pdf-extraction-fallbacks

Multi-fallback PDF/text extraction with early failure detection and sequential tool fallbacks

Quality

68%

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-extraction-fallbacks/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 delivers highly executable, well-sequenced guidance with strong validation checkpoints and feedback loops, making it immediately actionable. Its weaknesses are mild verbosity in the prose sections and a monolithic structure that does not leverage separate reference files.

Suggestions

Trim conceptual prose such as the Purpose rationale and Best Practices that restate obvious guidance; keep only what Claude would not already infer.

Move the full 'Example Complete Workflow Script' and the per-method code blocks into separate files under references/ or scripts/ and link to them from SKILL.md to improve progressive disclosure.

Consolidate the duplicated size/threshold checks between Step 1 and the workflow script to reduce redundancy.

Dimension	Reasoning	Score
Conciseness	Mostly efficient code-first content, but includes padded explanatory prose (e.g., 'single-method approaches often fail due to JavaScript protection, CORS restrictions...') and restates obvious guidance ('Always validate - Never assume a download succeeded') that could be trimmed.	3 / 5
Actionability	Fully executable, copy-paste-ready bash and Python blocks with concrete thresholds, plus a complete end-to-end workflow script covering the common cases.	5 / 5
Workflow Clarity	Steps are clearly sequenced with explicit validation checkpoints (size check, %PDF magic-byte check, word/char-count success thresholds) and feedback loops that fall through to the next method on failure, reinforced by a decision tree.	5 / 5
Progressive Disclosure	Good section headers organize the content, but it is a single monolithic file with multiple full inlined code blocks (including a complete workflow script) that could be split into separate reference files; no bundle files are present.	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 conveys a concrete, specific capability niche but is missing an explicit 'Use when...' trigger clause and lacks the natural keyword variations and file extensions that improve discoverability. It is solid but not exemplary.

Suggestions

Add an explicit 'Use when...' trigger clause naming common user phrasings (e.g., 'Use when extracting text from PDFs that fail standard tools, or when downloads return error pages instead of PDFs').

Broaden trigger terms to include natural synonyms and extensions such as 'PDFs', '.pdf', and 'document extraction'.

Consider naming the specific tools surfaced as fallbacks (pdftotext, PyMuPDF, pdfplumber) to strengthen distinctiveness from generic PDF skills.

Dimension	Reasoning	Score
Specificity	Names the domain ('PDF/text extraction') and several concrete actions ('early failure detection', 'sequential tool fallbacks'), with only minor gaps in coverage versus a fully comprehensive action list.	4 / 5
Completeness	Clearly states what the skill does, but provides no 'Use when...' trigger clause or equivalent explicit guidance on when to invoke it, which caps completeness at 3 per the rubric.	3 / 5
Trigger Term Quality	Includes 'PDF' and 'text extraction' as relevant keywords, but omits common natural variations and file extensions users would say ('PDFs', '.pdf', 'forms', 'document extraction').	3 / 5
Distinctiveness Conflict Risk	The multi-fallback failure-detection niche is mostly distinct from general PDF skills, with only minor overlap risk against closely related PDF-extraction skills.	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-extraction-fallbacks/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.