CtrlK
BlogDocsLog inGet started
Tessl Logo

officecli-pptx

Use this skill any time a .pptx file is involved -- as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx file; editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates, layouts, speaker notes, or comments. Trigger whenever the user mentions 'deck', 'slides', 'presentation', 'pitch', or references a .pptx filename.

70

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Critical

Do not install without reviewing

SKILL.md
Quality
Evals
Security

Quality

Content

81%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 highly actionable, well-sequenced skill with strong validation feedback loops and a clever help-based deferral of schema detail. Its main weakness is conciseness: a monolithic ~570-line body that interleaves genuinely useful CLI specifics with general slide-design wisdom Claude already knows, with some redundancy.

Suggestions

Move general design principles (the 'audience has 3 seconds', 'less is more', whitespace-as-structure prose) into a reference file or trim to officecli-specific guidance to cut tokens Claude doesn't need.

Split the large palette (10 themes) and font-pairing tables into a references/ file and point to them from SKILL.md to improve progressive disclosure toward a 5.

De-duplicate the currency-escaping rule, which is stated in both 'Shell & Execution Discipline' and re-explained in the recipes section.

DimensionReasoningScore

Conciseness

Densely packed with officecli-specific commands and gotchas, but it also explains general design concepts Claude already knows ('A deck is not a document. The audience has 3 seconds to get each slide.', 'Less is more', 'Whitespace is structural') and repeats the currency-escaping guidance in multiple places, fitting 'mostly efficient but includes some unnecessary explanation or could be tightened' rather than the 'minor instances' anchor at 4.

3 / 5

Actionability

Provides copy-paste-ready, fully executable bash blocks for the common cases (Quick Start cover+content+notes, plus recipes for data slides, flowcharts, KPI grids, and decision trees) alongside specific prop syntax and per-element command examples, matching the 'fully executable; copy-paste ready; covers common cases' anchor.

5 / 5

Workflow Clarity

An 8-step Common Workflow is reinforced by a QA section with explicit validation gates (validate, view issues, placeholder scan), a fix-verify loop capped at 3 cycles, and 'only proceed when valid' gating plus 'one command -> check exit code' and 'get after structural ops' — matching the 'clear sequence with explicit validation steps; feedback loops; checklists' anchor.

5 / 5

Progressive Disclosure

Well-organized into clear headed sections and defers prop/schema detail one level deep to `officecli help` (e.g. 'Full prop list: help pptx add chart'), but the skill is a single monolithic ~570-line file with no bundle reference files, so it fits 'good structure; references mostly clear; minor organization gaps' rather than the 'content appropriately split across files' anchor at 5.

4 / 5

Total

17

/

20

Passed

Description

92%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 strong, comprehensive description that explicitly states both capabilities and trigger conditions with concrete natural-language phrases. Its only gap is omitting the ubiquitous 'PowerPoint'/'PPT' synonyms from the trigger list.

Suggestions

Add 'PowerPoint' and 'PPT' to the trigger list so users who say those common terms match the skill.

Consider noting 'templates, layouts, speaker notes, or comments' more concisely — the action enumeration is long and could be tightened without losing specificity.

DimensionReasoningScore

Specificity

Lists multiple concrete actions across the full pptx lifecycle — 'creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text...; editing, modifying, or updating...; combining or splitting slide files; working with templates, layouts, speaker notes, or comments' — matching the comprehensive-coverage anchor rather than the 'several actions, minor gaps' anchor at 4.

5 / 5

Completeness

Explicitly answers both what (the enumerated create/parse/edit/split actions) and when — 'Use this skill any time a .pptx file is involved' and 'Trigger whenever the user mentions deck, slides, presentation, pitch, or references a .pptx filename' — with concrete trigger phrases, satisfying the top anchor and avoiding the missing-trigger cap at 3.

5 / 5

Trigger Term Quality

Strong natural coverage ('deck', 'slides', 'presentation', 'pitch', '.pptx'), but the very common user synonyms 'PowerPoint' and 'PPT' are absent, so it fits 'good keyword coverage; a few natural terms missing' (4) rather than the comprehensive synonym+extension anchor at 5.

4 / 5

Distinctiveness Conflict Risk

Scoped tightly to .pptx with distinct deck/slides/presentation/pitch triggers, giving a clear niche with minimal overlap risk against sibling docx/xlsx skills; fits the 'clear niche with distinct triggers' anchor rather than the 'minor overlap with closely related skills' anchor at 4.

5 / 5

Total

19

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (569 lines); consider splitting into references/ and linking

Warning

Total

15

/

16

Passed

Repository
iOfficeAI/OfficeCLI
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.