MCPInstall

presentation-builder

Build real deck artifacts when the user needs editable slides, not just prose: investor decks, roadmap/QBR decks, launch decks, architecture/demo decks, workshop/training decks, and game pitch or milestone decks. Use when the job is to choose one deck mode, one smallest useful artifact packet, and one honest handoff surface (HTML review, PPTX, PDF, Google Slides, or Figma Slides). Triggers on: presentation, slide deck, slides, pitch deck, roadmap deck, investor deck, launch deck, architecture review deck, demo deck, workshop slides, keynote, board deck, QBR deck, and game pitch deck. Route long-form docs to technical-writing, end-user tutorials to technical-writing, research manuscripts to research-paper-writing, and broad marketing planning to marketing-automation.

Installs
450
Last 24h
—
Trending rank
—
Security
Not audited

Install

Works with every agent the skills CLI supports.

npx skills add https://github.com/akillness/jeo-skills --skill presentation-builder
  1. 01

    Install

    Run the command in your project. The CLI asks which agents to install for.

  2. 02

    Describe the task

    Ask your agent for something this skill covers. It loads presentation-builder automatically when relevant.

  3. 03

    Review the result

    The agent follows the SKILL.md steps, scripts and references bundled with the skill.

SKILL.md

The instructions your agent reads when the skill is triggered.

Presentation Builder

Use this skill when the deliverable is a deck artifact people will review, present, or hand off as slides, not just an outline or narrative document.

presentation-builder is the documentation/publishing-cluster anchor for:

  • investor, fundraising, board, and executive decks
  • roadmap, QBR, status, and decision-review decks
  • launch, GTM, and sales-enablement decks
  • architecture walkthroughs, demo decks, and technical presentations
  • workshop, training, and keynote decks
  • game pitch, publisher, and milestone-update decks

Read these support docs before choosing the workflow:

  • references/presentation-modes-and-routing.md
  • references/artifact-packets-and-last-mile-handoffs.md
  • references/source-and-handoff-patterns.md
  • references/review-and-export-checklist.md

When to use this skill

  • The user needs an actual slide deck, not just bullets or a memo.
  • The workflow needs slide planning, visual iteration, and deck-specific evidence.
  • The work must survive browser review before export or downstream office/design-tool cleanup.
  • The output needs an editable or shareable slide surface such as HTML viewer, PPTX, PDF, Google Slides, or Figma Slides.
  • The request names a deck artifact directly or clearly implies a presentation deliverable for review, pitching, enablement, or decision-making.

When not to use this skill

  • The main job is a technical spec, ADR, runbook, migration guide, or internal implementation document → use technical-writing
  • The main job is an end-user tutorial, onboarding guide, FAQ, or screenshot-heavy help-center flow → use technical-writing
  • The main job is a research paper, rebuttal, or academic manuscript → use research-paper-writing
  • The main job is broad launch planning, campaign strategy, positioning, or messaging without a concrete deck artifact → use marketing-automation
  • The main job is only an outline, memo, or planning artifact and no deck file is actually needed → use the relevant planning or writing skill first

Instructions

Step 1: Classify one deck mode, one artifact packet, and one handoff surface

Normalize the request before drafting.

presentation_builder_mode:
  deck_mode: investor | roadmap-review | launch-gtm | architecture-demo | workshop-training | game-pitch | other
  audience: executives | investors | customers | internal-team | mixed | unknown
  source_material: brief | doc | spreadsheet | screenshots | charts | prototype | mixed | unknown
  review_need: outline-approval | visual-approval | export-ready | mixed
  artifact_packet: outline-brief | storyboard | review-ready-html | export-handoff | sync-packet | unknown
  handoff_surface: html-viewer | pptx | pdf | google-slides | figma-slides | mixed | unknown

Choose exactly one primary deck_mode for the run:

  • investor → fundraising, board, strategic pitch, or executive narrative deck
  • roadmap-review → roadmap, QBR, planning, KPI, status, or decision-review deck
  • launch-gtm → launch briefing, sales-enablement, product narrative, or GTM deck
  • architecture-demo → technical walkthrough, architecture review, developer talk, or demo deck
  • workshop-training → workshop, training, keynote, or enablement deck
  • game-pitch → publisher pitch, game concept, milestone update, or studio BD deck

Use references/artifact-packets-and-last-mile-handoffs.md to pick the smallest useful packet and the real last-mile surface early.

