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.

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

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.

A highly actionable, mostly lean reference of executable PDF snippets, but it lacks validation/feedback loops for its batch and destructive operations and its progressive disclosure is broken: the referenced reference.md and forms.md files are absent while the real ./scripts/ bundle goes unsurfaced.

Suggestions

Either add reference.md and forms.md to the bundle or remove/redirect those references; currently 'read forms.md and follow its instructions' is a dead end.

Surface the ./scripts/ scripts in the body (e.g., a 'Form filling' section pointing to scripts/fill_fillable_fields.py and scripts/extract_form_field_info.py) so the existing bundle is discoverable.

Add validation checkpoints to batch/destructive operations (e.g., verify merged page counts, confirm encryption by re-opening, validate filled fields against expected values) so workflow_clarity can exceed the cap of 3.

Dimension	Reasoning	Score
Conciseness	The body is almost entirely lean, executable code with brief section headers and assumes Claude's competence; it is not 5 because of minor redundancy — Quick Start extracts text the same way the pdfplumber section does, and the Quick Reference table plus Next Steps partly restate earlier content.	4 / 5
Actionability	Every section is copy-paste-ready executable code or shell commands covering the common cases (merge, split, extract text/tables, create, rotate, OCR, watermark, encrypt, CLI tools); it is not below because guidance is concrete and complete rather than pseudocode or hints.	5 / 5
Workflow Clarity	Operations are presented as standalone snippets with no sequenced multi-step workflow and no validation checkpoints, and several are batch/destructive (merge over many files, encrypt/decrypt, form filling), which the rubric caps at 3; it is not 2 because each snippet's individual action is unambiguous, and not 4 because validation/feedback loops are absent.	3 / 5
Progressive Disclosure	There is real section structure and references to reference.md/forms.md are signaled in the Overview and Next Steps, but the disclosure is broken: reference.md and forms.md do not exist in the bundle, while the actual ./scripts/ bundle (8 form-filling scripts) is never mentioned anywhere in the body; it is not 4 because missing referenced files plus an invisible real bundle is worse than 'minor organization gaps', and not 2 because structure exists and references are signaled rather than buried.	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, comprehensive description that explicitly states both capabilities and trigger conditions in third-person voice with concrete keywords including the file extension. No meaningful gaps relative to the rubric anchors.

Dimension	Reasoning	Score
Specificity	Lists many concrete actions — 'reading or extracting text/tables', 'merging multiple PDFs', 'splitting PDFs apart', 'rotating pages', 'adding watermarks', 'filling PDF forms', 'encrypting/decrypting', 'extracting images', 'OCR' — matching the comprehensive-coverage anchor; it is not below because it goes well beyond naming 1-2 actions.	5 / 5
Completeness	Explicitly answers both 'what' (the enumerated operations) 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; it is not below because the 'when' is explicit, not merely implied.	5 / 5
Trigger Term Quality	Covers natural terms and the file extension — 'PDF files', 'PDFs', '.pdf file', 'PDF forms', 'document extraction' — matching the comprehensive synonym-plus-extension anchor; it is not below because it includes both the extension and common phrasings users say.	5 / 5
Distinctiveness Conflict Risk	Scoped tightly to PDFs with distinct triggers (the .pdf extension, PDF forms), giving a clear niche with minimal overlap risk; it is not below because the domain is unambiguous rather than broadly overlapping with sibling skills.	5 / 5
	Total	20 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: K-Dense-AI/scientific-agent-skills
Path: skills/pdf/SKILL.md
Commit: b2a92ba

Reviewed: 3 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.