بنقرة واحدة
sc4sap-deep-interview
Socratic deep interview to crystallize SAP requirements before autonomous execution
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
القائمة
Socratic deep interview to crystallize SAP requirements before autonomous execution
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
Reverse-engineer an ABAP program into a Functional/Technical Specification artifact (Markdown or Excel). Socratic scope narrowing from "everything" to "only what the user needs".
Create ABAP programs (Report/CRUD/ALV/Batch) with Main+Include structure, OOP or Procedural, and full agent-driven coding/QA pipeline
Analyze a CBO (Customer Business Object) package — discover frequently-used Z tables / function modules / data elements / classes / structures / table types — and save a per-module / per-package reference file so later `program` / `program-to-spec` runs prefer existing CBO elements over new ones.
ABAP code analysis — delegate source reads + AST/semantic/where-used analysis + rule-based review to sap-code-reviewer, then optionally render a rich briefing via sap-writer
Step-by-step root cause analysis for SAP operational errors. Uses MCP to directly inspect dumps, logs, transports, and where-used relations, then narrows hypotheses with minimal user questions and provides SAP Note search keywords.
Direct operational Q&A with a SAP module consultant agent. Auto-routes the question to the matching sap-{module}-consultant and answers against the configured SAP environment (version, industry, country, active modules).
| name | sc4sap:deep-interview |
| description | Socratic deep interview to crystallize SAP requirements before autonomous execution |
| level | 2 |
| model | haiku |
Follows OMC deep-interview pattern adapted for SAP. Conducts a structured Socratic interview to crystallize SAP development requirements before any code is written. Prevents wasted execution cycles on underspecified ABAP tasks.
<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>
<Use_When>
<Do_Not_Use_When>
/sc4sap:create-object/sc4sap:create-program<SAP_Interview_Dimensions> The interview covers these dimensions until each is resolved:
Object scope: What ABAP objects are needed? (class, interface, program, function module, BAdI implementation, CDS view, RAP business object)
Package and transport: Which development package? New transport or existing? Which system landscape (DEV -> QAS -> PRD)?
Technical pattern: OO class hierarchy? Procedural? RAP/OData? Enhancement spot/BAdI? Which release (ECC vs S/4HANA)?
Integration points: Which SAP modules does this touch? (FI, MM, SD, HCM, etc.) Any BAPIs, RFCs, or IDocs involved?
Data model: Which tables are read/written? Custom Z-tables or standard SAP tables? Authorization objects needed?
Testing requirements: Unit tests needed? Which test classes? Test data strategy? </SAP_Interview_Dimensions>
<Ambiguity_Gating> After each round of questions, score ambiguity 0-10:
Do not proceed to spec generation until score is below 5. </Ambiguity_Gating>
When ambiguity threshold is met: 1. Write validated spec to `.sc4sap/deep-interviews/sap-{timestamp}.md` 2. Spec includes: object list, package, transport strategy, technical pattern, integration points, test requirements 3. Offer: "Spec ready. Proceed with `/sc4sap:create-program` (full program) or `/sc4sap:create-object` (single object)?"Task: {{ARGUMENTS}}