CtrlK
BlogDocsLog inGet started
Tessl Logo

extract-from-pdfs

This skill should be used when extracting structured data from scientific PDFs for systematic reviews, meta-analyses, or database creation. Use when working with collections of research papers that need to be converted into analyzable datasets with validation metrics.

Install with Tessl CLI

npx tessl i github:brunoasm/my_claude_skills --skill extract-from-pdfs
What are skills?

Overall
score

96%

Does it follow best practices?

Validation for skill structure

SKILL.md
Review
Evals

Discovery

89%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This is a well-structured description with strong trigger terms and clear use-case guidance for academic research contexts. The main weakness is the lack of specific concrete actions - it describes the general purpose well but doesn't enumerate the specific extraction capabilities (e.g., extracting tables, figures, methodology, sample sizes, statistical results).

Suggestions

Add specific concrete actions like 'extract study characteristics, sample sizes, statistical results, and methodology details from research papers'

Consider adding file format triggers like '.pdf' or mentioning common research paper sources

DimensionReasoningScore

Specificity

Names the domain (scientific PDFs, systematic reviews) and mentions some actions (extracting structured data, converting to datasets), but lacks specific concrete actions like 'extract tables', 'parse citations', or 'identify methodology sections'.

2 / 3

Completeness

Explicitly answers both what ('extracting structured data from scientific PDFs', 'converted into analyzable datasets with validation metrics') and when ('systematic reviews, meta-analyses, or database creation', 'collections of research papers').

3 / 3

Trigger Term Quality

Good coverage of natural terms users would say: 'scientific PDFs', 'systematic reviews', 'meta-analyses', 'research papers', 'database creation', 'datasets', 'validation metrics' - these are terms researchers would naturally use.

3 / 3

Distinctiveness Conflict Risk

Clear niche targeting scientific/research PDF extraction specifically for systematic reviews and meta-analyses - distinct from general PDF processing skills through its academic research focus and mention of validation metrics.

3 / 3

Total

11

/

12

Passed

Implementation

100%

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

This is an excellent skill file that demonstrates best practices across all dimensions. It provides a complete, executable pipeline with clear validation checkpoints, appropriate progressive disclosure to reference materials, and efficient use of tokens without unnecessary explanations. The iterative improvement section and quality assurance guidance show thoughtful workflow design for complex multi-step operations.

DimensionReasoningScore

Conciseness

The content is lean and efficient, avoiding explanations of concepts Claude already knows. Every section serves a clear purpose with no padding or unnecessary context about what PDFs are or how libraries work.

3 / 3

Actionability

Provides fully executable bash commands for each pipeline step with specific flags and arguments. The complete 6-step workflow plus validation steps are copy-paste ready with concrete file paths and options.

3 / 3

Workflow Clarity

Excellent multi-step workflow with clear sequencing (Steps 1-9), explicit validation checkpoints (Steps 7-9 for quality metrics), and an iterative improvement loop. The validation workflow provides feedback mechanisms for error recovery.

3 / 3

Progressive Disclosure

Well-structured overview with clear navigation to detailed documentation via `cat references/*.md` commands. Content is appropriately split between the main skill file and reference guides, with one-level-deep references clearly signaled.

3 / 3

Total

12

/

12

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata' field is not a dictionary

Warning

license_field

'license' field is missing

Warning

Total

14

/

16

Passed

Reviewed

Table of Contents

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.