Home / penfick / skills · pptx-penfick/SKILL.md · GitHub

pptx-penfick skillA

pptx-penfick is agent-read markdown (skill) from penfick/skills: Generate PowerPoint decks from a structured JSON outline (page-by-page types, titles, bullets). Use when the user asks to create, build, or export a PPT/PPTX/ 演示文稿/幻灯片/deck/presentation. CLI: pptx-penfick (alias pptskill). Produces local .pptx plus structural QA. Does not invent logos or real product photos..

Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.

What the file says

# pptx-penfick

Deterministic PPT renderer: **JSON outline → `.pptx` + QA**. Agent owns research and outline content; CLI owns layout, CJK fonts, and validity.

> CLI command: **`pptx-penfick`** (alias `pptskill` if installed that way). Requires the CLI package installed (see skill README).

## Iron laws (follow every deck job)

1. **Output only under the current project/workspace** (`cwd` or the project the user named). Never `%USERPROFILE%` / Desktop unless the user asks.
2. **User materials first** — if facts/structure/numbers are provided, do **not** web-search; fill gaps by asking one question or marking 示意.
3. **Never copy facts/numbers/segments/people from example outlines** into another topic. **Do not open `examples/` during generation jobs** when you already know the schema.
4. **Before render**: `pptx-penfick validate` then `pptx-penfick content-check` (use `--expect-pages` when the user asked for N pages; `--allow` only if the topic truly includes a deny term).
5. **Deliver the `.pptx`**: say `PPT 已生成` + absolute path + one-line summary; call `present_files` (or attach) with the `.pptx` first if the host has it. Never end on outline/QA only.
…

Read the whole file at its exact version.

How to install

Latest version
mdr add penfick/skills/pptx-penfick@git:20260920.a8b76cc
Exact content
mdr add penfick/skills/pptx-penfick@sha256:31352414f8fe2e06

Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_e7ggykoqlqgqbegq.svg)](https://markdownregistry.com/a/art_e7ggykoqlqgqbegq)

1 badge views in 30 days

Versions

versioncommittedcommitsizeaudit
git:20260920.a8b76cc latest2026-09-20 a8b76cc 3,917 BA view

Audit of the latest version

A  17 of 17 checks passed. Deterministic, no model, same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (3917 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

penfick/skills · 12 stars · license MIT · pushed 2026-09-20 · branch master

API

GET https://markdownregistry.com/api/v1/artifacts/art_e7ggykoqlqgqbegq
GET https://markdownregistry.com/api/v1/resolve?ref=penfick/skills/pptx-penfick
GET https://markdownregistry.com/api/v1/blob/31352414f8fe2e06975e8d2111eaa8360c968d4d9cfb8387673c5667a45ec5bf

Your agent does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

More from penfick/skills

vision-support skill
penfick/skills · vision-support/SKILL.md · 为非多模态模型(如 deepseek-v4-pro、GLM-5.1、mimo-v2.5-pro 等纯文本模型)提供图片识别能力。当主模型无法识别图片、用户发送了截图/设计稿/UI…
git:20260513.b41a63f · audit A · 12 stars

Every file in penfick/skills

Browse by kind, by grade A, or by owner.