Step 2: Lock the promise, evidence, and downstream editor

Before generating slides, answer these three questions:

  1. What should the audience understand, approve, or decide by the end?
  2. What evidence must appear on the slides? Screenshots, charts, metrics, citations, links, footage, or product visuals.
  3. Where will the final cleanup happen? Browser-only viewer, PPTX, PDF, Google Slides, or Figma Slides.

Do not pretend the handoff surface is irrelevant. Real deck workflows often start in HTML or Markdown but still end with office/design-tool cleanup.

Step 3: Route out non-deck work early

Use the smallest honest boundary:

If the request is mainly about...Use
technical specs, rollout docs, ADRs, migration detailstechnical-writing
tutorials, help docs, onboarding, screenshot walkthroughstechnical-writing
academic papers, rebuttals, manuscript sectionsresearch-paper-writing
messaging, launch strategy, campaigns, content calendarsmarketing-automation
a reviewable or handoff-ready deck artifactpresentation-builder

Many “make slides” requests are really document or messaging requests. Confirm the artifact before building slides.

Step 4: Choose the smallest artifact packet

Default to the smallest output that makes progress:

  • outline-brief → slide-by-slide outline with takeaway + evidence + risk notes
  • storyboard → stronger slide sequence and rough content plan before visual polish
  • review-ready-html → browser-reviewable deck source with visual iteration still open
  • export-handoff → approved deck plus explicit PPTX/PDF/Slides handoff status
  • sync-packet → deck plus short list of downstream artifacts or cleanup follow-ups

Do not jump straight to exported binaries when an outline or storyboard is the real next step.

Step 5: Build the deck from a stable source workspace

Default to a dedicated workspace such as:

decks/<deck-name>/
  slide-outline.md
  slide-01-cover.html
  slide-02-...
  assets/

Source rules:

  • keep the editable source in the deck workspace
  • keep raw evidence/assets close to the deck
  • revise the source slides, not the exported PPTX/PDF
  • keep spreadsheet/chart dependencies explicit if numbers may refresh later
  • treat PowerPoint / Google Slides / Figma as last-mile surfaces, not the hidden source of truth

Use references/source-and-handoff-patterns.md for source-lifecycle rules.

Step 6: Use the mode packet, then review visually

Use references/presentation-modes-and-routing.md for mode-specific slide patterns.

After creating or editing slides:

slides-grab build-viewer --slides-dir decks/<deck-name>
slides-grab validate --slides-dir decks/<deck-name>

For visual iteration:

slides-grab edit --slides-dir decks/<deck-name>

Review rules:

  • every slide should have one clear takeaway
  • screenshots, charts, and footage must remain legible
  • unsupported claims or placeholder visuals must be called out
  • if async review matters, plan for PDF readability, not only live presentation flow
  • if the deck will be edited outside the browser workflow, note the likely cleanup surface explicitly

Use references/review-and-export-checklist.md before export.

