CtrlK
BlogDocsLog inGet started
Tessl Logo

gpt-image2-ppt

Generate visually striking PPT slides via OpenAI's gpt-image-2 -- use any style in styles/<id>.md or mimic a user-supplied .pptx template; outputs high-res slide PNGs and a 16:9 .pptx. Use when the user asks to make a presentation, slides, deck, pitch deck, investor PPT, magazine-style PPT, or 做一份 PPT / 生成幻灯片 / 用 gpt-image 生成 PPT / 按这个模板生成 PPT.

71

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Failed to scan

The risk profile of this skill

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 commands and well-validated workflows, but it suffers from verbosity and references many styles/docs/examples files that are absent from the actual bundle, undermining progressive disclosure.

Suggestions

Move the 30-row style catalog into styles/ or docs/distilled-styles.md and keep only a short pointer + a few representative examples in SKILL.md to cut body length.

Ensure referenced files (styles/, examples/<id>/, docs/edit_guide.md, docs/workflow.md, docs/external_image_overlay_logic.txt) actually ship in the bundle, or remove/inline the references.

Condense the environment-variable and precedence prose into a compact table plus a single code block; the multi-paragraph explanation repeats concepts Claude already knows.

DimensionReasoningScore

Conciseness

The body is highly verbose (~800 lines) and explains considerable material — e.g. the full 30-style table, exhaustive env-var prose, and long readable-precedence narratives — that could be pushed into referenced files; it is mostly efficient but clearly could be tightened, matching the middle anchor.

2 / 3

Actionability

Provides fully executable copy-paste commands (generate_ppt.py invocations, md_to_plan.py, render_template.py --check, inline python-pptx packaging snippet) and concrete JSON slide_spec examples, matching the executable/code-ready top anchor.

3 / 3

Workflow Clarity

Multi-step flows are clearly sequenced with explicit validation checkpoints — "在跑任何 --template-pptx 命令之前,你必须先检查本机是否有可用 PPTX 渲染后端", render_template.py --check before --editable, and per-page editable_renders review — matching the clear-sequence-with-validation anchor.

3 / 3

Progressive Disclosure

The body signals many references (styles/<id>.md, examples/<id>/, docs/distilled-styles.md, docs/edit_guide.md, docs/workflow.md, docs/external_image_overlay_logic.txt) but none of these referenced files exist in the actual bundle (only scripts/ is present), so navigation points to missing material and overview/reference separation is incomplete, fitting the middle anchor.

2 / 3

Total

10

/

12

Passed

Description

100%

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 exemplary: it states concrete capabilities, provides explicit trigger guidance in both English and Chinese, and occupies a distinct niche. It uses correct third-person voice with no first/second person.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — "use any style in styles/<id>.md or mimic a user-supplied .pptx template", "outputs high-res slide PNGs and a 16:9 .pptx" — which matches the top anchor for listing several specific concrete actions.

3 / 3

Completeness

Clearly answers both what it does (generate slide PNGs and a .pptx via gpt-image-2) and when to use it via the explicit "Use when the user asks to..." clause, hitting the top anchor.

3 / 3

Trigger Term Quality

Excellent coverage of natural phrasings users would say — "make a presentation, slides, deck, pitch deck, investor PPT" plus Chinese variants "做一份 PPT / 生成幻灯片 / 用 gpt-image 生成 PPT / 按这个模板生成 PPT", matching the good-coverage anchor.

3 / 3

Distinctiveness Conflict Risk

The gpt-image-2 slide-generation niche with style/template triggers is highly specific and unlikely to be confused with general PPT or document skills, matching the clear-niche anchor.

3 / 3

Total

12

/

12

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.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (813 lines); consider splitting into references/ and linking

Warning

referenced_paths_exist

Referenced path issues: 1 missing

Warning

Total

14

/

16

Passed

Repository
JuneYaooo/gpt-image2-ppt-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.