Productivity & Collaboration pptx-generationhtml-to-pptxmulti-agentvisual-qapitch-deckslide-generatorpythonpuppeteer

PPT Agent

Generate professional presentations like software engineering: a multi-subagent pipeline with pixel-level visual QA that turns one sentence into a deliverable PPTX.

FollowSkills review · FSRS-2.0
Use with care
53/ 100 5-point scale 2.7 / 5
1 2 3 4 5 6
1Trust15 / 25 · 3.0/5

SKILL.md shows substantial safety design: subagent context isolation, output confined to relative paths, mandatory WAIT_USER confirmation points, forced manual-audit release gates, and prohibition on the main agent editing formal artifacts. Deducted: reliance on web search and Puppeteer with undisclosed dependency/security posture; prompt templates and scripts are absent from evidence so data-flow transparency is only partially confirmable; no explicit overall rollback/cleanup mechanism.

2Reliability10 / 20 · 2.5/5

High internal self-consistency at the documentation level: Gate validators, retry/rollback, and checkpoint-recovery rules are complete and coherent. Deducted: all key paths depend on scripts/*.py and references/ files that are not provided, so no command can be statically reproduced; the 'scripts are black boxes, never read them' rule shifts debugging cost to the user on interface mismatch; no test or CI evidence, and the static ceiling of 10 applies.

3Adaptability9 / 15 · 3.0/5

Target scenario is clear (Chinese-language end-to-end PPT generation), environment sensing and degradation strategies are specified, Chinese support is good. Deducted: the frontmatter trigger description is excessively broad ('beautify', 'visualize data', implicit intents all trigger), creating false-trigger risk; non-fit boundaries are weakly declared; heavy dependence on a CLI that must support subagent creation and model override, sharply reducing availability elsewhere.

4Convention10 / 15 · 3.3/5

Versioning (v4.1 / 2026.04.09), changelog, MIT LICENSE, directory layout, and single-source indices are clear and consistently named. Deducted: repository license metadata is NOASSERTION, inconsistent with LICENSE; publisher unverified with no maintenance commitment or update path; the '2026-04-09' date is anomalous; critical files (cheatsheet, templates) are absent so maintainability cannot be fully confirmed.

5Effectiveness6 / 15 · 2.0/5

Claims to turn a one-line request into directly usable PPTX, which would be high marginal value. Deducted: no statically verifiable output evidence (screenshot assets not included in evidence); the process is very heavy—multiple subagents, many user waits, high token cost—so cost/benefit is questionable; the core value claim rests on author statements, and the static ceiling is below 7.

6Verifiability3 / 10 · 1.5/5

Versioned changelog, artifact chain, and Gate design provide auditable internal consistency. Deducted: no CI workflow, no committed test suite, no third-party execution evidence; README marketing claims ('zero dropped fonts', 'pixel-level') are unverifiable; showcase images are not in the evidence and fact/marketing are not separated.

Evidence confidence:Low Reviewed Sep 10, 2026 Reviewed revision 13e353776d0b
Before you use it
  • Core scripts and template files were not in the reviewed evidence; none of the Gates or commands have been execution-verified, so real-world usability is unknown.
  • Trigger conditions are over-broad; the skill may falsely activate on mere beautification or data-visualization requests and launch a very heavy multi-agent pipeline.
  • Depends on web search and Puppeteer rendering; security and network reachability (especially from mainland China) are unverified.
  • License metadata is NOASSERTION, inconsistent with the MIT LICENSE file; verify via the install channel.
  • Token and time costs are high, and output-quality claims are author statements only; run a small pilot before production use.
Review evidence [1][2][3][4]
See the full review method →

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

PPT Agent (v4.1) is a code-driven, fully automated presentation generation framework that orchestrates multiple subagents via a strict state machine. It splits deck production into seven stages — interview, branch confirmation, research/source compression, outline, style lock, per-page parallel production (Planning → HTML → Visual QA), and dual-format export — with each stage's artifacts validated by gates before proceeding. Pages render HTML only after passing a validated JSON planning contract, then get screenshotted and visually audited, with structural DOM+CSS rewrites to fix overflow, addressing the hallucination, overlap, and layout chaos typical of LLM-generated slides. Final deliverables are a web preview plus PNG and SVG PPTX exports.

