What makes Deck Pipeline notable?

1.1K downloads. Trust evidence available

How should Deck Pipeline be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

Deck Pipeline

Production-grade Claude Code system that takes presentation decks from raw Chinese draft to McKinsey-polished English — with full audit trail, layout integri... Skill: Deck Pipeline Owner: tinadu-ai Summary: Production-grade Claude Code system that takes presentation decks from raw Chinese draft to McKinsey-polished English — with full audit trail, layout integri... Tags: bilingual:3.0.0, claude-code:3.0.0, latest:3.0.0, layout-audit:3.0.0, mckinsey:3.0.0, pptx:3.0.0, translation:3.0.0 Version history: v3.0.0 | 2026-05-12T16:33:27.011Z | user Major rewrite from DeckGlobalize

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

1.1k

Updated

Oct 11, 2026

Version

3.0.0

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 1.1K downloads reported by the source. Last updated 10/11/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 11, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 11, 2026
Adoption signal: 1.1K downloadsadoption · observed Oct 11, 2026
Latest release: 3.0.0release · observed May 12, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s178xc11mj68f9c018344m5xw183y7z8:deck-pipeline

Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.
Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-tinadu-ai-deck-pipeline/snapshot"

Documentation

CLAWHUB

64,532 characters of source documentation, loaded on request.

Extracted files

5 files captured from the source.

SKILL.md

---
name: deck-pipeline
description: |
  Production-grade Claude Code system that takes presentation decks from raw
  Chinese draft to McKinsey-polished English — with full audit trail, layout
  integrity checks, and a swappable PROFILE block for project-specific
  defaults. Built on a 4-stage pipeline (Sense Pass → McKinsey Translation →
  Layout Audit → Handoff). Also runs polish-only on any single-language deck.

  TRIGGER when the user:
    • hands over a .pptx containing Chinese and asks for English / translation
    • asks for "deck pipeline", "deck polish", "deck globalizer"
    • asks for layout polish, font cleanup, overflow fixing on any deck
    • asks to update / reverse-sync a bilingual comparison Excel against a deck

  SUPPRESS with "Ignore deck-pipeline".
version: 0.1.0
license: MIT
---

# Deck Pipeline

> **A 4-stage, audit-trailed Chinese→English deck globalization system with a swappable project profile.**

This skill bundles the generic deck-globalization engine (originally upstream
DeckGlobalizer v2.1.1) and an editable PROFILE block (palette, fonts,
glossary, style preferences). The two are **separated** by section so the
profile can be swapped per project / brand without touching the engine.

For a marketing-style overview, see `README.md` in this directory.
For implementation, see `scripts/` and the per-stage runbooks below.

---

## 0. Modes & activation

| Mode | Trigger | Stages |
|---|---|---|
| **Full pipeline** | CN deck (± EN draft) + user wants English output | 1 → 2 → 3 → 4 |
| **Polish-only**   | Single-language deck + "layout / format only / skip translation" | 1 → 3 → 4 |
| **Reverse-sync only** | User hand-edited a PPT after a comparison Excel was generated | 3.5 (sync sub-routine) |

Detect the mode in the first turn. If ambiguous, ask one yes/no question
("This deck is already in EN — should I just polish layout, or also rewrite
McKinsey-style?"). Do not guess silently.

