pdf

PDF files: create, read, merge, fill, OCR, edit text.

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

92%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 and well-structured, with explicit validation feedback loops and clean one-level-deep progressive disclosure; its only weakness is minor redundancy between the command example block and the Quick Reference table.

Dimension	Reasoning	Score
Conciseness	The body is action-dense and mostly free of concepts Claude already knows, but the How-to-Run block and Quick Reference table overlap in command coverage, leaving minor instances that could be trimmed; it sits just below the lean level-5 anchor.	4 / 5
Actionability	Every helper is shown as a concrete, copy-paste-ready argparse CLI invocation with exact flags and arguments (e.g. `pdf_stamp.py doc.pdf -o out.pdf --text "DRAFT" --x 150 --y 400`), fully covering the common cases.	5 / 5
Workflow Clarity	The 9-step Procedure is explicitly sequenced with validation checkpoints ("Inspect first", "Verify before reporting success") and a form-design feedback loop (spec → lint → overlay → iterate), matching the level-5 anchor with explicit validation and error-recovery loops.	5 / 5
Progressive Disclosure	SKILL.md is a clear overview with well-signaled one-level-deep references to real files (references/ocr-extraction.md, references/nano-pdf-editing.md, references/forms.md), with absorbed capabilities appropriately split out and no nested reference chains.	5 / 5
	Total	19 / 20 Passed

Description

75%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.

The description is specific and clearly PDF-scoped with a strong action list, but it omits any explicit "Use when" trigger guidance, which caps its completeness and leaves a few natural trigger terms (PDFs, .pdf, forms) uncovered.

Suggestions

Add a 'Use when...' clause naming concrete triggers, e.g. 'Use when creating, reading, merging, filling, or OCR-ing PDFs, or when the user mentions .pdf files or forms.'

Include synonyms and the file extension ("PDFs", ".pdf", "forms") to broaden natural trigger coverage.

Keep third-person voice (already correct) while extending the description with the trigger guidance rather than adding first/second person phrasing.

Dimension	Reasoning	Score
Specificity	The description enumerates six concrete actions — "create, read, merge, fill, OCR, edit text" — giving comprehensive coverage of the skill's capabilities, matching the level-5 anchor that lists multiple specific concrete actions.	5 / 5
Completeness	The "what" is clearly stated via the action list, but there is no "Use when..." clause or equivalent explicit trigger guidance, which per the judging guidelines caps completeness at 3.	3 / 5
Trigger Term Quality	"PDF files" plus action terms like "OCR" provide good natural keyword coverage, but synonyms ("PDFs") and the file extension ".pdf" and "forms" are missing, fitting just below the comprehensive level-5 anchor.	4 / 5
Distinctiveness Conflict Risk	"PDF files:" pins the skill to a distinct file format with PDF-specific actions, yielding a clear niche with minimal overlap risk against the related docx/xlsx skills.	5 / 5
	Total	17 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: NousResearch/hermes-agent
Path: skills/productivity/pdf/SKILL.md
Commit: 6327930

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.