CtrlK
BlogDocsLog inGet started
Tessl Logo

ppt-generation-resilient

Robust PowerPoint generation with shell_agent primary approach and python-pptx fallback, including working directory verification and inline error debugging

56

Quality

63%

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 ./benchmarks/gdpval/skills/ppt-workflow-location-enhanced-877e03/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

77%

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

The content is highly actionable with executable code and a well-sequenced, validated workflow including retry loops. Its main weaknesses are repetition that hurts token efficiency and a monolithic single-file structure with no progressive disclosure of detail into bundle files.

Suggestions

De-duplicate the '2>&1' stderr-capture advice into one authoritative section and reference it rather than restating it in five places.

Avoid re-printing the Python generation script in the 'Complete Workflow' example; reference the earlier full script instead.

Split long reference material (detailed troubleshooting, tool-specific notes) into a references/ file and link to it one level deep to improve progressive disclosure.

DimensionReasoningScore

Conciseness

The body is mostly efficient with concrete code and commands, but the '2>&1 to capture stderr' advice is repeated across Steps 2.2, debugging, the pitfalls table, tool-specific notes, and the troubleshooting section, and the Python script is duplicated in a second 'Complete Workflow' example, so it could be tightened.

2 / 3

Actionability

It provides fully executable, copy-paste-ready Python and bash snippets (generate_presentation.py, find/cp/stat commands, python-pptx verification one-liners) with specific examples rather than pseudocode.

3 / 3

Workflow Clarity

The process is clearly sequenced (Path 1 → verify → Path 2 fallback → locate → copy → verify) with explicit validation checkpoints (file size > 0, python-pptx can open it), a decision tree, a retry feedback loop (max 3 attempts), and a success-criteria checklist.

3 / 3

Progressive Disclosure

The skill is a single ~340-line monolithic SKILL.md with no bundle files (references/scripts/assets absent); the full script, troubleshooting, and tool notes that could be split out are all inline, so organization is present but content is not appropriately separated.

2 / 3

Total

10

/

12

Passed

Description

50%

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 conveys a clear, specific niche (resilient PowerPoint generation via a shell_agent-first, python-pptx-fallback strategy) but lacks an explicit 'Use when...' trigger and natural user keywords. It sits firmly at the middle level across all dimensions.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user asks to create or generate PowerPoint presentations, slides, or .pptx files, especially when shell_agent may fail or return opaque errors.'

Include natural user terms alongside the technical ones: 'presentations', 'slides', '.pptx', 'make a PowerPoint'.

List a couple more concrete actions (e.g. 'create slide decks, add titles and bullet points, save .pptx files') to lift specificity.

DimensionReasoningScore

Specificity

Names the domain ('PowerPoint generation') and the two concrete mechanisms ('shell_agent primary path', 'python-pptx fallback') but describes the approach rather than listing multiple specific actions like extract/fill/merge, so it is not comprehensive.

2 / 3

Completeness

It states what the skill does but includes no explicit 'Use when...' trigger, so the 'when' guidance is only implied; per the rubric a missing trigger clause caps completeness at 2.

2 / 3

Trigger Term Quality

'PowerPoint generation' is a somewhat natural term, but the rest is technical jargon ('shell_agent', 'python-pptx', 'resilient') and common user phrasings like 'slides', '.pptx', 'presentations', or 'make slides' are missing.

2 / 3

Distinctiveness Conflict Risk

The dual-path PowerPoint niche is fairly specific, but the thin trigger vocabulary means it could still overlap with generic presentation-generation skills.

2 / 3

Total

8

/

12

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
HKUDS/OpenSpace
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.