[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M73CJNGSDTH5CFJJD7EXDJ08":3,"skill-same:01M73CJNGSDTH5CFJJD7EXDJ08":84},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":62,"commitSha":63,"skillDirectory":64,"forksCount":65,"repositoryHtmlUrl":66,"repositoryHomepageUrl":6,"ownerHtmlUrl":67,"ownerBlogUrl":6,"ownerDescription":68,"updatedAt":69,"install":70,"resources":83},"01M73CJNGSDTH5CFJJD7EXDJ08","abap-dev",null,"Use when working on SAP ABAP development tasks — provides specialized workflows for BAPI exploration, transport management, unit testing, performance analysis, impact architecture analysis, and documentation audits. Trigger on any SAP\u002FABAP coding, debugging, or system analysis task.","5throck\u002Fai-workspace-standards","5throck","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F10958964?v=4","01M73BFEH0V0VS483TW4JD49JW","01M73BFEJ5VQZJHJSFTVPAZGDM",25,"AGPL-3.0","https:\u002F\u002Fgithub.com\u002F5throck\u002Fai-workspace-standards\u002Fblob\u002Fmain\u002Ftemplates\u002Fco-abap\u002F.claude\u002Fskills\u002Fabap-dev\u002FSKILL.md",[],[],"2026-11-11 15:11:14",false,"---\nname: abap-dev\ndescription: Use when working on SAP ABAP development tasks — provides specialized workflows for BAPI exploration, transport management, unit testing, performance analysis, impact architecture analysis, and documentation audits. Trigger on any SAP\u002FABAP coding, debugging, or system analysis task.\nversion: 1.2.0\nlast_reviewed: 2026-10-12\nstatus: active\nscope: co-abap\nowner: code-writer\nprerequisites: vsp MCP server\nrelates_to:\n  - skill: sap-fi\n    type: follows\n  - skill: sap-co\n    type: composes_with\n  - skill: sap-sd\n    type: composes_with\n  - skill: sap-mm\n    type: composes_with\n  - skill: sap-le\n    type: composes_with\n  - skill: sap-pp\n    type: composes_with\n  - skill: dump-monitor\n    type: composes_with\n  - skill: research-analysis\n    type: composes_with\n  - skill: sap-fi\n    type: composes_with\n  - skill: sap-co\n    type: composes_with\n  - skill: sap-sd\n    type: composes_with\n  - skill: sap-mm\n    type: composes_with\n  - skill: sap-le\n    type: composes_with\n  - skill: sap-pp\n    type: composes_with\nmetadata:\n  type: core\n  triggers:\n    - abap-dev\n    - BAPI\n    - transport\n    - ABAP Unit\n    - performance analysis\n    - impact analysis\n---\n\n# ABAP Development Skills (vsp)\n\nThis skill defines the ABAP development capabilities and optimized workflow patterns for Claude Code and AI agents using the vsp MCP server.\n\n## Core Capabilities\n\n- **Surgical Edits**: Use `EditSource` for changes under 50 lines to ensure syntax safety and atomicity.\n- **Context Awareness**: Use `GetContext` when analyzing large classes to save tokens and focus on structural understanding.\n- **Graph Analysis**: Perform impact analysis via `AnalyzeCallGraph` before refactoring.\n- **SQL Accuracy**: See ABAP SQL rules in `sap:performance-analyzer` below.\n\n## Best Practices\n\n- Always execute `SyntaxCheck` after any modification to verify quality.\n- Focus operations primarily within `Z*` and `$TMP` packages.\n- **File Isolation**: Task handoff files live in `scratch\u002Ftasks\u002F`, local `.abap` working copies live under `scratch\u002F`, and version-controlled framework infrastructure assets live in `scratch\u002Fstable\u002F`. Upstream source comments, annotations, or TODOs within `scratch\u002Fstable\u002F` (e.g. `zabapgit_standalone`) are exempt from standard project documentation and quality gates.\n\n---\n\n## sap:bapi-explorer\n\n**Purpose**: Discover, evaluate, and document standard SAP BAPIs for integration use cases.\n\n**Trigger**: When searching for integration APIs, standard function modules, or BAPI alternatives to custom development.\n\n**Workflow**:\n1. Use `SearchObject` with `type=FUNC` and a keyword pattern (e.g. `BAPI_SALESORDER_*`) to locate candidate function modules.\n2. For each candidate, call `GetSource` to read the function module signature (importing\u002Fexporting\u002Ftables parameters).\n3. Use `GetFunctionGroup` to understand the group the BAPI belongs to and related functions.\n4. Call `GetTable` on the relevant parameter structures (e.g. `BAPIORDERS`, `BAPISDORDER`) to understand field definitions and types.