CtrlK
BlogDocsLog inGet started
Tessl Logo

pdf

Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill.

92

1.31x
Quality

86%

Does it follow best practices?

Impact

95%

1.31x

Average score across 8 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

72%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 highly actionable with executable code for the common PDF tasks and stays lean, but it lacks validation checkpoints for its batch/destructive operations and its reference structure is broken — it points to nonexistent REFERENCE.md/FORMS.md files while leaving the provided scripts/ bundle orphaned.

Suggestions

Add explicit validation/verification steps after destructive or batch operations (e.g., verify the merged PDF has the expected page count, confirm decryption succeeded by re-opening) to lift workflow clarity above the destructive-operation cap of 3.

Resolve the broken references: either create the referenced REFERENCE.md and FORMS.md files or repoint the body to the existing scripts/ bundle (e.g., link the form-filling scripts from the form-filling section instead of the missing FORMS.md).

Reduce redundancy by collapsing the overlapping qpdf/pdftk/pdftotext merge/split/rotate entries and the Quick Reference table, or move the per-tool CLI detail into a single comparison table.

DimensionReasoningScore

Conciseness

The body is mostly lean executable code with minimal concept explanation and a genuinely useful non-obvious note on ReportLab subscript glyphs, but it carries mild redundancy — the Quick Reference table restates commands already shown, and qpdf/pdftk/pdftotext overlap on merge/split/rotate — so it sits above anchor 3 but short of the every-token-earns-its-place bar at 5.

4 / 5

Actionability

Code blocks are complete and copy-paste ready across the common cases — merge, split, rotate, text/table extraction, PDF creation, OCR, watermark, password protection, image extraction — with concrete CLI commands, matching the anchor-5 fully-executable example.

5 / 5

Workflow Clarity

Each task is self-contained with clear code, but destructive/batch operations (merge, split, encrypt/decrypt, OCR) lack any validation or verification checkpoints, which per the rubric caps this dimension at 3 even though individual snippets are unambiguous.

3 / 5

Progressive Disclosure

Sections are well organized and references are clearly signaled at one level deep ('see REFERENCE.md', 'read FORMS.md'), but those referenced files do not exist in the bundle while the actual scripts/ bundle (8 form-filling scripts) is never linked from the body — form-filling is pointed at a missing FORMS.md instead of the real scripts, a meaningful navigation gap that keeps this below anchor 4.

3 / 5

Total

15

/

20

Passed

Description

100%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.

A strong description that explicitly states a comprehensive set of concrete capabilities and pairs them with clear, natural-language trigger conditions including the .pdf extension. It reads as a model 'what + when' description with low conflict risk.

DimensionReasoningScore

Specificity

Lists many concrete actions — 'reading or extracting text/tables', 'combining or merging', 'splitting PDFs apart', 'rotating pages', 'adding watermarks', 'creating new PDFs', 'filling PDF forms', 'encrypting/decrypting', 'extracting images', and 'OCR on scanned PDFs' — giving comprehensive coverage rather than the 1-2 actions at anchor 3.

5 / 5

Completeness

Explicitly answers both what (the long action list) and when ('Use this skill whenever the user wants to do anything with PDF files... If the user mentions a .pdf file or asks to produce one, use this skill'), with concrete trigger phrases as required for anchor 5.

5 / 5

Trigger Term Quality

Covers natural terms and synonyms plus the file extension — 'PDF files', 'PDFs', 'PDF forms', and '.pdf file' — matching the anchor-5 example of comprehensive coverage including synonyms and extensions.

5 / 5

Distinctiveness Conflict Risk

Scoped to a clear niche (PDF files) with distinct, PDF-specific triggers and the .pdf extension, giving minimal overlap risk with other skills, matching the anchor-5 example.

5 / 5

Total

20

/

20

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
eigent-ai/eigent
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.