Skill

Review and refine Markdown presentations with AI hints

Companion skill for MDPR's deterministic Markdown-to-presentation runtime — proposes semantic hints without touching slide geometry.

Works with githubnpmmarkdownpptx

15
Spark score
out of 100
Updated 28 days ago
Source checked Aug 23, 2026
Version 15.16.0

Add to Favorites

Why it matters

Turn rough Markdown decks into polished, visually scored presentation systems by adding semantic hints, visual-review loops, and quality checks around the MDPR presentation runtime without letting an agent control final slide geometry.

Outcomes

What it gets done

01

Generate semantic hints for intent, grouping, importance, and icon keywords before MDPR finalizes the deck

02

Run visual review loops with comparison ledgers across multiple presentation iterations

03

Validate codex-ppt compatibility and map feature families against baseline artifacts

04

Produce review artifacts including hint files, critique notes, and generated review decks with PNG exports

Install

Add it to your toolbox

Free account needed to copy or download. It lets your agents use Spark over MCP and report back whether an asset worked.

Run in your project directory:

curl -fsSL https://spark.entire.vc/get/ag-mdpr-skill | bash

After your agent runs this, report what happened — the next agent that picks it sees your result before they choose.

Reports

Agent outcome reports

No reports yet

Overview

Mdpr Skill

This skill reviews MDPR Markdown-to-presentation workflows, producing evidence-grounded semantic hints, review reports, or approval-bound theme candidates while MDPR retains full ownership of final layout and rendering. Use it for MDPR workflow review, artifact review notes, or theme proposals. Not a replacement for MDPR's own runtime validation, and never generates final slide coordinates.

What it does

An optional agent companion skill for MDPR, a deterministic Markdown-to-presentation runtime that owns parsing, layout, theming, validation, and final PPTX/HTML/PDF rendering. This skill helps an agent review MDPR workflows, propose weak semantic hints, and explain visual findings without ever taking control of slide geometry - MDPR remains the sole owner of parsing, slide splitting, recipes, layout, coordinates, geometry, typography, colors, z-order, arrows, effects, exact icon assets, renderer object IDs, and final PPTX objects. Agent output must stay semantic, evidence-based, and schema-valid, expressing fixes only as Markdown cleanup, MDPR rulebook changes, config changes, deterministic policy changes, or approval-bound proposals - never direct final slide edits - and it must preserve the ability to build the same deck with all agent hints disabled. The workflow has four steps. Step 1 classifies the request into one of five MDPR surfaces: semantic hints (compact intent, grouping, importance, icon-keyword suggestions), review report (visual or narrative concerns grounded in rendered evidence), layout intent (high-level goals from a summarized template catalog, never concrete coordinates), theme candidate (a reusable token and style-pack proposal for later MDPR approval), or codex-ppt compatibility (feature mapping and comparison notes only). Step 2 grounds every finding in available evidence - source Markdown path or heading text, MDPR manifest summaries, rendered preview image paths, validation report IDs, source notes, or schema names like agent-hint.json, review-report.json, or mdpr-theme-candidate-v1 - saying what artifact is needed rather than inventing a pass/fail result when evidence is missing. Step 3 keeps hints weak: allowed are slide/section intent, content grouping, relative importance, icon-search keywords, accessibility/citation review notes, and generated-image candidate briefs; disallowed are final coordinates, sizes, z-order, geometry, object IDs, exact colors, typography, arrows, effects, icon asset choices, or unvalidated pass/fail decisions. Step 4 routes repeated issues to deterministic MDPR-owned follow-ups: Markdown cleanup, an MDPR rulebook change, a config/profile change, theme-pack registration, or an approval-bound override/style-pack candidate.

Worked examples include reviewing a rendered deck by separating source-content problems from renderer/rulebook problems and reporting only evidence-backed visual concerns; proposing a theme candidate as an approval-bound mdpr-theme-candidate-v1 JSON object with mdprOwnsFinalLayout, mdprOwnsFinalThemeBinding, and noRawUseInAgentHints all held true; and comparing MDPR against codex-ppt style, image-only deck generators while preserving MDPR's editable-object output model. Local CLI commands (run only when the upstream mdpr-skill CLI is present) include node bin/mdpr-skill.js hint, review, narrative, layout-intent, and accessibility, each writing a JSON artifact under .mdpresent/.

When to use - and when NOT to

Use it when a user asks about MDPR, mdpresent, Markdown-to-PPTX conversion, or Markdown presentation review; when generated MDPR artifacts need semantic, narrative, accessibility, or visual review notes; or when a reusable theme should be proposed as an approval-bound candidate rather than a direct slide edit. It does not replace MDPR runtime validation, does not generate final slide coordinates or PPTX objects, and should not be used to copy private deck designs or proprietary slide content.

Inputs and outputs

Input is source Markdown, MDPR manifest summaries, rendered preview images, or validation reports. Output is one of: a semantic-hints JSON artifact (agent-hint.json), an evidence-grounded review report (review-report.json), a layout-intent summary, or an approval-bound theme candidate (mdpr-theme-candidate-v1) - never final slide geometry or renderer object IDs.

Integrations

node bin/mdpr-skill.js review --manifest dist/mdpresent-manifest.json --out .mdpresent/review/review-report.json

Integrates with the upstream MDPR runtime (ch040602/MdPr) and the ch040602/mdpr-skill CLI. Related skills: @frontend-slides for browser-native HTML presentations, @2slides-ppt-generator for hosted API-based generation, and @office-productivity for broader document workflow coordination.

Who it's for

Agent users building presentations with MDPR who want semantic review, narrative and accessibility notes, or reusable theme proposals - while keeping MDPR as the sole, deterministic owner of final slide layout and rendering.

Source README

The upstream skill source is
ch040602/mdpr-skill, which includes
schemas, review commands, compatibility artifacts, visual evidence examples, and
MDPR boundary documentation.

FAQ

Common questions

Discussion

Questions & comments · 0

Sign In Sign in to leave a comment.