\n5. Document findings: BAPI name, parameters, return code structure (BAPIRET2), known limitations.\n\n**Output format**:\n```\nBAPI: \u003Cname>\nFunction Group: \u003Cgroup>\nPurpose: \u003Cone-line>\nKey Parameters:\n  IN:  \u003Cparam> (\u003Ctype>) — \u003Cdescription>\n  OUT: \u003Cparam> (\u003Ctype>) — \u003Cdescription>\nReturn: BAPIRET2 (check TYPE = 'E' for errors, TYPE = 'S' for success)\nUsage pattern: CALL FUNCTION '\u003CBAPI>' ... COMMIT WORK.\nLimitations: \u003Cknown issues or missing fields>\n```\n\n---\n\n## sap:transport-manager\n\n**Purpose**: Create, populate, and release SAP Transport Requests (CTS) for object deployment.\n\n**Trigger**: When working on dev\u002Fproduction systems, deploying objects, or managing change management.\n\n**Workflow**:\n1. **Check existing transports**: Call `ListTransports` to see open requests. Reuse an existing request if the task is part of an ongoing change.\n2. **Create a new request** (if needed): Call `CreateTransport` with a clear description (`feat: \u003Csummary>`).\n3. **Add objects**: After each `WriteSource`\u002F`EditSource`\u002F`Activate`, call `AddToTransport` with the object URL and transport number.\n4. **Pre-release gate**: Before `ReleaseTransport`, verify:\n   - `SyntaxCheck` → 0 errors on all objects\n   - `RunUnitTests` → 0 failures\n   - `RunATCCheck` → 0 Priority-1 findings\n5. **Release**: Call `ReleaseTransport`. Log the transport number in `memory\u002FYYYY-MM-DD.md`.\n\n**Slash command**: Use `\u002Ftransport` for all steps above.\n\n**Golden rule**: Never release a transport with Priority-1 ATC findings. If blocked, escalate to PM.\n\n---\n\n## sap:unit-architect\n\n**Purpose**: Design and implement ABAP Unit test classes that satisfy the Acceptance Criteria from Business Analysis.\n\n**Trigger**: When writing quality code, implementing new features, or ensuring test coverage.\n\n**Workflow**:\n1. Map each Acceptance Criterion (AC-01, AC-02 …) to one or more test methods.\n2. Identify dependencies (DB tables, function modules, BAPIs) and design TEST-SEAMs and TEST-INJECTIONs for isolation.\n3. Write the test class using `WriteSource` with `FOR TESTING`, `RISK LEVEL HARMLESS`, `DURATION SHORT`.\n4. Run `RunUnitTests` — all methods must pass before considering the task complete.\n\n**Test class skeleton**:\n```abap\nCLASS ltc_\u003Cobject_name> DEFINITION FOR TESTING\n  RISK LEVEL HARMLESS DURATION SHORT.\n  PRIVATE SECTION.\n    DATA: cut TYPE REF TO \u003Cclass_under_test>.\n    CLASS-METHODS: class_setup.\n    CLASS-METHODS: class_teardown.\n    METHODS: setup.\n    METHODS: teardown.\n    METHODS: test_\u003Cac_id>_\u003Cscenario> FOR TESTING.\nENDCLASS.\n\nCLASS ltc_\u003Cobject_name> IMPLEMENTATION.\n  METHOD setup.\n    cut = NEW #( ).\n  ENDMETHOD.\n  METHOD test_\u003Cac_id>_\u003Cscenario>.\n    \" Arrange — inject mock data via TEST-INJECTION\n    \" Act    — call cut->method( )\n    \" Assert — cl_abap_unit_assert=>assert_equals( )\n  ENDMETHOD.\nENDCLASS.\n```\n\n**Coverage target**: Every AC must have at least one test method. Priority-1 ATC findings of type \"No unit test\" must be resolved.\n\n---\n\n## sap:performance-analyzer\n\n**Purpose**: Identify and resolve performance bottlenecks in ABAP code and SQL queries.\n\n**Trigger**: When optimizing code, profiling slow reports, or reviewing SQL for efficiency.\n\n**Workflow**:\n1. **Identify hot paths**: Use `AnalyzeCallGraph` on the suspect object to see call frequency and depth.\n2. **Inspect SQL**: Extract all `SELECT` statements from `GetSource`. Check for:\n   - Missing `WHERE` clause or missing index fields in WHERE\n   - `SELECT *` instead of field list\n   - Nested SELECTs inside loops (N+1 problem)\n   - Missing `UP TO N ROWS` on large tables\n3. **Validate with data**: Use `RunQuery` to measure actual row counts on the relevant tables.\n4. **Check CDS**: Use `GetCDSDependencies` to see if a CDS view with built-in aggregation can replace the ABAP logic.\n5. **Apply fixes** using `EditSource` — replace problem patterns with:\n   - `SELECT field1, field2 INTO TABLE @DATA(lt_result) FROM table WHERE ...`\n   - Single JOIN instead of nested SELECT\n   - `FOR ALL ENTRIES IN lt_driver` — **only when `lt_driver` is guaranteed non-empty**; always guard with `IF lt_driver IS NOT INITIAL` to prevent full-table read\n6. Run `SyntaxCheck` and `RunUnitTests` after every change.