CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

pdf

Read, create, merge, split, fill, watermark, stamp, secure, inspect, render, and visually verify PDF files, including AcroForm workflows.

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

86%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 tight, well-structured skill body: lean prose, concrete commands, and a workflow with two explicit verification checkpoints, backed by a real one-level reference file and a complete script bundle. The main gaps are missing example invocations for several helpers and no explicit fix-and-retry loop after validation.

Suggestions

Add one-line example invocations for the remaining helpers (pdf_create.py, pdf_fill_form.py, pdf_secure.py, pdf_watermark.py) so users of the skill don't rely solely on --help for the most common non-read operations.

Extend the workflow with an explicit error-recovery step, e.g. 'If re-reading or the rendered page reveals a problem, fix the transformation and re-verify before returning the path.'

Clarify what to check when verification fails per operation type (e.g. field values not persisted after a fill) to close the feedback-loop gap.

DimensionReasoningScore

Conciseness

The ~53-line body is lean with no concept explanations (no 'what a PDF is' padding) and every section carries operational weight, e.g. 'Page rendering uses pypdfium2 when available and can fall back to Poppler's pdftoppm.' This matches the 'every token earns its place' anchor and is clearly above 4, which allows over-explanation to trim.

5 / 5

Actionability

Four copy-paste-ready commands are given ('python3 <baseDirectory>/scripts/pdf_read.py input.pdf --json', pdf_page_image, pdf_merge, pdf_split) plus 'Use --help to inspect exact arguments', matching 'mostly executable guidance with minor gaps'. It falls short of 5 because half the listed helpers (create, fill_form, watermark, stamp, meta, secure) have no example invocation.

4 / 5

Workflow Clarity

The 5-step workflow has explicit validation checkpoints ('Re-read the output to verify page count, text, metadata, attachments, or field values' and 'Render every changed page ... and inspect it with view_image'), so no validation cap applies. It is below 5 because there is no explicit error-recovery feedback loop saying what to do when verification fails.

4 / 5

Progressive Disclosure

The body is a concise overview that delegates form detail to a single, clearly signaled, one-level-deep reference ('For form work, read references/forms.md through skill_view before editing' — verified to exist with substantive content), and the Helpers section maps all 12 bundled scripts, which all exist. This matches the 'clear overview with well-signaled one-level-deep references' anchor.

5 / 5

Total

18

/

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.

A highly specific, comprehensive, well-scoped description that clearly communicates what the skill does across the whole PDF domain. Its one structural weakness is the absence of any 'when to use this' trigger clause, and the description text itself lacks the natural terms '.pdf' and plain 'forms'.

Suggestions

Append an explicit trigger clause such as 'Use when the user mentions PDF files, PDFs, .pdf files, forms, or document merging/splitting.'

Work the natural terms '.pdf' and plain 'forms' into the description body (not just metadata keywords) to improve trigger matching.

DimensionReasoningScore

Specificity

The description lists eleven concrete actions — 'Read, create, merge, split, fill, watermark, stamp, secure, inspect, render, and visually verify PDF files, including AcroForm workflows' — giving comprehensive coverage of the domain, matching the 5 anchor exactly rather than 4's 'minor gaps in coverage'.

5 / 5

Completeness

The 'what' is clear and comprehensive, but there is no 'Use when...' clause or equivalent explicit trigger guidance, which per the judging guidelines caps completeness at 3 ('when' missing or only weakly implied).

3 / 5

Trigger Term Quality

'PDF files' plus operation verbs users naturally say ('merge', 'fill', 'watermark') give good keyword coverage, but the description itself omits plain 'forms', '.pdf', and 'PDFs' (those appear only in metadata keywords). Better than 3's 'some relevant keywords', short of 5's 'synonyms and file extensions'.

4 / 5

Distinctiveness Conflict Risk

The scope is explicitly 'PDF files' with PDF-specific operations ('watermark, stamp, ... AcroForm workflows'), establishing a clear niche with minimal overlap risk against generic document or OCR skills, matching the 5 anchor.

5 / 5

Total

17

/

20

Passed

Validation

87%

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

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

Total

14

/

16

Passed

Repository

EKKOLearnAI/hermes-studio

Path

packages/ekko-agent/skills/pdf/SKILL.md

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.