sap-activate-object
Activates an inactive SAP repository object via SAP GUI Scripting. Routes to the correct transaction by object type: SE38 for…
Validates an extracted design spec before ABAP code generation, across two dimensions: `ddic` checks DDIC objects (domains / data elements / tables) — naming, data-type validity, domain/DTEL/table cross-references, currency-ref completeness, the primitive-as-data-element trap;
Claude Code
$ npx -y skills add sapdev-ai/sap-dev --skill sap-docs-check --agent claude-code
Codex
$ npx skills add sapdev-ai/sap-dev --skill sap-docs-check -a codex -y
Cursor
$ npx skills add sapdev-ai/sap-dev --skill sap-docs-check -a cursor -y
Gemini CLI
$ npx skills add sapdev-ai/sap-dev --skill sap-docs-check -a gemini-cli -y
GitHub Copilot
$ npx skills add sapdev-ai/sap-dev --skill sap-docs-check -a github-copilot -y
OpenCode
$ npx skills add sapdev-ai/sap-dev --skill sap-docs-check -a opencode -y
Windsurf
$ npx skills add sapdev-ai/sap-dev --skill sap-docs-check -a windsurf -y
name: sap-docs-check description: | Validates an extracted design spec before ABAP code generation, across two dimensions: `ddic` checks DDIC objects (domains / data elements / tables) — naming, data-type validity, domain/DTEL/table cross-references, currency-ref completeness, the primitive-as-data-element trap; `process` checks the process-logic text for unclear/ambiguous steps, missing info, and logic / type / cross-reference inconsistencies. Both optionally verify references against the live system over RFC when a SAP logon is given. Runs BOTH by default (whichever inputs exist); --dimension ddic|process forces one. Writes a TAB-separated result file per dimension for Excel review. Replaces the former /sap-docs-check-ddic and /sap-docs-check-process. Input: work folder path; optional SAP Logon description enables the RFC checks. argument-hint: "<work-folder-path> [--dimension ddic|process|all] [<sap-logon-description>]"
You validate an extracted design spec before it feeds ABAP code generation (`/sap-gen-abap`) and DDIC creation (`/sap-se11`). One skill, two dimensions:
`_tables.txt`) → `check_result_ddic.txt`.
By default both run (whichever dimension's inputs are present). Pass `--dimension ddic` or `--dimension process` to force one.
Task: $ARGUMENTS
---
| File | Token | Purpose | |---|---|---| | `<SAP_DEV_CORE_SHARED_DIR>/rules/skill_operating_rules.md` | *(rule)* | Mandatory operating rules | | `<SAP_DEV_CORE_SHARED_DIR>/rules/ddic_excel_layout_rules.md` | *(rule)* | DDIC Excel-spec authoring rules — naming-suffix consistency, primitive-type-as-DTEL trap, currency reference, column order. Cross-check extracted DDIC against these rules. | | `<SAP_DEV_CORE_SHARED_DIR>/rules/language_independence_rules.md` | *(rule)* | GUI-scripting language independence — RFC-only validator, but rule applies to downstream deploy skills (sap-se11) the validated spec feeds | | `<SAP_DEV_CORE_SHARED_DIR>/rules/abap_code_quality_rules.md` | *(rule)* | ABAP code-quality rules — DDIC + process-logic spec quality directly determines downstream ABAP quality; validation findings here surface ABAP-quality risk before code generation | | `sap-dev-core/shared/tables/sap_object_naming_rules.tsv` | *(read by helper)* | DDIC naming patterns (DDIC_DOMAIN / DDIC_DATAELEMENT / DDIC_TABLE). Custom override: `{custom_url}\sap_object_naming_rules.tsv` | | `sap-dev-core/shared/tables/domain_datatypes.tsv` | *(read directly)* | Valid SE11 domain data types + per-type length/decimals/sign rules — the authority for the DDIC dimension's data-type check (same table `/sap-se11` validates against) | | `sap-dev-core/shared/scripts/sap_check_object_name.ps1` | *(helper)* | Shared name validator invoked by the DDIC dimension | | `sap-dev-core/shared/scripts/sap_rfc_lookup_struct.ps1` | *(helper)* | DDIC structure signature cache — populates `_struct_signatures.txt` for the live ReferenceTable / TABLE.FIELD checks (both dimensions; same cache `/sap-gen-abap` Step 1.5e uses) | | `sap-dev-core/shared/scripts/sap_check_spec_refs.ps1` | *(helper)* | Offline `(TABLE, FIELD)` reference validator — appends `Error`/`Warning` rows to the result file (both dimensions' live-ref checks) |
---
**Resolve `work_dir` via the env-aware helper** — do NOT take `work_dir` from a direct `settings.json` read (that ignores the `SAPDEV_AI_WORK_DIR` env var and `userconfig.json`). Use the `WORK_DIR=` value printed by:
powershell -NoProfile -ExecutionPolicy Bypass -Command ". '<SAP_DEV_CORE_SHARED_DIR>\scripts\sap_settings_lib.ps1'; . '<SAP_DEV_CORE_SHARED_DIR>\scripts\sap_connection_lib.ps1'; Write-Output ('WORK_DIR=' + (Get-SapWorkDir))"The settings note below still applies to the OTHER keys.