\n\n**ABAP SQL rules**:\n- Use `DESCENDING` not `DESC`; `ASCENDING` not `ASC`\n- Use `max_rows` parameter, not `LIMIT`\n- Always specify field list — avoid `SELECT *` in production code\n- `FOR ALL ENTRIES IN`: guard with `IF \u003Ctable> IS NOT INITIAL` — an empty driving table reads the entire target table\n\n---\n\n## sap:impact-architecture\n\n**Purpose**: Analyse the full impact of a proposed change before implementation, to prevent regressions.\n\n**Trigger**: When modifying core BAPIs, CDS views, or widely-used objects. Run before any significant refactoring.\n\n**Workflow**:\n1. **Call graph analysis**: Call `AnalyzeCallGraph` on the target object. Record all direct and transitive callers.\n2. **CDS dependency tree**: Call `GetCDSDependencies` and `GetCDSImpactAnalysis` to identify all CDS views, OData services, and Fiori apps downstream of any changed CDS view.\n3. **Cross-package scan**: Call `GrepPackages` with the object name pattern to find references outside the primary package.\n4. **Risk matrix**: For each caller\u002Fdependent, classify:\n   - **Low**: Test-only or rarely-called utility\n   - **Medium**: Core business logic — requires regression test\n   - **High**: Real-time interface, batch job, or external API consumer — requires stakeholder sign-off\n5. **Gate**: Present findings to PM. Do not proceed to Technical Design until PM approves.\n\n**Output format** — produce both sections below:\n\n**Section A — Impact Summary table**:\n```\n| \u003CObjectName> | \u003CType> | \u003CN callers> | Low \u002F Medium \u002F High |\n```\n\n**Section B — Risk Assessment**:\n```\n- Scope: \u003CN objects affected>\n- Downtime required: Yes \u002F No\n- Transport needed: Yes \u002F No\n- Rollback plan: \u003Cdescribe or \"N\u002FA\">\n```\n\n---\n\n## sap:globalization\n\n**Purpose**: Keep user-facing behavior correct across time zones, countries, and languages — code that works in a single-zone test system and breaks in a global landscape.\n\n**Trigger**: Whenever implemented code has user-facing output (reports, messages, interfaces, forms) or computes dates, amounts, quantities, or deadlines.\n\n**Rules** (full pass\u002Ffail checklist: [docs\u002Fsap-globalization-checklist.md](..\u002F..\u002Fdocs\u002Fsap-globalization-checklist.md)):\n\n- **Time**: store instants as UTC timestamps (`GET TIME STAMP FIELD`); display with `CONVERT TIME STAMP ... TIME ZONE sy-zonlo` (user master zone). `SY-DATUM`\u002F`SY-UZEIT` are application-server time — never the basis for user-facing dates. No hardcoded UTC offsets or zone abbreviations (DST zones shift twice a year).\n- **Money & numbers**: monetary output always `WRITE ... CURRENCY \u003Cwaers>` (TCURX decimals — KRW\u002FJPY 0, USD 2). Never assemble dates\u002Fnumbers as concatenated text. In batch, print, and file-interface contexts, fix the output country and language explicitly (`SET COUNTRY` \u002F `SET LANGUAGE`) instead of inheriting the job user's profile.\n- **Units**: T006 internal codes with T006A display texts; convert via standard function units — never hardcoded factors; quantity and unit inseparable.\n- **Calendars**: working-day\u002Fdeadline logic uses factory + holiday calendars parameterized by country, not weekday arithmetic.\n- **Texts**: user-visible literals in text symbols and message classes; maintain translations — or record the deferral as a known limitation in the implementation and release reports.\n- **Output**: choose spool device type \u002F form page size (A4 vs US Letter) by where the document is printed, not by its language; global forms need country variants. Per-market expectations: `docs\u002Fcountries\u002F\u003CCODE>.md`.\n\n---\n\n## sap:documentation-audit\n\n**Purpose**: Ensure all project documentation is cross-platform compatible, links are valid, and absolute paths are avoided.\n\n**Trigger**: Before finalization\u002Fsync, or before running `\u002Fsync` command.\n\n**Workflow**:\n1. Run the audit script:\n   ```bash\n   bun scripts\u002Fco-abap\u002Fvsp-audit.ts\n   ```\n2. **Analyze Results**:\n   - If audit passes: proceed to `\u002Fsync`.\n   - If audit fails: identify the specific issue and fix it in the source `.md` or script.