PPT Agent

Generate professional presentations the way you build software — from a one-line request straight to a validated PPTX file.

Stars
★ 926
Last updated
5mo ago
License
NOASSERTION
Primary language
Python

At a glance

How it runs
Agent plugin / skill
Works with
Portable with changes
Cost
Free software; you pay for model usage
Setup effort
Medium · a few setup steps
You'll need
PuppeteerAgent Skill-compatible runtimeShell / CLINetwork accessLocal filesystem
Typical use
A founder needing a 15-page pitch deck fast can give a single line (e.g. "embodied intelligence trends in 2026, dark tech style") and receive dual-format PPTX plus a web preview
Not a fit if
  • Agent platforms without Skill loading support need extra adaptation
  • Teams unwilling to bear the high runtime and token cost of per-page screenshots and LLM visual audits
Maintenance
Commits in the last 6 monthslast commit 2026-06-08

What does this agent do, and when should you use it?

PPT Agent (sunbigfly/ppt-agent-skills) is a code-driven, state-machine-managed multi-agent framework that turns a one-line request into a professional PPTX file. It splits the pipeline into seven stages: interview, branch confirmation, web search or local source compression, narrative outline, global style lock, per-page parallel production (Planning → HTML → Visual QA), and dual-format export — each stage's artifacts are gate-checked before proceeding. Research / Outline / Style / Planning run as isolated subagents with non-overlapping contexts, and every subagent is forced to carry a SUBAGENT_MODEL parameter. Each page first produces a JSON contract validated by planning_validator.py, then renders to HTML, is screenshot automatically, and is audited pixel-by-pixel by an LLM, with overflow fixed by DOM + CSS structural rewriting. The built-in Puppeteer rasterization engine exports both PNG and SVG PPTX files, and all artifacts land in ppt-output/runs/<RUN_ID>/. Distributed as an Agent Skill with no separate deployment, it ships 8 themes, 10 layout types, 13 chart templates, and 15 scripts.

After the user submits a one-line request, the framework executes its state machine: P0 interview produces interview-qa.txt and requirements-interview.txt; P2A web search or P2B local source compression yields search.txt / source-brief.txt; P3 generates outline.txt and P3.5 locks style.json; P4 runs per-page parallel production — Planning (planningN.json validated by planning_validator.py) → HTML rendering (slide-N.html) → screenshot slide-N.png audited by LLM Visual QA, where detected overflow triggers DOM + CSS structural rewriting by a patch subagent; P5 builds preview.html and exports presentation-png.pptx and presentation-svg.pptx, finishing with delivery-manifest.. Execution relies on SKILL.md as the main console (state machine, gates, recovery rules), scripts in scripts/ (validators, harness, exporter), plus visual_qa.py (planning + html dual-layer assertions), subagent_logger.py, and planning_validator.py. Interrupted runs resume statelessly by scanning existing artifacts on disk (outline.txt / style.json / slide-N.png, etc.) to infer the recovery point.

  1. A founder needing a 15-page pitch deck fast can give a single line (e.g. "embodied intelligence trends in 2026, dark tech style") and receive dual-format PPTX plus a web preview
  2. A consultant who compresses local reports into decks can use the P2B local source compression branch to distill documents before per-page generation
  3. A content team sensitive to layout quality can rely on the pixel-level Visual QA loop to eliminate overflow, overlap, and hallucination issues
  4. An operations staffer producing structured decks with charts can reuse the 13 chart templates and 10 layout types directly
  5. A technical user who wants auditability can use subagent_logger.py stage commands and run logs to replay and redo from checkpoints

Key setup facts

Pulled from the install and usage notes below. The project README has the current values.

Environment variables
RUN_ID

How do you install or deploy this agent?

Run in a terminal: npx skills add sunbigfly/ppt-agent-skills. The project runs as an Agent Skill and needs no standalone deployment; the README does not list system dependencies (Node.js version, browser requirements) beyond this install command, so verify against the repository scripts.

How do you use this agent?