Step 7: Export or hand off honestly

Only export after the chosen packet is ready.

slides-grab convert --slides-dir decks/<deck-name> --output decks/<deck-name>.pptx
slides-grab pdf --slides-dir decks/<deck-name> --output decks/<deck-name>.pdf

Report all of these:

  • source workspace path
  • artifact packet selected
  • validation status
  • review status (outline approved / visually approved / export-ready)
  • handoff surface and likely cleanup location
  • output file paths
  • remaining manual-polish risks such as fonts, layout drift, chart refresh, or office-tool cleanup

Step 8: Return the deck status in the right shape

Preferred response structure:

  1. deck mode + audience
  2. artifact packet selected
  3. source workspace path
  4. evidence used and review findings
  5. export / handoff status and remaining risks

Core commands

slides-grab edit
slides-grab build-viewer
slides-grab validate
slides-grab convert
slides-grab pdf
slides-grab list-templates
slides-grab list-themes

All commands support --slides-dir <path>.

Examples

Example 1: Investor deck with explicit PPTX handoff

Turn this product brief into a 10-slide investor deck. Show me the outline first, then generate the deck in decks/series-a and hand off an editable PPTX after visual review.

Example 2: Architecture review deck for async review

Build an 8-slide architecture review deck for our browser automation service. Use screenshots, flow diagrams, and one slide on failure handling. I need a reviewable HTML deck first and a PDF for async review.

Example 3: Launch planning that should route out

Help me figure out the launch messaging, channel plan, and owners for next month's release.

Good direction: route to marketing-automation unless the user also needs a concrete deck artifact.

Best practices

  1. Treat deck work as a narrative + evidence + handoff problem, not just a styling task.
  2. Pick one deck mode, one packet, and one last-mile surface first.
  3. Prefer a stable HTML source and regenerate exports instead of editing binaries directly.
  4. Keep docs, spreadsheets, screenshots, and other upstream evidence explicit.
  5. Call out where manual cleanup is likely instead of hiding fidelity limits.
  6. Use the smallest packet that keeps progress honest.
  7. Keep route-outs sharp: many “slides” requests are really docs, research, or marketing work.

References

  • Upstream tool: https://github.com/vkehfdl1/slides-grab
  • Figma Slides: https://www.figma.com/slides/
  • Marp: https://marp.app/
  • Slidev: https://sli.dev/
  • Google Slides: https://workspace.google.com/products/slides/
  • Microsoft PowerPoint: https://support.microsoft.com/en-us/powerpoint

FAQ

What does the presentation-builder skill do?

Build real deck artifacts when the user needs editable slides, not just prose: investor decks, roadmap/QBR decks, launch decks, architecture/demo decks, workshop/training decks, and game pitch or milestone decks. Use when the job is to choose one deck mode, one smallest useful artifact packet, and one honest handoff surface (HTML review, PPTX, PDF, Google Slides, or Figma Slides). Triggers on: presentation, slide deck, slides, pitch deck, roadmap deck, investor deck, launch deck, architecture review deck, demo deck, workshop slides, keynote, board deck, QBR deck, and game pitch deck. Route long-form docs to technical-writing, end-user tutorials to technical-writing, research manuscripts to research-paper-writing, and broad marketing planning to marketing-automation.

How do I install presentation-builder?

Run npx skills add https://github.com/akillness/jeo-skills --skill presentation-builder in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/presentation-builder/ (personal) or .claude/skills/presentation-builder/ (project).

Which AI agents can use presentation-builder?

Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.

Is presentation-builder safe to install?

No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.

Who maintains presentation-builder?

It is published by akillness in akillness/jeo-skills. It has 450 recorded installs.

More from akillness/jeo-skills

View all →

rtk

akillness/jeo-skills

Install, initialize, verify, and troubleshoot RTK (Rust Token Killer) for AI coding agents. Use when you need to reduce shell-command token output, confirm that the correct rtk binary is installed, choose between Homebrew, install.sh, or Cargo installation, wire rtk init for Claude Code, Codex, Gemini CLI, Cursor, Copilot, Windsurf, Cline, or OpenCode, or use compact wrappers such as rtk git status, rtk read, rtk grep, rtk test, rtk lint, and rtk gain. Triggers on: rtk, rust token killer, token saver cli, rtk init, rtk gain, codex rtk, gemini rtk, opencode rtk, claude hook token reduction.