\n3. **Re-run**: Repeat until the audit returns 0 errors.\n\n**Gate**: A passing audit is required before running the final `\u002Fsync` command.\n\n## Context\n\nThis skill provides the core ABAP development workflow patterns for AI agents operating against an SAP system via the vsp MCP server. It covers the full development lifecycle from BAPI discovery and transport management through unit testing, performance analysis, impact assessment, and documentation auditing. Each sub-section maps to a specialized capability that can be invoked independently or as part of an end-to-end delivery chain.\n\n## When to Use\n\n- Working on any SAP ABAP coding, debugging, or system analysis task\n- Searching for BAPIs or standard function modules for integration scenarios\n- Creating, populating, or releasing SAP transport requests (CTS)\n- Writing or running ABAP Unit tests for custom objects\n- Investigating slow ABAP programs or expensive SQL queries\n- Analyzing the impact of a proposed change before implementation\n- Running documentation audits before finalization or sync\n\n## Execution Steps\n\n1. **BAPI Exploration** — Use `sap:bapi-explorer` to discover, evaluate, and document standard SAP BAPIs for integration use cases.\n2. **Transport Management** — Use `sap:transport-manager` to create, populate, and release transport requests via CTS.\n3. **Unit Test Architecture** — Use `sap:unit-architect` to design and implement ABAP Unit test classes mapped to acceptance criteria.\n4. **Performance Analysis** — Use `sap:performance-analyzer` to identify and resolve SQL and code performance bottlenecks.\n5. **Impact Assessment** — Use `sap:impact-architecture` to analyze the full call-graph and CDS dependency impact of a proposed change.\n6. **Globalization Check** — Apply `sap:globalization` rules (time zones, currency\u002Fnumber formatting, units, calendars, texts) whenever the code has user-facing output; record the outcome in the Code Writer Report.\n7. **Documentation Audit** — Use `sap:documentation-audit` to verify documentation quality before finalization.\n\n## Output Format\n\nEach sub-section produces its own structured output:\n- **BAPI Explorer**: Standardized BAPI documentation block with name, function group, parameters, return structure, and limitations.\n- **Transport Manager**: Transport number logged in `memory\u002FYYYY-MM-DD.md` with object list and release confirmation.\n- **Unit Architect**: Test class skeleton code with method-per-AC mapping and coverage report from `RunUnitTests`.\n- **Performance Analyzer**: Finding list with problem patterns, recommended fixes, and before\u002Fafter metrics.\n- **Impact Architecture**: Impact Summary table (object, type, caller count, risk level) and Risk Assessment block.\n- **Documentation Audit**: Pass\u002Ffail result from `bun scripts\u002Fco-abap\u002Fvsp-audit.ts` with error details if applicable.\n\n## Related Skills\n\n- [post-write-chain](..\u002Fpost-write-chain\u002FSKILL.md) — Mandatory QA gate after every ABAP write operation\n- [dump-monitor](..\u002Fdump-monitor\u002FSKILL.md) — System health monitoring for ABAP short dumps\n- [performance-tuning](..\u002Fperformance-tuning\u002FSKILL.md) — Standardized performance analysis workflow for large-table scenarios\n- [desktop-app-fallback](..\u002Fdesktop-app-fallback\u002FSKILL.md) — Manual QA chain for Claude Code Desktop App sessions\n","# ABAP Development Skills (vsp)\n\nThis skill defines the ABAP development capabilities and optimized workflow patterns for Claude Code and AI agents using the vsp MCP server.\n\n## Core Capabilities\n\n- **Surgical Edits**: Use `EditSource` for changes under 50 lines to ensure syntax safety and atomicity.\n- **Context Awareness**: Use `GetContext` when analyzing large classes to save tokens and focus on structural understanding.\n- **Graph Analysis**: Perform impact analysis via `AnalyzeCallGraph` before refactoring.\n- **SQL Accuracy**: See ABAP SQL rules in `sap:performance-analyzer` below.\n\n## Best Practices\n\n- Always execute `SyntaxCheck` after any modification to verify quality.\n- Focus operations primarily within `Z*` and `$TMP` packages.