After installing, enter a natural-language request in any Skill-capable agent environment, e.g.: "Generate a 15-page pitch deck on embodied intelligence trends in 2026, dark tech style." The framework runs all seven stages (P0–P5) automatically; all outputs (preview.html, presentation-png.pptx, presentation-svg.pptx, and intermediate contract files) are written to ppt-output/runs/<RUN_ID>/.

What are this agent's strengths and limitations?

Pros
  • Subagent stage isolation keeps Research / Outline / Style / Planning contexts uncontaminated, and SUBAGENT_MODEL is mandatory per subagent to prevent silent fallback
  • Pixel-level Visual QA loop: each page is screenshot and audited by an LLM; detected overflow is fixed via DOM + CSS structural rewriting rather than spacing tweaks, addressing root causes of overlap and layout chaos
  • Data/render separation: JSON contracts pass planning_validator.py before driving HTML rendering, with an html-level physical structure detector blocking non-conforming skeletons
  • Stateless checkpoint recovery: interrupts resume by scanning existing artifacts on disk; a failed step rolls back only that step, not other pages
  • Dual-engine export: PNG raster stream guarantees cross-platform visual fidelity; SVG vector stream keeps fonts editable; the Puppeteer engine uses event hooks (document.fonts.ready) for hard-delay-free screenshots
Limitations
  • Requires an agent environment that supports Skill loading; platforms without Skill support need extra adaptation, and the README offers no standalone deployment path
  • Subagents must have SUBAGENT_MODEL set with no default fallback, so users must configure model access and bear LLM call costs
  • The multi-stage pipeline — per-page screenshots plus LLM visual audits — carries high execution time and token consumption
  • The GitHub License field is NOASSERTION; although README badges say MIT, verify the LICENSE file before adopting
  • Install docs omit concrete runtime requirements (Node.js version, browser dependencies); validate your environment before deployment

How does this agent compare with similar options?

Key facts side by side with the most closely related agents.

Agent Source review Form / cost Stars Updated Language Full support on
PPT Agent This agent 51 · Major gaps Agent plugin / skillFree + model costs ★ 926 5mo ago Python —
PPT Master — AI-native PowerPoint generation 70 · Some gaps Agent plugin / skillFree + model costs ★ 79k 1d ago Python Claude Code
OfficeCLI 62 · Some gaps CLIFree ★ 33k 1d ago C# Codex · Claude Code
Kineo (Kineo AI) 34 · Major gaps — ★ 137 5d ago TypeScript —

How does FollowAgents rate this agent?

FollowAgents source review · FARS-2.1
Major gaps
51/ 100 5-point scale 2.6 / 5
Trust 13/29
Reliability 8/14
Adaptability 10/18
Convention 10/18
Effectiveness 7/13
Verifiability 3/8
Why each dimension lost points
Trust13 / 29 · 2.2/5

SKILL.md requires a Step 0 interview, branch confirmation, manual audit gates, and isolated subagents; the artifact chain and per step outputs make data flow and rollback reasonably explicit. Deductions: these are mostly procedural requirements, with no concrete permission inventory, sensitive data rules, dependency pinning, or security review guidance. The scope of web research and script side effects is also not well bounded. The license names sunbigfly, but identity is unverified and no more specific source attribution policy is shown.

Reliability8 / 14 · 2.9/5

The documents define a fixed sequence, gates, validator rechecks, and retry or rollback behavior, giving the workflow reasonable internal structure; the README also describes artifact based recovery and visual QA. Deductions: the README's feature and performance claims are not corroborated by implementation evidence in this sample, dependency availability is lightly documented, and concrete failure messages or dependency failure handling are not shown.

Adaptability10 / 18 · 2.8/5

SKILL.md covers Chinese and English presentation requests, document to deck conversion, pitches, training, and redesign of existing slides; it also describes web or local source branches, image modes, and manual review. Deductions: the trigger language includes broad implicit intents and may over-trigger; environment fit depends on CLI and subagent capabilities, but the sample provides no compatibility matrix.