---

## 1. PROFILE block — defaults (swappable)

Edit this block to retarget the skill for your project / brand. Everything
below this block is **profile-agnostic**.

```yaml
PROFILE:
  # ---- L1 Tokens ----
  palette:
    # Replace with your brand colors.
    ink:          "#1A1A1A"
    primary:      "#000000"   # accent / brand primary
    soft:         "#FFFFFF"   # soft fill behind banners
    page_bg:      "#FFFFFF"
  fonts:
    # Choose a serif title face + a sans-serif body face for best contrast.
    title:        "Georgia"
    body:         "Verdana"
    title_bold:   true
  unit_table:
    # Chinese number magnitudes → English. 亿 is 100M, NOT "billion".
    "百万":       "M"
    "千万":       "10M"
    "亿":         "100M"
    "十亿":       "1B"
    "百亿":       "10B"
    "千亿":       "100B"
    "万亿":       "1T"
    # Currency suffix is left to the user — append "$" / "RMB" / "€" as appropriate.

  # ---- L2 Constants ----
  size_ladder:           [22, 14, 10, 8, 6, 4]   # H1, H2, body, caption, footnote, source
  floors:
    body:     7

README.md

# Deck Pipeline · CN→EN · McKinsey Polish · Layout Audit

![version](https://img.shields.io/badge/version-0.1.0-blue)
![license](https://img.shields.io/badge/license-MIT-green)
![python](https://img.shields.io/badge/python-3.9%2B-blue)
![status](https://img.shields.io/badge/status-beta-orange)

> A production-grade Claude Code system for taking decks from raw Chinese draft to McKinsey-polished English — with full audit trail, layout integrity checks, and a swappable PROFILE block for project-specific defaults. Built on a 4-stage pipeline; also runs polish-only on any single-language deck.
>
> 一套生产级 Claude Code 系统，把 deck 从中文原稿做到麦肯锡级英文成稿——全程留痕、排版守护、可替换的项目级 PROFILE 块。基于 4 阶段流水线；也支持纯排版模式，处理任意单语言 deck。

---

## What it does / 做什么

Takes a Chinese deck (and optionally an English draft) and runs it through a 4-stage pipeline. Or, if you give it a single-language deck and ask for layout-only cleanup, skips translation and runs polish stages alone.

Works for any kind of deck — sales, product, research, conference talks, internal reports, whatever.

输入一份中文 deck（可选搭配一版英文草稿），经过 4 阶段流水线。或者，给它一份单语言 deck + 要求"只做排版"，就跳过翻译，只跑排版相关 stage。

| Stage / 阶段 | What happens / 做什么 | Polish-only? |
|---|---|---|
| **1. Sense Pass** | Reverse-engineer design DNA (palette, fonts, size hierarchy) and surface candidate glossary terms.<br>反推设计 DNA（色板、字体、字号梯队），扒出候选术语。 | ✅ runs |
| **2. McKinsey Translation** | CN → EN in McKinsey style from the first pass (top-down, parallel, strong verbs, no filler). Glossary applied inline; unclear terms asked on the spot. Runs **page-by-page** with a checkpoint after each slide.<br>中翻英直接出麦肯锡风格（top-down、平行结构、强动词、去填充词）。术语表 inline 应用；生僻词当场问。**逐页执行**，每页结束 checkpoint 等用户确认。 | ⏭️ skipped |
| **3. Layout Audit** | Font pollution cleanup, overflow estimation, structural-anchor protection, reverse-sync from hand-edits.<br>字体污染清理、溢出估算、结构锚点保护、手动改动反向同步。 | ✅ runs |
| **4. Handoff** | Three or four deliverables + a HANDOFF.md contract for the next session.<br>3–4 件交付物 + 给下一个 session 的 HANDOFF.md 接力契约。 | ✅ runs |

You do **not** need any external skill installed. The generic deck-globalization engine (3-phase visual audit / semantic alignment / page-by-page execution) is bundled inside.

**不需要**安装任何外部 skill。通用 deck 全球化引擎（3 阶段：视觉审计 / 语义对齐 / 逐页执行）已内置。

---

## Install / 安装

