CtrlK
BlogDocsLog inGet started
Tessl Logo

pptx

Use this skill any time the user wants to create a new PowerPoint presentation, slide deck, pitch deck, or .pptx file from scratch. Covers creating business presentations, quarterly reports, project proposals, product roadmaps, training materials, and any multi-slide document destined for PowerPoint. Works by generating HTML/CSS slides (which LLMs excel at), rendering them in agent-browser for pixel-accurate DOM position extraction, and assembling the final PPTX with native PowerPoint charts, tables, and images via PptxGenJS. Includes bundled scripts for validation, DOM extraction, and PPTX assembly. Do NOT use this skill for editing existing PPTX files, converting other formats to PPTX, or extracting content from PPTX files.

92

2.05x
Quality

96%

Does it follow best practices?

Impact

76%

2.05x

Average score across 3 eval scenarios

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

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.

A strong, execution-focused skill body: a clearly sequenced five-step pipeline with validation and visual-review checkpoints, copy-paste-ready commands at every step, and a clean overview-to-references split verified against the actual bundle. The only weakness is minor redundancy (repeated viewport instructions, duplicated placeholder markup, and a scripts table that restates workflow commands).

Suggestions

State the 960x540 viewport requirement once (Step 2) and have Step 4 and the Troubleshooting table reference it instead of repeating the full command.

Trim the Scripts table to script name and purpose (the full invocation commands already appear in the workflow steps), and drop the duplicated placeholder HTML example from the Key constraints list since the Placeholder System section shows it.

Note that `open` is macOS-specific (e.g., suggest `xdg-open` on Linux) and add `jq` to the Prerequisites block, since both are used in the pipeline.

DimensionReasoningScore

Conciseness

The body is dense and command-driven with no explanations of concepts Claude already knows, but contains trimmable redundancy: the viewport-setting instruction appears in Step 2, Step 4, and the Troubleshooting table; the placeholder HTML snippet is duplicated; and the Scripts table repeats full command lines already shown in the workflow steps. Not 5 because not every token earns its place; not 3 because the padding is minor and the material is otherwise tightly written.

4 / 5

Actionability

Every step ships exact, copy-paste-ready commands ('agent-browser set viewport 960 540', 'cat $SKILL_DIR/scripts/validate.js | agent-browser eval --stdin --json', 'node $SKILL_DIR/scripts/build-pptx.js …'), with the {title} directory convention explained and exact numeric constraints given. The only nits (macOS-only `open`, `jq` unlisted in prerequisites) do not leave common cases without executable guidance.

5 / 5

Workflow Clarity

The five-step pipeline is explicitly sequenced with an early validation gate ('Returns { "valid": true/false }. Fix any errors before proceeding'), mandatory visual checkpoints ('You MUST run `open` after each screenshot'), and a symptom/cause/fix troubleshooting table for error recovery. This matches the top anchor's explicit validation, feedback loops, and recovery guidance; not 4 because checkpoints are explicit rather than implied.

5 / 5

Progressive Disclosure

The body is a genuine overview that inlines only key constraints and delegates detail to three clearly signaled, one-level-deep references (html-rules.md, slide-templates.md, pptxgenjs.md — all verified present with the promised content) plus four bundled scripts, with a closing Reference Files section for navigation. Not 4: no content that belongs in a reference is inlined and no organization gaps observed.

5 / 5

Total

19

/

20

Passed

Description

100%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.

An exemplary description: third-person voice, explicit 'use when' triggers with natural synonyms and the .pptx extension, concrete capability statements, and explicit boundary exclusions that prevent mis-triggering. Every clause carries information with no fluff or over-claims.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions — 'generating HTML/CSS slides', 'rendering them in agent-browser for pixel-accurate DOM position extraction', 'assembling the final PPTX with native PowerPoint charts, tables, and images via PptxGenJS', plus 'bundled scripts for validation, DOM extraction, and PPTX assembly' — giving comprehensive, non-generic coverage. Not 4: the action list is comprehensive with no meaningful coverage gaps.

5 / 5

Completeness

Both questions are explicitly answered: what it does (HTML-to-PPTX generation pipeline with native charts, tables, images) and when to use it ('Use this skill any time the user wants to create a new PowerPoint presentation, slide deck, pitch deck, or .pptx file from scratch'), with concrete trigger phrases throughout. Not 4: the 'when' clause is fully explicit, not merely present.

5 / 5

Trigger Term Quality

Natural user phrasing is comprehensively covered: 'PowerPoint presentation, slide deck, pitch deck, or .pptx file', plus concrete use cases ('quarterly reports, project proposals, product roadmaps, training materials'). Includes both synonyms and the file extension, matching the top anchor rather than the 'a few natural terms missing' anchor.

5 / 5

Distinctiveness Conflict Risk

It occupies a clear niche (creation from scratch only) and explicitly states 'Do NOT use this skill for editing existing PPTX files, converting other formats to PPTX, or extracting content from PPTX files', eliminating overlap with an edit/extract-focused presentation skill. Minimal conflict risk.

5 / 5

Total

20

/

20

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
treasure-data/td-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.