\n- **File Isolation**: Task handoff files live in `scratch\u002Ftasks\u002F`, local `.abap` working copies live under `scratch\u002F`, and version-controlled framework infrastructure assets live in `scratch\u002Fstable\u002F`. Upstream source comments, annotations, or TODOs within `scratch\u002Fstable\u002F` (e.g. `zabapgit_standalone`) are exempt from standard project documentation and quality gates.\n\n---\n\n## sap:bapi-explorer\n\n**Purpose**: Discover, evaluate, and document standard SAP BAPIs for integration use cases.\n\n**Trigger**: When searching for integration APIs, standard function modules, or BAPI alternatives to custom development.\n\n**Workflow**:\n1. Use `SearchObject` with `type=FUNC` and a keyword pattern (e.g. `BAPI_SALESORDER_*`) to locate candidate function modules.\n2. For each candidate, call `GetSource` to read the function module signature (importing\u002Fexporting\u002Ftables parameters).\n3. Use `GetFunctionGroup` to understand the group the BAPI belongs to and related functions.\n4. Call `GetTable` on the relevant parameter structures (e.g. `BAPIORDERS`, `BAPISDORDER`) to understand field definitions and types.\n5. Document findings: BAPI name, parameters, return code structure (BAPIRET2), known limitations.\n\n**Output format**:\n```\nBAPI: \u003Cname>\nFunction Group: \u003Cgroup>\nPurpose: \u003Cone-line>\nKey Parameters:\n  IN:  \u003Cparam> (\u003Ctype>) — \u003Cdescription>\n  OUT: \u003Cparam> (\u003Ctype>) — \u003Cdescription>\nReturn: BAPIRET2 (check TYPE = 'E' for errors, TYPE = 'S' for success)\nUsage pattern: CALL FUNCTION '\u003CBAPI>' ... COMMIT WORK.\nLimitations: \u003Cknown issues or missing fields>\n```\n\n---\n\n## sap:transport-manager\n\n**Purpose**: Create, populate, and release SAP Transport Requests (CTS) for object deployment.\n\n**Trigger**: When working on dev\u002Fproduction systems, deploying objects, or managing change management.\n\n**Workflow**:\n1. **Check existing transports**: Call `ListTransports` to see open requests. Reuse an existing request if the task is part of an ongoing change.\n2. **Create a new request** (if needed): Call `CreateTransport` with a clear description (`feat: \u003Csummary>`).\n3. **Add objects**: After each `WriteSource`\u002F`EditSource`\u002F`Activate`, call `AddToTransport` with the object URL and transport number.\n4. **Pre-release gate**: Before `ReleaseTransport`, verify:\n   - `SyntaxCheck` → 0 errors on all objects\n   - `RunUnitTests` → 0 failures\n   - `RunATCCheck` → 0 Priority-1 findings\n5. **Release**: Call `ReleaseTransport`. Log the transport number in `memory\u002FYYYY-MM-DD.md`.\n\n**Slash command**: Use `\u002Ftransport` for all steps above.\n\n**Golden rule**: Never release a transport with Priority-1 ATC findings. If blocked, escalate to PM.\n\n---\n\n## sap:unit-architect\n\n**Purpose**: Design and implement ABAP Unit test classes that satisfy the Acceptance Criteria from Business Analysis.\n\n**Trigger**: When writing quality code, implementing new features, or ensuring test coverage.\n\n**Workflow**:\n1. Map each Acceptance Criterion (AC-01, AC-02 …) to one or more test methods.\n2. Identify dependencies (DB tables, function modules, BAPIs) and design TEST-SEAMs and TEST-INJECTIONs for isolation.\n3. Write the test class using `WriteSource` with `FOR TESTING`, `RISK LEVEL HARMLESS`, `DURATION SHORT`.\n4. Run `RunUnitTests` — all methods must pass before considering the task complete.\n\n**Test class skeleton**:\n```abap\nCLASS ltc_\u003Cobject_name> DEFINITION FOR TESTING\n  RISK LEVEL HARMLESS DURATION SHORT.\n  PRIVATE SECTION.\n    DATA: cut TYPE REF TO \u003Cclass_under_test>.\n    CLASS-METHODS: class_setup.\n    CLASS-METHODS: class_teardown.\n    METHODS: setup.\n    METHODS: teardown.\n    METHODS: test_\u003Cac_id>_\u003Cscenario> FOR TESTING.\nENDCLASS.\n\nCLASS ltc_\u003Cobject_name> IMPLEMENTATION.\n  METHOD setup.\n    cut = NEW #( ).\n  ENDMETHOD.\n  METHOD test_\u003Cac_id>_\u003Cscenario>.\n    \" Arrange — inject mock data via TEST-INJECTION\n    \" Act    — call cut->method( )\n    \" Assert — cl_abap_unit_assert=>assert_equals( )\n  ENDMETHOD.\nENDCLASS.\n```\n\n**Coverage target**: Every AC must have at least one test method. Priority-1 ATC findings of type \"No unit test\" must be resolved.\n\n---\n\n## sap:performance-analyzer\n\n**Purpose**: Identify and resolve performance bottlenecks in ABAP code and SQL queries.