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.

96

2.48x
Quality

90%

Does it follow best practices?

Impact

97%

2.48x

Average score across 10 eval scenarios

SecuritybySnyk

High

Do not use without reviewing

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

SKILL.md
Quality
Evals
Security

Quality

Content

80%

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 and token-efficient, packed with executable code and CLI examples with minimal filler. Its weaknesses are structural: no validation checkpoints around destructive/batch operations, and the body points to reference.md and forms.md files that are missing from the bundle while leaving the present scripts/ un-signaled.

Suggestions

Provide the missing reference.md and forms.md files (or remove/fix the dangling references) so the signaled navigation actually resolves.

Reference the existing scripts/ (e.g. fill_fillable_fields.py, extract_form_field_info.py) from the form-handling sections so the bundle is discoverable instead of orphaned.

Add explicit validation/verification steps for destructive or batch operations (e.g. verify a merged/split PDF opens and has the expected page count, or confirm encryption by attempting a decrypted read) to lift workflow clarity above 2.

DimensionReasoningScore

Conciseness

The body is lean code with almost no explanatory prose — it does not explain what a PDF is or recommend libraries at length, and assumes Claude's competence, matching the score-3 anchor; minor redundancy in the Quick Reference table keeps it from being maximally tight but it is clearly above score 2.

3 / 3

Actionability

Every section provides fully executable, copy-paste-ready Python and bash (pdftotext, qpdf, pdftk) rather than pseudocode or abstract description, matching the score-3 anchor.

3 / 3

Workflow Clarity

The recipes are individually unambiguous, but batch/destructive operations (merge, split, encrypt, OCR) include no validation or verify-then-proceed checkpoints, which the rubric caps at 2; it is above score 1 because steps are present and clear.

2 / 3

Progressive Disclosure

The body signals one-level-deep references to reference.md and forms.md and reads as an overview, but those referenced files do not exist in the bundle and the available scripts/ are never referenced, so navigation is broken/under-signaled — better than a monolithic wall (score 1) but short of the score-3 ideal of easy, working navigation.

2 / 3

Total

10

/

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, complete, and distinct: it names multiple concrete PDF actions and pairs them with an explicit 'Use when'-style trigger clause, covering both what the skill does and when Claude should reach for it.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'extracting text and tables', 'creating new PDFs', 'merging/splitting documents', and 'handling forms' — matching the score-3 anchor for multiple specific concrete actions, well above naming only a domain and some actions.

3 / 3

Completeness

Explicitly answers both what (the toolkit capabilities) and when via the explicit trigger '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

Covers natural terms users would say — 'PDF', 'PDF form', 'PDF documents', 'tables', 'forms', 'documents' — giving broad coverage rather than just some relevant keywords with missing variations.

3 / 3

Distinctiveness Conflict Risk

A clear PDF-manipulation niche with distinct triggers ('PDF form', 'fill', 'process/generate/analyze ... at scale') makes it unlikely to fire for the wrong skill, matching the score-3 anchor.

3 / 3

Total

12

/

12

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
ThinkInAIXYZ/deepchat
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.