CtrlK
BlogDocsLog inGet started
Tessl Logo

pdf

Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.

65

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./SKILLs/pdf/SKILL.md

The canonical home for this skill is pdf in anthropics/skills

SKILL.md
Quality
Evals
Security

Quality

Content

57%

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 with executable code throughout, but it suffers from broken progressive disclosure (reference.md and forms.md are referenced but absent) and lacks validation checkpoints for destructive/batch operations. It also carries some redundancy between the Overview, Quick Reference, and Next Steps sections.

Suggestions

Add the missing reference.md and forms.md files (or repoint the references to the actual scripts/*.py bundle), since the body repeatedly directs readers to files that do not exist.

Insert explicit validation/verification steps for destructive and batch operations — e.g. after merge/split/encrypt, verify page count or open the output with PdfReader before declaring success.

Trim redundancy: collapse the 'Next Steps' list and the Quick Reference table into the Overview so the same pointers and tool choices are not stated three times.

DimensionReasoningScore

Conciseness

The body is mostly efficient executable snippets, but it repeats import blocks per example, includes a duplicated 'Next Steps' list that restates the Overview, and the Quick Reference table largely re-surfaces code already shown — it could be tightened without losing clarity. It is not a score-1 wall of conceptual explanation, but also not the lean score-3 ideal.

2 / 3

Actionability

Nearly every section provides complete, copy-paste-ready Python and shell commands (e.g. the merge/split/rotate pypdf blocks, qpdf, pdftotext, OCR), matching the score-3 anchor of fully executable, specific examples.

3 / 3

Workflow Clarity

Operations are organized as discrete named tasks but lack explicit validation checkpoints for batch or destructive operations (e.g. merging/splitting/encrypting have no 'verify the output' step), which the rubric caps at 2 for missing feedback loops. The single-action tasks are unambiguous, but no validation is mentioned anywhere.

2 / 3

Progressive Disclosure

The body repeatedly points to 'reference.md' and 'forms.md' ('see reference.md', 'read forms.md and follow its instructions', Quick Reference and Next Steps), but no such files exist in the bundle — only scripts/*.py are present, and those scripts are documented as 'See forms.md' yet forms.md is missing. This is a broken/missing reference path with no navigation to the actual scripts, matching the score-1 anchor of poor organization and missing actual content.

1 / 3

Total

8

/

12

Passed

Description

100%

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, trigger-rich, and clearly answers both what the skill does and when to use it, with low conflict risk against other skills. It is one of the strongest reference examples in the rubric.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions — 'extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms' — matching the score-3 anchor of multiple specific concrete actions.

3 / 3

Completeness

It answers both 'what' (extract/create/merge/split/forms) and 'when' via the explicit trigger clause 'When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale,' matching the score-3 anchor.

3 / 3

Trigger Term Quality

It includes natural terms a user would say ('PDF form', 'PDF documents', 'fill a PDF form') and broad coverage of phrasings; below 3 would require missing common variations, but 'process, generate, or analyze PDF documents at scale' covers the common verbs.

3 / 3

Distinctiveness Conflict Risk

The PDF-specific scope and concrete triggers ('fill in a PDF form', 'PDF documents at scale') carve a clear niche unlikely to fire for unrelated skills, matching the score-3 anchor.

3 / 3

Total

12

/

12

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
netease-youdao/LobsterAI
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.