Mck-ppt-design-skill
A Python-based PowerPoint (pptx) design system/engine that generates slide decks from high-level calls and a set of predefined layout patterns (including BLOCK_ARC chart rendering). It includes a post-generation QA pipeline with automated fixes to reduce overflow/collision/font consistency issues and performs PPT XML cleanup and CJK font handling.
Score Breakdown
⚙ Agent Friendliness
🔒 Security
No remote service is described, so TLS/auth around network transport are not applicable. As a local PPT generator, risk is mainly around handling font assets and any external resources; the excerpt emphasizes deterministic cleanup (_clean_shape/full_cleanup) which can reduce corrupted output but does not address supply-chain dependency scanning or runtime sandboxing. No secret handling details are provided; assume typical library usage without credentials.
⚡ Reliability
Best When
You want programmatic generation of .pptx files using Python (python-pptx) with consistent, repeatable layouts and automatic QA/fix-up of common rendering defects.
Avoid When
You need a network service with REST/GraphQL endpoints, OAuth, webhooks, or strong guarantees of stable behavior across versions without running tests.
Use Cases
- • Automatically generating consulting-style/pitch-deck PowerPoint slide decks from structured inputs
- • Creating and rendering chart-heavy decks with deterministic layout/geometry logic
- • Applying a consistent brand/typography/layout system across many slides
- • Auto-checking generated decks for text overflow, collisions, and legend/layout boundary issues
Not For
- • Interactive/real-time presentation editing workflows
- • Using through a remote API without embedding the Python library
- • Production environments that require formal SLAs, documented operational error codes, or guaranteed backward compatibility without verification
Interface
Authentication
No authentication described; this appears to be a local/offline Python library that writes .pptx files.
Pricing
No pricing information provided in the supplied README excerpt; license is Apache-2.0.
Agent Metadata
Known Gotchas
- ⚠ No network interface or agent-friendly contract (MCP/REST) is documented; agents must use the Python API surface.
- ⚠ If QA/autofix fails to reach a 0-error gate, the run behavior/returned artifact is not fully specified in the excerpt—agents should be prepared to handle failures after save and/or during autofix.
Alternatives
Full Evaluation Report
Comprehensive deep-dive: security analysis, reliability audit, agent experience review, cost modeling, competitive positioning, and improvement roadmap for Mck-ppt-design-skill.
AI-powered analysis · PDF + markdown · Delivered within 30 minutes
Package Brief
Quick verdict, integration guide, cost projections, gotchas with workarounds, and alternatives comparison.
Delivered within 10 minutes
Score Monitoring
Get alerted when this package's AF, security, or reliability scores change significantly. Stay ahead of regressions.
Continuous monitoring
Scores are editorial opinions as of 2026-03-30.