Interface Mapping Spec logo

Interface Mapping Spec

Community
babamba2
interface-mapping-spec

Write an interface mapping specification as one editable HTML page in the classic template layout — cover, revision history, header, Source → Target field grid with conversion rules and MAPPING, optional synchronous response block, extraction condition, field guide. SAP side read from DDIC (table, structure, view, function module) or, for new interfaces, from a field list or the module consultant's proposal; non-SAP side proposed; in-page checks; versioned; English companion.

Overview

Publisherbabamba2
Repositorysuperclaude-for-sap
Skill nameinterface-mapping-spec
Stars
69
Forks
26
Bundled files
2
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.

  • 2 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

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

Installation

Install the Interface Mapping Spec 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/interface-mapping-spec
  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/interface-mapping-spec .claude/skills/interface-mapping-spec
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Interface Mapping Spec 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 Interface Mapping Spec 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 Interface Mapping Spec 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 Interface Mapping Specification

Interviews the consultant briefly and writes one editable HTML page per interface: cover, revision history, the mapping sheet (header, systems, Source → Target grid with R / MAPPING columns, response block for synchronous interfaces, conversion rules, extraction condition, remarks) and the field guide. The SAP side comes from the system; the other side is proposed and corrected in the page.

<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.</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>

<Phase_Banner>Before each Agent(...) dispatch, emit ▶ phase=<id> (<label>) · agent=<name> · model=<Opus|Sonnet|Haiku> per ../../common/model-routing-rule.md § Phase Banner Convention. Resolve the dispatch mode first per ../../common/model-dispatch-mode.md.</Phase_Banner>

<Team_Mode>No teamMode integration. Reading SAP, proposing and building are scripted; agents only propose fields (optional) and translate.</Team_Mode>

<Use_When>

  • "인터페이스 매핑 정의서", "매핑 스펙", "interface mapping spec", "I/F 정의서", "EAI 매핑", "field mapping for interface "
  • A new interface must be specified before development (the usual case)
  • An existing RFC / proxy structure / Z table needs its mapping written down
  • An edited page comes back (import), or the SAP structure changed (refresh) </Use_When>

<Do_Not_Use_When>

  • Specification of a program → /sc4sap:program-to-spec
  • Creating the Z structure / RFC itself → /sc4sap:create-object (this skill hands it the field list, Step 8)
  • An interface catalogue across many interfaces — one interface per document </Do_Not_Use_When>

<Decisions_Fixed> Settled with the user when the skill was designed — do not ask again:

TopicDecision
OutputEditable HTML only (no .xlsx); one interface per document; one page with an optional response block (B01…) for synchronous interfaces
SAP sideRead from SAP (DDIC table / DB view / structure — a proxy by its structure —, CDS by SQL view name, function module signature). New interfaces: a TABLE-FIELD / data-element list, the module consultant's proposal (checked against DDIC), Excel paste in the page, or an empty grid
CarriersThe grid is split by ▸ group rows — the unit the fields travel in, per side: name, kind (PARAMETER / STRUCTURE / TABLE), occurrence (0:1 … 1:N). A row's Table column holds only the source DDIC table. The system block's Structure / occurrence is the read-only summary of the groups. FM: scalar parameters of one direction share one PARAMETER group; each structure / table parameter is its own group
ColoursSource side blue, target side green — header, system block and grid cells
SAP typesShown as DB types of the code list (NUMC → NUMBER, DATS → DATE …); the DDIC type is the cell tooltip
Other sideProposed (same names, DB types, MAPPING 1:1), marked "Proposal" until edited or confirmed
Conversion rulesProposed from the SAP types (date, time, leading zeros / ALPHA, currency, quantity / unit) and linked in the R column
ChecksEmpty required (*) items, MAPPING to a missing row, unknown R id, size truncation, type-family mismatch, unmapped target field, key mismatch — all in the page's Checks panel
Versionsv0.1 → +0.1 per saved / imported edit, per refresh with changes; the revision-history table fills itself (author, change, optional approver)
LanguagePage language from .sc4sap/config.json (language, else ko); English companion always built unless the user opts out
Settings<base>/interfaces/project.json: cover (project name, title, document-number pattern IF-MAP-{ifId}, copyright), idPattern for IF ID numbering, code-list overrides (codes)
File namePage: <IF_ID>_<OBJECT>_<interface name>-v<ver>-<lang>.html (SAP object of the SAP side, else the object typed in the system block; empty parts left out). The model json stays <IF_ID>-v<ver>-<lang>.json
Location<base>/interfaces/<IF_ID>/ — <base> per ../../common/multi-profile-artifact-resolution.md (.sc4sap/work/<alias>/ with an active profile)
Template contentGeneric: never put customer, vendor or people names into the skill or into public docs; real names belong only in the user's project.json and documents
</Decisions_Fixed>

Entry check. If the user hands back an edited page → Step 6. "Refresh / SAP changed" → Step 7. "Z structure / create the RFC" → Step 8. Otherwise a new document: Steps 1–5.