\n\n**Trigger**: When optimizing code, profiling slow reports, or reviewing SQL for efficiency.\n\n**Workflow**:\n1. **Identify hot paths**: Use `AnalyzeCallGraph` on the suspect object to see call frequency and depth.\n2. **Inspect SQL**: Extract all `SELECT` statements from `GetSource`. Check for:\n   - Missing `WHERE` clause or missing index fields in WHERE\n   - `SELECT *` instead of field list\n   - Nested SELECTs inside loops (N+1 problem)\n   - Missing `UP TO N ROWS` on large tables\n3. **Validate with data**: Use `RunQuery` to measure actual row counts on the relevant tables.\n4. **Check CDS**: Use `GetCDSDependencies` to see if a CDS view with built-in aggregation can replace the ABAP logic.\n5. **Apply fixes** using `EditSource` — replace problem patterns with:\n   - `SELECT field1, field2 INTO TABLE @DATA(lt_result) FROM table WHERE ...`\n   - Single JOIN instead of nested SELECT\n   - `FOR ALL ENTRIES IN lt_driver` — **only when `lt_driver` is guaranteed non-empty**; always guard with `IF lt_driver IS NOT INITIAL` to prevent full-table read\n6. Run `SyntaxCheck` and `RunUnitTests` after every change.\n\n**ABAP SQL rules**:\n- Use `DESCENDING` not `DESC`; `ASCENDING` not `ASC`\n- Use `max_rows` parameter, not `LIMIT`\n- Always specify field list — avoid `SELECT *` in production code\n- `FOR ALL ENTRIES IN`: guard with `IF \u003Ctable> IS NOT INITIAL` — an empty driving table reads the entire target table\n\n---\n\n## sap:impact-architecture\n\n**Purpose**: Analyse the full impact of a proposed change before implementation, to prevent regressions.\n\n**Trigger**: When modifying core BAPIs, CDS views, or widely-used objects. Run before any significant refactoring.\n\n**Workflow**:\n1. **Call graph analysis**: Call `AnalyzeCallGraph` on the target object. Record all direct and transitive callers.\n2. **CDS dependency tree**: Call `GetCDSDependencies` and `GetCDSImpactAnalysis` to identify all CDS views, OData services, and Fiori apps downstream of any changed CDS view.\n3. **Cross-package scan**: Call `GrepPackages` with the object name pattern to find references outside the primary package.\n4. **Risk matrix**: For each caller\u002Fdependent, classify:\n   - **Low**: Test-only or rarely-called utility\n   - **Medium**: Core business logic — requires regression test\n   - **High**: Real-time interface, batch job, or external API consumer — requires stakeholder sign-off\n5. **Gate**: Present findings to PM. Do not proceed to Technical Design until PM approves.\n\n**Output format** — produce both sections below:\n\n**Section A — Impact Summary table**:\n```\n| \u003CObjectName> | \u003CType> | \u003CN callers> | Low \u002F Medium \u002F High |\n```\n\n**Section B — Risk Assessment**:\n```\n- Scope: \u003CN objects affected>\n- Downtime required: Yes \u002F No\n- Transport needed: Yes \u002F No\n- Rollback plan: \u003Cdescribe or \"N\u002FA\">\n```\n\n---\n\n## sap:globalization\n\n**Purpose**: Keep user-facing behavior correct across time zones, countries, and languages — code that works in a single-zone test system and breaks in a global landscape.\n\n**Trigger**: Whenever implemented code has user-facing output (reports, messages, interfaces, forms) or computes dates, amounts, quantities, or deadlines.\n\n**Rules** (full pass\u002Ffail checklist: [docs\u002Fsap-globalization-checklist.md](..\u002F..\u002Fdocs\u002Fsap-globalization-checklist.md)):\n\n- **Time**: store instants as UTC timestamps (`GET TIME STAMP FIELD`); display with `CONVERT TIME STAMP ... TIME ZONE sy-zonlo` (user master zone). `SY-DATUM`\u002F`SY-UZEIT` are application-server time — never the basis for user-facing dates. No hardcoded UTC offsets or zone abbreviations (DST zones shift twice a year).\n- **Money & numbers**: monetary output always `WRITE ... CURRENCY \u003Cwaers>` (TCURX decimals — KRW\u002FJPY 0, USD 2). Never assemble dates\u002Fnumbers as concatenated text. In batch, print, and file-interface contexts, fix the output country and language explicitly (`SET COUNTRY` \u002F `SET LANGUAGE`) instead of inheriting the job user's profile.\n- **Units**: T006 internal codes with T006A display texts; convert via standard function units — never hardcoded factors; quantity and unit inseparable.\n- **Calendars**: working-day\u002Fdeadline logic uses factory + holiday calendars parameterized by country, not weekday arithmetic.