pdf-processor

Process PDFs - extract text, tables, and structured data from documents

Quality

57%

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 ./skills/research-tools/capabilities/pdf-processor/SKILL.md

Quality

Content

61%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 well-organized and mostly lean, but its curl examples contain broken JSON payloads (malformed -d bodies and stray quotes) that undermine executability, and it lacks validation checkpoints for batch extraction. Fixing the code blocks and adding verification steps would substantially raise quality.

Suggestions

Fix the malformed curl JSON payloads in Steps 2-3 and the Example Usage section: the -d bodies are split across lines with misplaced quotes, producing invalid commands.

Add validation/verification checkpoints (e.g. check the response status, verify extracted tables against the source) to lift workflow_clarity above the destructive/batch cap of 3.

Move the endpoint-discovery and parameter-detail content into a separate reference file to push progressive_disclosure toward 5.

Dimension	Reasoning	Score
Conciseness	The body is largely code-driven and avoids explaining concepts Claude already knows, with only minor redundancies (e.g. restating 'extract text, tables...' after Setup), placing it just above the efficient anchor.	4 / 5
Actionability	Commands are present but several curl examples are malformed (broken JSON payloads, misplaced quotes after -d), so the guidance is only partly executable, matching 'some concrete guidance but incomplete'.	3 / 5
Workflow Clarity	Steps are numbered but there are no validation/verification checkpoints for batch extraction operations; per the rubric this caps workflow_clarity at 3 despite the clear sequence.	3 / 5
Progressive Disclosure	Content is well-sectioned (Setup, Workflow steps, Examples, Tips, Discover More) and stays one level deep with no bundle files, sitting just below a 5 because some endpoint detail could be offloaded to references.	4 / 5
	Total	14 / 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 states a clear capability niche (PDF text/table/structured-data extraction) but lacks an explicit 'Use when...' trigger clause and omits file-extension synonyms, capping completeness and trigger quality. It is distinct enough from generic skills but would benefit from explicit invocation guidance.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when the user mentions PDFs, .pdf files, or needs to extract text, tables, or structured data from documents.'

Include the .pdf file extension and synonyms (e.g. 'PDF files, PDFs') to improve trigger-term coverage.

Optionally list more concrete actions (e.g. 'convert to markdown', 'fetch PDF URLs') to raise specificity toward comprehensive coverage.

Dimension	Reasoning	Score
Specificity	Names the domain (PDFs) and 2 concrete actions ('extract text, tables, and structured data') but no further coverage, matching the anchor for domain plus 1-2 actions.	3 / 5
Completeness	Has a clear 'what' but no 'Use when...' trigger clause; per guidelines a missing explicit trigger caps completeness at 3.	3 / 5
Trigger Term Quality	Includes 'PDFs' and 'documents' but omits common variations and the .pdf file extension, fitting 'some relevant keywords but missing common variations or synonyms'.	3 / 5
Distinctiveness Conflict Risk	The PDF-specific niche is fairly distinct with only minor overlap risk against generic document skills, sitting above the 'somewhat specific' anchor but below a fully explicit trigger-rich example.	4 / 5
	Total	13 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: gooseworks-ai/goose-skills
Path: skills/research-tools/capabilities/pdf-processor/SKILL.md
Commit: 2523432

Reviewed: 7 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.