**Settings reads/writes follow `<SAP_DEV_CORE_SHARED_DIR>/rules/settings_lookup.md`** — merge per-key on the `.value` field (env var → `settings.local.json` → `userconfig.json` → `settings.json`); non-per-connection writes go to `userconfig.json`. Set `{WORK_TEMP}` = `{work_dir}\temp` and ensure it exists:
cmd /c if not exist "{WORK_TEMP}" mkdir "{WORK_TEMP}"Set `{RUN_TEMP}` = the per-run scratch dir (`Get-SapRunTemp` mints + creates `{work_dir}\temp\run_<id>`):
powershell -NoProfile -ExecutionPolicy Bypass -Command ". '<SAP_DEV_CORE_SHARED_DIR>\scripts\sap_connection_lib.ps1'; Write-Output ('RUN_TEMP=' + (Get-SapRunTemp))"Per the CLAUDE.md "Two-bucket temp model" write this skill's per-run scratch (the `_run.json` log state and the live-ref request files) under `{RUN_TEMP}`; keep `{WORK_TEMP}` (base) only for `Get-SapCurrentSessionPath -WorkTemp`.
---
Start a structured log run. State file: `{RUN_TEMP}\sap_docs_check_run.json`. Best-effort.
powershell -ExecutionPolicy Bypass -File "<SAP_DEV_CORE_SHARED_DIR>\scripts\sap_log_helper.ps1" -Action start -StateFile "{RUN_TEMP}\sap_docs_check_run.json" -Skill sap-docs-check -ParamsJson "{\"work_folder\":\"<WORK_FOLDER>\",\"dimension\":\"<DIMENSION>\"}"---
Extract from `$ARGUMENTS`:
dimension.
Locate the input files in the work folder:
Decide which dimensions to run:
| `--dimension` | Runs | |---|---| | `all` (default) | **DDIC** if any of `_domains` / `_dataElements` / `_tables` is
SAP development automation skills for AI coding assistants. Windows-only — the skills drive SAP GUI for Windows via GUI Scripting (plus optional RFC via SAP NCo); there is no macOS/Linux path.
Activates an inactive SAP repository object via SAP GUI Scripting. Routes to the correct transaction by object type: SE38 for…
Natural-language SAP API discovery over RFC (no GUI): turn a goal like "create a sales order" or "post a goods movement" into a…
Runs the SAP ABAP Test Cockpit (ATC) end-to-end as a quality gate: builds an SCI Object Set scoped to the target object(s),…
Executes BDC (Batch Data Communication) sessions in SAP via RFC. Reads SHDB recording files from the bdc/ folder, connects via…
Changes the package (TADIR-DEVCLASS) assignment of an SAP repository object via the "Object Directory Entry" dialog (Goto >…
Validates ABAP source (report / program / FM / class / include) before deployment — one skill, dimension-dispatched: naming…
You MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or…
Ask which skill or flow fits your situation. A router over the skills in this repo.