CtrlK
BlogDocsLog inGet started
Tessl Logo

metis-strategy/metis-pptx

Create or edit PowerPoint presentations. Dual-mode skill: (1) Editing mode preserves existing templates via Open XML unpack/edit/repack when an existing .pptx is provided. (2) Generation mode creates new Metis-branded decks from a design system with 36 composable components and 5 layout grids. Includes brand extraction for client decks and visual QA via PowerPoint COM. Triggers on deck, slides, presentation, PPT, or any .pptx request.

72

Quality

90%

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

Overview
Quality
Evals
Security
Files

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 body is highly actionable with clear sequenced workflows and validation loops, and its bundle references are real and well-organized. It loses points on conciseness and progressive disclosure due to a ~940-line monolithic body with verbatim duplication and inline material that could be externalized.

Suggestions

Remove the verbatim duplicate of the 'Visual Variety Rule' block in §2.5 Phase 1 (it appears twice back-to-back) and trim the scope-down rationalization paragraphs to recover tokens.

Extract the §0.6 concept-to-shape philosophy and the §0.6.1 worked example into a reference file (e.g. references/thought-to-shape.md), leaving SKILL.md as an overview that points to it.

Tighten the meta-commentary around 'Why build init is mandatory' and the anti-patterns lists into concise bullet form to reduce padding.

DimensionReasoningScore

Conciseness

The body avoids teaching concepts Claude already knows and is dense with domain-specific operational detail, but it runs ~940 lines with padded meta-commentary and a verbatim duplicate of the 'Visual Variety Rule' (§2.5 Phase 1), so it is mostly efficient but could be tightened rather than lean.

2 / 3

Actionability

Provides fully executable bash commands with exact python paths, copy-paste-ready PowerPoint COM snippets, precise brand tokens (#20206E, exact inches), and named helper functions — matching the 'copy-paste ready' anchor.

3 / 3

Workflow Clarity

Editing (§1.1–1.11) and Generation (§2.5 phased) workflows are explicitly sequenced with validation checkpoints (clean+pack, visual QA loop §3.5, 'fix-and-verify cycle' requirement) and feedback loops for the fragile XML/COM operations.

3 / 3

Progressive Disclosure

All bundle references (patterns.md, metis-brand.md, timesaver_index.md, representatives.json, scripts/) are real, one level deep, and clearly signaled, but the SKILL.md body itself is a large monolithic wall with substantial inline content (full browse philosophy, §0.6.1 worked example, duplicated rules) that could live in references.

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 specific, trigger-rich, and answers both 'what' and 'when' with concrete two-workflow routing, all in third person. It is among the strongest reference examples.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Create or edit PowerPoint presentations' with two distinct workflows (template-preserving editing and Metis-branded generation) — matching the 'multiple specific concrete actions' anchor.

3 / 3

Completeness

Clearly states both what the skill does (create/edit PowerPoint presentations via two workflows) and when to use it (explicit 'Also trigger on…' guidance plus two routing conditions), answering what AND when.

3 / 3

Trigger Term Quality

Explicit natural triggers — "slides," "deck," "presentation," "PPT," and "any .pptx request" — give good coverage of terms users would actually say, matching the highest anchor.

3 / 3

Distinctiveness Conflict Risk

Targets a clear niche (PowerPoint/Metis-branded decks) with distinct two-mode routing; unlikely to fire for unrelated skills. Uses correct third-person voice throughout.

3 / 3

Total

12

/

12

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 (949 lines); consider splitting into references/ and linking

Warning

Total

15

/

16

Passed

Reviewed

Table of Contents