```bash
git clone https://github.com/<your-org>/deck-pipeline ~/.claude/skills/deck-pipeline
pip3 install python-pptx openpyxl pymupdf pyyaml
```

The skill is loaded automatically by Claude Code on next start.

下次 Claude Code 启动时会自动加载本 skill。

---

## Modes / 模式

| Mode / 模式 | Trigger / 触发 | Stages run / 跑哪些 stage |
|---|---|---|
| **Full pipeline / 完整流水线** | CN deck (± EN draft) provided, translation requested<br>提供 CN deck（± EN 草稿），要翻译 | 1 → 2 → 3 → 4 |
| **Polish-only / 纯排版** | Single-language deck, "just polish / format only / skip translation"<br>单语言 deck，说"只做排版 / 跳过翻译 / format only" | 1 → 3 → 4 |
| **Reverse-sync only / 反向同步** | User hand-edited PPT after Excel was generated<br>用户在

_meta.json

{
  "ownerId": "kn7c4vnnxm0hrg85thcqxz9h3181tzkd",
  "slug": "deck-pipeline",
  "version": "3.0.0",
  "publishedAt": 1778603607011
}

CHANGELOG.md

# Changelog

All notable changes are documented here.
Format follows [Keep a Changelog](https://keepachangelog.com/).

## [Unreleased]

## [0.1.0] — 2026-05-12

### Added
- Initial public release.
- 4-stage pipeline: Sense Pass → McKinsey Translation → Layout Audit → Handoff.
- Polish-only mode for single-language decks (skips translation).
- Swappable `PROFILE` block (palette, fonts, glossary, style rules, slide-offset config).
- 10 helper scripts:
  - `sense_pass.py` — reverse-engineer design DNA (palette, fonts, size hierarchy).
  - `extract.py` — paragraph-level text extraction.
  - `apply.py` — apply EN edits + write comparison Excel.
  - `layout_audit.py` — font pollution cleanup + font-name suffix audit.
  - `overflow_recheck.py` — overflow estimator with HIGH/MED/LOW tiers.
  - `anchor_detect.py` — cross-page structural-anchor detection.
  - `glossary_audit.py` — late-stage glossary re-scan + wavering detection.
  - `excel_sync.py` — bidirectional PPT ↔ Excel sync, configurable CN↔EN slide alignment.
  - `handoff.py` — HANDOFF.md template writer.
  - `style_distill.py` — distill style fingerprint from a reference PDF/.pptx.
- Page-by-page execution with per-slide user checkpoint.
- Extensible style references (McKinsey baseline; users can layer additional reference samples).
- Bidirectional PPT ↔ Excel sync (ordinal-position + fuzzy fallback).
- Overflow estimator improvements: honors `auto_size`, reads real margins, per-character width by class, greedy word-wrap simulation.
- Font-name suffix audit (`Bold`/`Regular`/`Italic`/`Light` not allowed in `font.name`).
- Structural-anchor cross-page detection (auto per-page compression protection list).
- Discrete `-0.1pt` font compression step; line-spacing fallback (1.25 → 1.15).
- Companion-file lock detection (`~$xxx`).
- Excel three guard-rails (pre-write check, post-write readback, reverse sync).
- HANDOFF.md as a session-end deliverable.
- Bilingual README (English + 中文).

### Sources / credits
- The generic deck-globalization engine is derived from upstream
  **DeckGlobalizer v2.1.1** by tinadu-ai
  (<https://clawhub.ai/tinadu-ai/deckglobalizer>).
  Original three-phase architecture (Visual Audit / Semantic Alignment /
  Page-by-Page Execution) credited and retained.

CONTRIBUTING.md

# Contributing

Thanks for your interest. This is a small, opinionated tool — contributions are welcome but please keep the surface area minimal.

## Reporting issues

Open a GitHub issue with:
- What you ran (command + relevant CLI flags)
- What you expected vs what happened
- A minimal reproduction (a sanitized 1–3 slide `.pptx` is ideal)
- Your environment (Python version, OS, `python-pptx` version)

Do **not** attach decks containing confidential content.

## Pull requests

1. Fork → branch from `main` → PR back into `main`.
2. Keep PRs focused. One concern per PR. Split if needed.
3. Touch the smallest possible surface.
4. Update `CHANGELOG.md` under `[Unreleased]` with a one-line summary.
5. If you change script behavior, update the corresponding section in `SKILL.md` and `README.md`.
6. New scripts must:
- Be runnable standalone via `python3 <script>.py`.
- Print a usage line when called with no args.
- Honor `~$xxx` lock-file checks if they write `.pptx` / `.xlsx`.
- Follow the existing scripts as style references.

## Design principles (please respect)

- **No silent guessing.** When unsure, stop and ask the user (the skill is bidirectional by design).
- **Discrete steps over bulk reductions.** Font compression goes by `-0.1pt`, never `-1pt` shortcuts.
- **Profile-agnostic core.** Anything organization-specific belongs in the `PROFILE` block in `SKILL.md`, never hardcoded in a script.
- **Reverse-syncable.** Excel companion files must support being updated from hand-edited PPTs, not just one-way generation.
- **Don't delete content.** Layout fixes use geometry / line-height / discrete font compression. If those fail, escalate to the user.

## Style references

Adding additional reference samples for style distillation is supported via `style_distill.py` and the `PROFILE.style_references` list. PRs that ship new bundled samples should:
- Use materials that are publicly distributable (no NDA / leaked content).
- Add a note in the `style_references` documentation describing the sample's origin and any usage caveats.

## Code of conduct

Be decent. Disagree on technical substance, not on the person.

Github ReposUpdated 2d agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.