger: it names the tool sequence but omits a 'Use when' clause and natural synonyms. It would benefit from explicit trigger guidance and more user-natural terms.

Suggestions

Add an explicit 'Use when...' clause naming user-facing triggers, e.g. 'Use when extracting text from PDF files, especially when read_file returns binary data.'

Include natural synonyms and the file extension (PDFs, document extraction, .pdf) so it matches how users phrase the request.

Lead with the user-facing action ('Extracts text from PDF documents') before the internal tool-chain detail.

Dimension	Reasoning	Score
Specificity	Names the PDF-extraction domain and the three concrete tools (read_file, run_shell, execute_code_sandbox) in sequence, but lists tool names rather than the full set of user-facing actions like tables, forms, or merging.	4 / 5
Completeness	Gives a clear 'what' (progressive tool-chain PDF extraction) but provides no 'Use when...' trigger clause, which caps completeness at 3 per the judging guidelines.	3 / 5
Trigger Term Quality	Includes 'PDF' and 'extraction' but is dominated by tool-chain jargon users would not naturally say, and omits synonyms (PDFs, forms, document extraction) and the .pdf extension.	3 / 5
Distinctiveness Conflict Risk	Targets a fairly distinct niche (progressive tool sequencing for PDF extraction) with low overlap risk, though the jargon-heavy framing keeps its triggers from being maximally clean.	4 / 5
	Total	14 / 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-download-extract-fallback-enhanced-899f5b/SKILL.md
Commit: 3827781

Reviewed: 10 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.