Backend & APIs672 installs

graphify

akillness/jeo-skills

Drive Graphify from its CLI to build, refresh, query, export, and serve a durable code/corpus knowledge graph. Use when the user wants .graphify/GRAPHREPORT.md, graph.json, graph.html, graphify update/summary/query/path/explain/tree, change-aware review context, git-hook or watch-based refresh, a stdio MCP graph server, or an install into jeo, jeopi, gjc, opencode, Claude, Codex, or Gemini. Also covers the honest structural fallback when native extraction is empty or misleading. Route simple locate/reference work to codebase-search, narrative knowledge-base work to llm-wiki, and project-memory handoff to opencontext. Triggers on: graphify, graphify update, graphify query, knowledge graph CLI, GRAPHREPORT.md, graph.json, codebase graph, graph refresh, graphify install, graphify serve, review context, affected flows.

data-analysis

akillness/jeo-skills

Analyze datasets to extract insights, identify patterns, and generate reports.

598 installs

code-refactoring

akillness/jeo-skills

Turn a cleanup packet into one behavior-preserving refactor brief. Use when simplifying a messy function/component/service, freezing behavior before touching fragile legacy code, splitting a cleanup-heavy diff into reviewable slices, or planning a repeated migration / codemod without changing intended behavior. Route diagnosis to debugging, review judgment to code-review, validation-program design to testing-strategies, bottleneck-led tuning to performance-optimization, and pure symbol inventory to codebase-search.

technical-writing

akillness/jeo-skills

Write internal technical documentation for engineers and operators: technical specs, architecture docs, ADRs, runbooks, migration plans, and developer-facing implementation guides. Use when the main job is capturing a technical decision, system boundary, operating procedure, or rollout path for builders and maintainers. Triggers on: tech spec, design doc, architecture doc, ADR, runbook, migration guide, implementation guide, rollout doc, operational guide, and internal technical writing. End-user onboarding guides, tutorials, FAQs, and help-center flows belong here too. Route API portals to api-documentation, release notes to changelog-maintenance, decks to presentation-builder, and GTM messaging to marketing-automation.

Docs & Writing544 installs

web-accessibility

akillness/jeo-skills

Routing-first skill for web accessibility remediation and verification. Use when the main job is classifying which accessibility surface is failing — semantics, keyboard/focus, labels/announcements, visual perception/reflow, media alternatives, or routed-app navigation feedback — and turning vague audit, WCAG, axe/Lighthouse, or "make this accessible" requests into one concrete remediation packet. Broad UI critique for hierarchy, polish, and launch readiness belongs here too. Route component API architecture and system governance to design-system, and responsive layout strategy to responsive-design.

Frontend & Design531 installs

Popular docs & writing skills

View category →

grill-with-docs

mattpocock/skills

A relentless interview to sharpen a plan or design, which also creates docs (ADR's and glossary) as we go.

Docs & Writing1.2M installs

lark-markdown

open.feishu.cn

飞书 Markdown:查看、创建、上传、编辑和比较飞书中的原生 Markdown 文件。当用户要操作飞书 Markdown 文件,或比较其远端版本及本地草稿时使用。纯本地 Markdown 文件操作不触发本 skill。不负责将 Markdown 导入为飞书在线文档,也不负责文件搜索、权限、评论、移动、删除等云空间管理操作。

Docs & Writing778.7K installs

writing-beats

mattpocock/skills

Writing, exploit; assemble raw material into a journey of beats, grounding each term before a beat leans on it.

Docs & Writing490.7K installs

writing-shape

mattpocock/skills

Writing, exploit: shape raw material into an article, paragraph by paragraph.

Docs & Writing490.2K installs

writing-fragments

mattpocock/skills

Writing, explore: mine raw fragments, no structure yet.

Docs & Writing489.6K installs

writing-for-agents

mattpocock/skills

Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.

Docs & Writing479.3K installs