Convention10 / 18 · 2.8/5

The README has a clear workflow, artifact chain, repository map, quick start, example request, and update note, while SKILL.md is organized by stages. Deductions: installation guidance is mostly a single npx command, limitations and FAQ coverage are sparse, and although a version and date are shown, only one update entry is present. The license provides MIT text, but metadata says NOASSERTION; maintenance responsibility is not described beyond the copyright name, with no maintainer or update channel identified.

Effectiveness7 / 13 · 2.7/5

The product has a clear goal and deliverables, including HTML preview and PNG/SVG PPTX exports; staged planning, validation, and visual review indicate potential value beyond one shot generation. Deductions: quality, speed, and cross platform claims are mainly project assertions in the supplied material, with little comparative evidence, and the cost of the multi agent and rendering pipeline is not discussed.

Verifiability3 / 8 · 1.9/5

The README and SKILL.md make workflow, artifacts, gates, and validation responsibilities traceable, and the license text is directly inspectable. Deductions: the sample contains no main scripts, validator, or tests to corroborate those descriptions; claims such as automatic screenshots, structural assertions, and checkpoint recovery remain documentation claims that cannot be checked against the supplied sources. The rationale therefore distinguishes explicit file content from uncorroborated outcome claims.

Risks and how to mitigate them
  • The README's pixel level visual QA, automatic recovery, cross platform fidelity, and fast screenshot claims are not corroborated by implementation code in the supplied sample and should be treated as project claims, not verified capabilities.
  • The workflow may search the web, read user supplied materials, and write HTML, images, and PPTX files to disk; users should review inputs and the output directory, since the sample does not explain boundaries for handling sensitive local content.
  • The license file contains MIT terms, while the supplied license metadata is NOASSERTION; verify the repository's actual licensing status before publishing or redistributing.
Evidence confidence: Low Reviewed Nov 08, 2026 Reviewed revision 13e353776d0b
Review evidence README.mdSKILL.mdLICENSE
See the full review method →
Maintain this project? Add the FARS badge to your README

The badge shows the current review score and verdict and links back to this page. It refreshes about once an hour after a re-review.

FARS

[![FARS review](https://followagents.com/badge/ppt-agent-skills.svg)](https://followagents.com/en/agents/ppt-agent-skills)
<a href="https://followagents.com/en/agents/ppt-agent-skills"><img src="https://followagents.com/badge/ppt-agent-skills.svg" alt="FARS review"></a>

FAQ

Do I need to deploy a standalone service?
No. The project runs as an Agent Skill: install with npx skills add sunbigfly/ppt-agent-skills and trigger it directly from any Skill-capable agent environment.
What happens if generation is interrupted?
The framework is stateless and stores no progress files. Re-running scans existing artifacts on disk (outline.txt / style.json / slide-N.png, etc.) to infer the recovery point; a failed step rolls back only itself.
What guarantees layout quality?
Each page is screenshot and audited pixel-level by an LLM after HTML build; page density becomes a verifiable constraint via density_bias and density_label / density_contract; visual_qa.py also enforces planning + html dual-layer assertions on structure and decoration budgets.
What output formats are produced?
Dual-engine export: presentation-png.pptx (raster, 100% cross-platform visual fidelity) and presentation-svg.pptx (vector with independently editable fonts), plus preview.html and delivery-manifest..
What is the license?
README badges and the footer state MIT, but the GitHub License field shows NOASSERTION — check the LICENSE file before formal adoption.
Is PPT Agent free?
The software is free, but PPT Agent calls an AI model, and you pay that model provider for usage (or run a local model).
Is PPT Agent safe to use?
FollowAgents' FARS review (Nov 08, 2026) scored PPT Agent 13/29 on trust and safety. None of the eight safety controls the review checks for was missing outright.
Is PPT Agent still maintained?
Development has slowed: the latest commit on GitHub is from 2026-06-08, within the last six months but not the last 30 days.
Who makes PPT Agent?
PPT Agent is published on GitHub by the account sunbigfly. FollowAgents has not verified which person or company is behind that account.
Was this page helpful?
View on GitHub ↗ Install ↓

Related concepts