Step 1 — Preflight and project settings. Confirm the active profile in one line. If <base>/interfaces/project.json is missing, ask once (MUST read interview.md § Project) and Write it.

Step 2 — Interview. MUST read interview.md § Interface. One AskUserQuestion round (scenario preset, where the SAP fields come from, IF ID), then one short free-text ask for name, summary, systems and the SAP object or field list. Unanswered items stay empty — the page highlights them; do not chase every field in chat.

Step 3 — Field proposal (only when the user chose "describe the business"). Dispatch the module consultant with dispatch-prompts.md § 1. Show the returned TABLE-FIELD list with one reason each and ask the user to confirm or trim it in one message; the confirmed list becomes fields.

Step 4 — Build v0.1. Write the answers to <base>/interfaces/_answers/<IF_ID>.json (shape in interview.md § Answers), then <B> init --answers <file>. Report problems (fields SAP does not have, unreadable parameter types — for those offer --line PARAM=STRUCTURE and refresh).

Step 4a — Korean polish (page language ko). Per common/humanize-korean.md, <dir> = <base>/interfaces/<IF_ID>/_humanize: texts = node scripts/lib/humanize.mjs texts-json <base>/interfaces/<IF_ID>/<IF_ID>-v<ver>-ko.json --skip desc,ddic,dom --out <dir>/texts.json (latest version; desc / ddic are SAP's DDIC texts), apply = node scripts/lib/humanize.mjs apply-json <dir>/texts.json <dir>/humanized.json (or fixed.json), then <B> build --if <IF_ID>. Runs again after an import or refresh that adds prose.

Step 5 — English companion. Skip when the page language is en or the user opted out. <B> texts --if <ID> --to en → when todo > 0, dispatch sc4sap:sap-writer with dispatch-prompts.md § 2 to write outFile; then <B> companion --if <ID> --to en. missing must be empty.

Step 6 — Import an edited page. <B> import <file> → new version with the reader's revision row; hand-typed SAP fields (EKPO-MATNR, data elements) are filled from DDIC at the same time (resolved, problems). Refusals: version already imported; the page was edited from an older version (--force only when the user says to overwrite); an English companion page (edits go into the primary-language page, the companion is rebuilt from it); a page whose ID / version / language was changed outside edit mode. Then Step 5 again.

Step 7 — Refresh from SAP. <B> refresh --if <ID> [--line PARAM=STRUCTURE] → unchanged: true, or a new version with added / changed / removed fields marked in the grid and a revision row. Only SAP facts (type, length, DDIC type) are updated; key, null and descriptions the user wrote stay. --line values are remembered for later refreshes. Then Step 5 again.

Step 8 — Hand-off to create-object (on request, or offered once the user says the mapping is agreed). <B> fields --if <ID> lists the SAP-side fields with data elements; offer /sc4sap:create-object for a Z structure (proxy / RFC) built from that list. Never create SAP objects from this skill.

Close. Report in the user's language: page path(s), version, findings (errors / warnings / to confirm) with the first few error texts, problems, and the next steps: open the page → Edit → Save → hand the file back for import.

<MCP_Tools_Used> Through the scripts only: GetTable, GetStructure, GetView, GetDataElement, GetTypeInfo, SearchObject, GetFunctionModule — DDIC metadata and source, never table contents. </MCP_Tools_Used>

Task: $ARGUMENTS

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Interface Mapping Spec AI skill do?

Write an interface mapping specification as one editable HTML page in the classic template layout — cover, revision history, header, Source → Target field grid with conversion rules and MAPPING, optional synchronous response block, extraction condition, field guide. SAP side read from DDIC (table, structure, view, function module) or, for new interfaces, from a field list or the module consultant's proposal; non-SAP side proposed; in-page checks; versioned; English companion.

Why use Interface Mapping Spec on TypingMind?

Because you install it once and use it with any model. Interface Mapping Spec 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 Interface Mapping Spec in TypingMind?

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

Which AI models can use Interface Mapping Spec?

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 Interface Mapping Spec?

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

Is the Interface Mapping Spec 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 👇