\n- **Texts**: user-visible literals in text symbols and message classes; maintain translations — or record the deferral as a known limitation in the implementation and release reports.\n- **Output**: choose spool device type \u002F form page size (A4 vs US Letter) by where the document is printed, not by its language; global forms need country variants. Per-market expectations: `docs\u002Fcountries\u002F\u003CCODE>.md`.\n\n---\n\n## sap:documentation-audit\n\n**Purpose**: Ensure all project documentation is cross-platform compatible, links are valid, and absolute paths are avoided.\n\n**Trigger**: Before finalization\u002Fsync, or before running `\u002Fsync` command.\n\n**Workflow**:\n1. Run the audit script:\n   ```bash\n   bun scripts\u002Fco-abap\u002Fvsp-audit.ts\n   ```\n2. **Analyze Results**:\n   - If audit passes: proceed to `\u002Fsync`.\n   - If audit fails: identify the specific issue and fix it in the source `.md` or script.\n3. **Re-run**: Repeat until the audit returns 0 errors.\n\n**Gate**: A passing audit is required before running the final `\u002Fsync` command.\n\n## Context\n\nThis skill provides the core ABAP development workflow patterns for AI agents operating against an SAP system via the vsp MCP server. It covers the full development lifecycle from BAPI discovery and transport management through unit testing, performance analysis, impact assessment, and documentation auditing. Each sub-section maps to a specialized capability that can be invoked independently or as part of an end-to-end delivery chain.\n\n## When to Use\n\n- Working on any SAP ABAP coding, debugging, or system analysis task\n- Searching for BAPIs or standard function modules for integration scenarios\n- Creating, populating, or releasing SAP transport requests (CTS)\n- Writing or running ABAP Unit tests for custom objects\n- Investigating slow ABAP programs or expensive SQL queries\n- Analyzing the impact of a proposed change before implementation\n- Running documentation audits before finalization or sync\n\n## Execution Steps\n\n1. **BAPI Exploration** — Use `sap:bapi-explorer` to discover, evaluate, and document standard SAP BAPIs for integration use cases.\n2. **Transport Management** — Use `sap:transport-manager` to create, populate, and release transport requests via CTS.\n3. **Unit Test Architecture** — Use `sap:unit-architect` to design and implement ABAP Unit test classes mapped to acceptance criteria.\n4. **Performance Analysis** — Use `sap:performance-analyzer` to identify and resolve SQL and code performance bottlenecks.\n5. **Impact Assessment** — Use `sap:impact-architecture` to analyze the full call-graph and CDS dependency impact of a proposed change.\n6. **Globalization Check** — Apply `sap:globalization` rules (time zones, currency\u002Fnumber formatting, units, calendars, texts) whenever the code has user-facing output; record the outcome in the Code Writer Report.\n7. **Documentation Audit** — Use `sap:documentation-audit` to verify documentation quality before finalization.\n\n## Output Format\n\nEach sub-section produces its own structured output:\n- **BAPI Explorer**: Standardized BAPI documentation block with name, function group, parameters, return structure, and limitations.\n- **Transport Manager**: Transport number logged in `memory\u002FYYYY-MM-DD.md` with object list and release confirmation.\n- **Unit Architect**: Test class skeleton code with method-per-AC mapping and coverage report from `RunUnitTests`.\n- **Performance Analyzer**: Finding list with problem patterns, recommended fixes, and before\u002Fafter metrics.\n- **Impact Architecture**: Impact Summary table (object, type, caller count, risk level) and Risk Assessment block.\n- **Documentation Audit**: Pass\u002Ffail result from `bun scripts\u002Fco-abap\u002Fvsp-audit.ts` with error details if applicable.\n\n## Related Skills\n\n- [post-write-chain](..\u002Fpost-write-chain\u002FSKILL.md) — Mandatory QA gate after every ABAP write operation\n- [dump-monitor](..\u002Fdump-monitor\u002FSKILL.md) — System health monitoring for ABAP short dumps\n- [performance-tuning](..\u002Fperformance-tuning\u002FSKILL.md) — Standardized performance analysis workflow for large-table scenarios\n- [desktop-app-fallback](..