Smartform Preview logo

Smartform Preview

Community
babamba2
smartform-preview

Draw the expected print of a SmartForm as a JPG (plus the HTML it is drawn from) — windows at their real mm positions, SmartStyle fonts, template / table grids with borders and shading, SE78 graphics such as logos and signatures, loops with sample rows — with invented sample values in place of the &fields&, sized to the real field types. Reports the cells and windows whose content gets cut off.

Overview

Publisherbabamba2
Repositorysuperclaude-for-sap
Skill namesmartform-preview
Stars
69
Forks
26
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by babamba2 on GitHub. Read the source before you install it.

Installation

Install the Smartform Preview AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/babamba2/superclaude-for-sap/tree/main/skills/smartform-preview
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/babamba2/superclaude-for-sap.git /tmp/superclaude-for-sap
mkdir -p .claude/skills
cp -r /tmp/superclaude-for-sap/skills/smartform-preview .claude/skills/smartform-preview
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Smartform Preview in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Smartform Preview on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Smartform Preview is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

SC4SAP SmartForm → Print Preview

Reads one SmartForm from the connected system and draws what a printed page will look like, without running the print program: one JPG and one HTML page (A4 in mm). Field symbols (&HEADER-NAME1&) are filled with invented sample values that fit the field types read from the DDIC, so the picture shows realistic widths — and the places where the form cuts text off.

<Response_Prefix>Every response triggered by this skill MUST begin with [Model: <main-model> · Dispatched: <sub-summary>] per ../../common/model-routing-rule.md § Response Prefix Convention. This skill dispatches no agents (Dispatched: none).</Response_Prefix> <Target_Object>The target object is looked up on the active profile's system only. Not found → stop and ask per ../../common/multi-profile-artifact-resolution.md § Target object not on the active system — never substitute a similar name, never switch profiles on your own.</Target_Object>

<Team_Mode>No teamMode integration. Reading and drawing are scripted; the main thread writes the sample values.</Team_Mode>

<Use_When>

  • "SmartForm preview", "what does this form print", "expected output of ZXX_FORM", "스마트폼 미리보기", "출력물 예상 이미지", "スマートフォームのプレビュー"
  • A spec or test case needs a picture of the form output
  • Before / after a layout change of a form </Use_When>

<Do_Not_Use_When>

  • The user wants to change the form — this skill is read-only; SmartForm editing is not supported
  • SAPscript forms (SE71) or Adobe forms (SFP) — only SmartForms
  • The user wants the output with real document data — refuse (see Data_Rules) and offer invented values </Do_Not_Use_When>

<Decisions_Fixed>

TopicDecision
SourceMCP GetSmartFormContent (active version, logon language) → <form>.content.json in the MCP output directory
ValuesInvented by the main thread from the field types (GetStructure / GetDataElement / GetTable), never read from documents
Loops / tables3 sample rows unless the user asks for more; a row count that overflows MAIN shows where the page would break
PagesFirst page; firstPage / lastPage windows all shown (one-page document)
Cut-off textDrawn cut off, as SAP prints it (cell clips, no wrap); listed in the report
Borders / shadingAs stored in the form — gaps in borders are real
Output<artifact-base>/smartforms/<FORM>/<FORM>-preview.{jpg,html} + values.json (artifact base per ../../common/multi-profile-artifact-resolution.md)
</Decisions_Fixed>

Step 1 — Target. Form name from ARGUMENTS; if missing ask once. Uppercase it.

Step 2 — Read the form. GetSmartFormContent(form_name, summary: true) — the summary lists windows, data declarations, symbols, graphics, styles and files.content (the full result on disk). Read only the summary; never load the content file into the conversation.

  • graphics[].error or dynamicReferences (keys set at print time) → the drawing shows a box there; say so in the result.
  • If <out>/values.json exists from an earlier run, offer to reuse it (Recommended) or write new values.

Step 3 — Where each symbol prints.

node scripts/smartform/build-preview.mjs symbols "<content>"

→ per symbol: its declaration (HEADER → type ZXX_S_HEAD), every place it prints (window, paragraph, font pt, cell width mm, in a loop or not).

Step 4 — Field types. For every declaration type behind a symbol: GetStructure (structures, table lines), GetDataElement (single fields such as CHAR100, STCEG); GetTable when the type is a table. Parallel calls. Keep per field: data type, length, decimals, description.

