CtrlK
BlogDocsLog inGet started
Tessl Logo

impress

Presentation creation, format conversion (ODP/PPTX/PDF), slide automation with LibreOffice Impress.

46

Quality

49%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/libreoffice/impress/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

32%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This skill reads more like a feature overview or documentation landing page than an actionable skill file. It spends significant tokens on capability enumeration and generic best practices while lacking validation steps for its batch and XML-manipulation workflows. The code examples, while present, are incomplete in terms of error handling and practical usability.

Suggestions

Remove the 'Core Capabilities' bullet list and 'When to Use This Skill' section entirely — they describe what the skill does rather than instructing Claude how to do it.

Add explicit validation steps to the template-based generation workflow (e.g., validate the modified content.xml, verify the output ZIP is a valid ODP) and add error handling to the batch conversion loop.

Replace the generic 'Best Practices' list with specific, actionable guidance tied to common failure modes (e.g., 'Always kill existing soffice processes before starting headless conversion to avoid port conflicts').

Split the UNO scripting details and format conversion reference into separate bundle files, keeping SKILL.md as a concise overview with clear pointers.

DimensionReasoningScore

Conciseness

The skill is noticeably verbose with sections like 'When to Use This Skill' listing obvious use cases, 'Core Capabilities' that merely enumerate features without adding actionable value, and 'Best Practices' that are generic advice Claude already knows. The bulleted capability lists are padding that could be eliminated.

2 / 5

Actionability

There are some concrete code examples (conversion commands, UNO script, template generation), but the UNO example is questionable in practice (requires a running LibreOffice instance with socket), the template generation lacks validation, and many sections are just descriptive bullet lists without executable guidance. The command-line reference section is redundant with earlier examples.

3 / 5

Workflow Clarity

Workflows are loosely presented without clear sequencing or validation checkpoints. The batch conversion loop has no error handling or validation. The template-based generation manipulates XML (a fragile operation) with no validation step after modification, and the UNO workflow doesn't verify the socket connection is available before proceeding. Per rubric guidelines, missing feedback loops for batch and XML manipulation operations should cap this at 3, and the actual content falls below even that threshold.

2 / 5

Progressive Disclosure

No bundle files are provided, yet the skill is ~150 lines with inlined content that could benefit from separation (e.g., UNO API examples, format conversion reference). The 'Core Capabilities' section is a wall of bullet points that adds no navigational value. References to external docs exist but there's no structured layering of content.

2 / 5

Total

9

/

20

Passed

Description

66%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 reasonably specific about capabilities and tools, naming concrete formats and the underlying tool (LibreOffice Impress). Its main weakness is the absence of a 'Use when...' clause, which limits Claude's ability to know when to select this skill. Adding trigger guidance and a few more natural user terms (e.g., 'PowerPoint', 'slideshow') would significantly improve it.

Suggestions

Add a 'Use when...' clause with trigger phrases like 'Use when the user asks to create, edit, or convert presentations, or mentions slides, .pptx, .odp, PowerPoint, or LibreOffice Impress.'

Include common synonyms and terms users naturally say, such as 'PowerPoint', 'slideshow', '.pptx files', and 'slide deck'.

DimensionReasoningScore

Specificity

Lists several specific actions: 'presentation creation', 'format conversion', 'slide automation', and names specific formats (ODP/PPTX/PDF) and the tool (LibreOffice Impress). Minor gaps — doesn't elaborate on what 'slide automation' entails or mention editing, adding content, etc.

4 / 5

Completeness

Has a clear 'what' (presentation creation, format conversion, slide automation) but completely lacks a 'when' clause. There is no 'Use when...' or equivalent trigger guidance, which per the rubric caps completeness at 3.

3 / 5

Trigger Term Quality

Includes good keywords like 'presentation', 'ODP', 'PPTX', 'PDF', 'slide', 'LibreOffice Impress'. Missing some natural user terms like 'slideshow', '.pptx', '.odp', 'PowerPoint', or 'slides' as a standalone term. Users often say 'PowerPoint' even when meaning generic presentations.

4 / 5

Distinctiveness Conflict Risk

Fairly distinct by specifying LibreOffice Impress and the specific formats ODP/PPTX/PDF. Could overlap with a generic presentation skill or a PDF conversion skill, but the LibreOffice Impress mention narrows the niche well.

4 / 5

Total

15

/

20

Passed

Validation

90%

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

Validation10 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

10

/

11

Passed

Repository
administrakt0r/AI-Agents-Safe-Coding-Skills
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.