Reads user interview answers and local files (or performs web research), generates subagent prompts from templates via prompt_harness.py, and dispatches ResearchSynth / SourceSynth / Outline / Style / PageAgent subagents to produce search-brief.txt, outline.txt, style., planningN., and slide-N.html. It runs two-layer validation with contract_validator, planning_validator, and visual_qa.py; after each page's HTML renders, it screenshots the page and has a subagent rewrite DOM+CSS to eliminate layout conflicts. Finally, a Puppeteer-based rasterization engine exports preview.html, presentation-png.pptx, presentation-svg.pptx, and delivery-manifest. into ppt-output/runs/<RUN_ID>/.

  1. Professionals who need a structured report for their boss — a single sentence like 'make me a deck about X' triggers the full pipeline
  2. Founders building an investor pitch deck, e.g. a 15-page dark tech-style roadshow presentation
  3. Teams with existing doc/excel/pdf/pptx material who want it converted into a deck, or just beautified/restructured
  4. Trainers generating multi-page courseware who want to personally review key pages via the manual audit mode
  5. Interrupted tasks: supply the RUN_ID and the framework scans on-disk artifacts to infer the resume point and continue

What are this skill's strengths and limitations?

Pros
  • Stage-isolated subagents keep contexts uncontaminated; models are explicitly pinned to prevent silent downgrade
  • Data/render layer separation: planning JSON passes validation before HTML renders, so bad structure is caught early
  • Pixel-level Visual QA loop: screenshots are audited and fixed via DOM+CSS rewrites, not spacing nudges
  • Stateless checkpoint recovery: trusts only disk artifacts and gate checks, resumable across conversations
  • Dual PPTX export: PNG pipeline for pixel-perfect fidelity, SVG pipeline with editable fonts
Limitations
  • GitHub license field is NOASSERTION (README says MIT) — an inconsistency to verify before adoption
  • Heavy runtime requirements: Python, a screenshot engine, and subagent-creation capability; bare model APIs won't run it directly
  • The 7-stage pipeline with mandatory interview and multiple gates is overkill for small tasks; dead subagents force full page reruns
  • Blocked pages require human adjudication — long runs need someone watching
  • No test suite or cross-platform compatibility evidence in the source; output quality depends on the chosen model

How do you install this skill?

Run npx skills add sunbigfly/ppt-agent-skills to install the skill into an Agent Skills-compatible agent environment. The repo contains SKILL.md (main console), scripts/ (validators, harness, exporters), references/ (playbooks, styles, layouts, charts, blocks), and assets/. Ensure the environment has Python 3 and a working screenshot/Puppeteer engine; the research branch also needs web search tooling.

How do you use this skill?

Trigger it with natural language in any Skill-capable agent environment, e.g.: "Create a 15-page pitch deck on embodied intelligence trends for 2026, dark tech style." The flow starts with a mandatory interview (Step 0) covering audience, page density, image policy, subagent model and thinking effort, and whether manual audit is on; then the P0→P5 pipeline runs, writing all outputs to ppt-output/runs/<RUN_ID>/. Exact CLI parameters live in the repo's cli-cheatsheet.md (not enumerated in the source material).

FAQ

Does it need internet access?
Not necessarily. The Research branch (P2A) relies on web search; if you don't need expanded research, the non-Research branch (P2B) works with local material only — though you still need a local environment that can run scripts and take screenshots.
Can I intervene and revise a page?
Yes. With manual audit mode enabled, the review stage has a mandatory checkpoint: the main agent shows slide-N.png and waits for an explicit pass/fail. A fail reopens PagePatchAgent from the review stage; the main agent never hand-edits artifacts.
What happens if the task gets interrupted?
The framework is stateless: say 'continue' with your RUN_ID (or use the latest run directory) and it scans disk artifacts in order — delivery-manifest → planning → style → outline → brief → requirements — to find the highest passed gate, then resumes from the next step.
What if a page keeps failing?
Two consecutive non-converging rounds of the same issue force a fallback to planning to rewrite budgets; three consecutive failures mark the page BLOCKED. The agent skips it, finishes other pages, then reports back for you to choose manual fix, simplified retry, or skip — it never silently drops pages.

Related skills