Step 5 — Sample values → write <out>/values.json with the Write tool:

json
{ "form": "ZXX_FORM", "defaultParagraph": "AA", "rows": 3,
  "values": { "HEADER-NAME1": "Northwind Trading Co., Ltd.",
              "GS_ITEM-MATNR": ["100234", "100235", "100512"] } }
  • Write values as printed: dates and numbers in the user's format (country file / config.json → country; KR / US style 1,250.000, DE style 1.250,000), currency amounts with their decimals, units as their external code.
  • Numbers (CURR / QUAN / DEC / INT / P) print right-justified in their output length — pad with leading blanks (QUAN 13,3 → 17 characters: " 12.500") unless the symbol has a length or (C) option. Signed fields (CURR, signed DEC) end with the sign position: a blank when positive (" 1,234.56 "), - when negative. In a narrow cell the blanks wrap the number onto a second line that a fixed-height row cuts off — SAP prints the cell empty, and so must the preview.
  • A variable the form's code sets differently in one place (a footer total in a loop's last event) takes a value for that text node only: "L_WRBTR@%TEXT59": "99,999.96" wins over "L_WRBTR": [...].
  • A dynamic text node (text type D, REF_NAME &GV_TEXT&) prints a text table: give its lines, "GV_TEXT": ["First line", {"TDFORMAT": "", "TDLINE": "continued"}] (a string = a * line; a blank TDFORMAT continues the paragraph). One text per loop row = an array of such arrays.
  • Realistic lengths: names and texts typically 50–90 % of the field length; keys at their usual length (4500001234, 0010004567). A symbol inside a loop or table gets an array, one value per row; totals add up.
  • Values hang together: same buyer in buyer and ship-to when the form implies it, item amounts = quantity × price, a total that matches.
  • defaultParagraph: the paragraph for lines formatted * (the style's standard paragraph is not in the content). Take the paragraph of the neighbouring label of the same kind (e.g. the title cell next to it); say which one in the result. Keep the choice in values.json for later runs.
  • System symbols (SFSY-PAGE, SFSY-FORMPAGES) default to 1; set them only for a different picture.

Step 6 — Build.

node scripts/smartform/build-preview.mjs build "<content>" --values "<out>/values.json" --out-dir "<out>" [--rows N] [--mark]

--mark tints the sample values yellow (for review); unfilled symbols always show as blue &NAME& placeholders. The JSON report lists filled, unfilled, overflow (cells / windows whose content does not fit), approximations and the defaultParagraph used.

Step 7 — Check and show. Read the JPG and look at it before answering: overlapping windows, empty windows, missing graphics, symbols left blue. Fix values.json and rebuild for value problems; report layout findings — never "fix" the form's layout in the drawing.

<Data_Rules> Only the form definition, styles, graphics and DDIC metadata are read. Sample values are invented — never business data, never real customer, vendor or company names, never real tax numbers or addresses of real parties. Do not call GetTableContents / GetSqlQuery to fill the form; a request for "the real output of document X" is refused: say the preview uses invented values and the real output comes from the print program (e.g. the output type's processing program or SMARTFORMS test). </Data_Rules>

<Output_Format>

SmartForm preview: ZXX_FORM  (page %PAGE1, A4 portrait)
Windows: 7 · Graphics: 2 (logo, signature) · Symbols: 30 filled, 0 left blank · Sample rows: 3
Cut off as printed (4): "Purchase Order No." (%TEXT24), "(Unit)" (%TEXT45, %TEXT50), …
Window overflow: %WINDOW4 — graphic 27.2 mm in a 25 mm window
Standard paragraph: AA assumed for '*' lines
JPG:  .sc4sap/work/DEV/smartforms/ZXX_FORM/ZXX_FORM-preview.jpg
HTML: .sc4sap/work/DEV/smartforms/ZXX_FORM/ZXX_FORM-preview.html
Values: .sc4sap/work/DEV/smartforms/ZXX_FORM/values.json

Next: "10 rows", "other values", "mark the sample values", "show the second page"

Reply in the user's language; show the JPG to the user when the client can display images. </Output_Format>

<MCP_Tools_Used>

  • GetSmartFormContent (summary: true)
  • GetStructure, GetDataElement, GetTable, GetDomain (field types only) </MCP_Tools_Used>

<Related_Skills>

  • /sc4sap:program-to-spec — the print program's specification (attach the preview as expected output)
  • /sc4sap:program-to-manual — user manual of the print program </Related_Skills>

Task: $ARGUMENTS

Frequently asked questions

What does the Smartform Preview AI skill do?

Draw the expected print of a SmartForm as a JPG (plus the HTML it is drawn from) — windows at their real mm positions, SmartStyle fonts, template / table grids with borders and shading, SE78 graphics such as logos and signatures, loops with sample rows — with invented sample values in place of the &fields&, sized to the real field types. Reports the cells and windows whose content gets cut off.

Why use Smartform Preview on TypingMind?

Because you install it once and use it with any model. Smartform Preview is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Smartform Preview in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/babamba2/superclaude-for-sap/tree/main/skills/smartform-preview. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Smartform Preview?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Smartform Preview?

As many as you like. As long as a model supports skills, you can use Smartform Preview with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Smartform Preview AI skill free?

Yes. It is published on GitHub by babamba2 under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