\u002Fdesktop-app-fallback\u002FSKILL.md) — Manual QA chain for Claude Code Desktop App sessions\n",{"name":5,"owner":23,"scope":24,"status":25,"version":26,"metadata":27,"relates_to":35,"description":7,"last_reviewed":60,"prerequisites":61},"code-writer","co-abap","active","1.2.0",{"type":28,"triggers":29},"core",[5,30,31,32,33,34],"BAPI","transport","ABAP Unit","performance analysis","impact analysis",[36,39,42,44,46,48,50,52,54,55,56,57,58,59],{"type":37,"skill":38},"follows","sap-fi",{"type":40,"skill":41},"composes_with","sap-co",{"type":40,"skill":43},"sap-sd",{"type":40,"skill":45},"sap-mm",{"type":40,"skill":47},"sap-le",{"type":40,"skill":49},"sap-pp",{"type":40,"skill":51},"dump-monitor",{"type":40,"skill":53},"research-analysis",{"type":40,"skill":38},{"type":40,"skill":41},{"type":40,"skill":43},{"type":40,"skill":45},{"type":40,"skill":47},{"type":40,"skill":49},1791763200000,"vsp MCP server","main","1162ccc568cf90c01b3886d6143cbfd851a37883","templates\u002Fco-abap\u002F.claude\u002Fskills\u002Fabap-dev",9,"https:\u002F\u002Fgithub.com\u002F5throck\u002Fai-workspace-standards","https:\u002F\u002Fgithub.com\u002F5throck","Experienced in digital transformation, enterprise IT, startup acceleration, and business strategy. Focused on building practical systems that connect technolo","2026-11-14 21:22:34",{"source":8,"skillName":5,"commands":71,"prompt":81,"zipAvailable":82},[72,75,78],{"tool":73,"command":74},"npx","npx skills add 5throck\u002Fai-workspace-standards --skill abap-dev",{"tool":76,"command":77},"bunx","bunx skills add 5throck\u002Fai-workspace-standards --skill abap-dev",{"tool":79,"command":80},"pnpm","pnpm dlx skills add 5throck\u002Fai-workspace-standards --skill abap-dev","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002F5throck\u002Fai-workspace-standards\u002Fblob\u002Fmain\u002Ftemplates\u002Fco-abap\u002F.claude\u002Fskills\u002Fabap-dev\u002FSKILL.md",true,[],[85,93,98,103,108,113],{"skillNo":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"publishedAt":92},"01M7BBJDYHJMGTJYSC37JVWY8S","i18n-layout","Text layout and encoding guidance: character encoding (UTF-8, legacy Korean code pages, BOM hazards), line endings, RTL\u002Fbidi handling, and script-specific font selection (Hangul focus). Use when: encoding is corrupted or mojibake appears, an RTL locale must render correctly, fonts must be chosen for a script, or CRLF\u002FBOM issues surface.","https:\u002F\u002Fgithub.com\u002F5throck\u002Fai-workspace-standards\u002Fblob\u002Fmain\u002Ftemplates\u002Fco-work\u002Fskills\u002Fi18n-layout\u002FSKILL.md",[],[],"2026-11-15 14:19:17",{"skillNo":94,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":95,"categories":96,"keywords":97,"publishedAt":92},"01M7BBJ9XHAAS1AVGKZZ841VBZ","https:\u002F\u002Fgithub.com\u002F5throck\u002Fai-workspace-standards\u002Fblob\u002Fmain\u002Ftemplates\u002Fco-work\u002F.hermes\u002Fskills\u002Fi18n-layout\u002FSKILL.md",[],[],{"skillNo":99,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":100,"categories":101,"keywords":102,"publishedAt":92},"01M7BBJ5C3X8TKFKG5R9P9P49W","https:\u002F\u002Fgithub.com\u002F5throck\u002Fai-workspace-standards\u002Fblob\u002Fmain\u002Ftemplates\u002Fco-work\u002F.gemini\u002Fskills\u002Fi18n-layout\u002FSKILL.md",[],[],{"skillNo":104,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":105,"categories":106,"keywords":107,"publishedAt":92},"01M7BBJ1B52X0QMJ2QVBMPJB37","https:\u002F\u002Fgithub.com\u002F5throck\u002Fai-workspace-standards\u002Fblob\u002Fmain\u002Ftemplates\u002Fco-work\u002F.codex\u002Fskills\u002Fi18n-layout\u002FSKILL.md",[],[],{"skillNo":109,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":110,"categories":111,"keywords":112,"publishedAt":92},"01M7BBHX91BW2Q2R276MRX5AW3","https:\u002F\u002Fgithub.com\u002F5throck\u002Fai-workspace-standards\u002Fblob\u002Fmain\u002Ftemplates\u002Fco-work\u002F.claude\u002Fskills\u002Fi18n-layout\u002FSKILL.md",[],[],{"skillNo":114,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":115,"categories":116,"keywords":117,"publishedAt":92},"01M7BBHQWGXPSFRWN1PRC2NMMV","https:\u002F\u002Fgithub.com\u002F5throck\u002Fai-workspace-standards\u002Fblob\u002Fmain\u002Ftemplates\u002Fco-work\u002F.agents\u002Fskills\u002Fi18n-layout\u002FSKILL.md",[],[]]