agentleFS
williamcorrea23williamcorrea23/sap-router-skill/.agents/skills/sap-sac-planning/SKILL.md

sap-sac-planning

Skill1 starsChanged 4 months agoMITView on GitHub

SAC Planning — models, versions, allocations, data actions, value driver trees, calendar tasks, predictive forecasting, BPC migration. Use when building SAC planning apps, creating allocations, or migrating from BPC.

  • Sends data out

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use "Smart Insights" on VDT nodes to surface hidden correlations before manual modeling.

    line 116

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

SAP Analytics Cloud Planning

SAC Planning = Model (structure) → Process (actions) → Governance (versions, calendars). Each layer builds on the previous.

Prerequisites

  • SAC tenant with Planning license (not BI-only)
  • Model Builder role or planning_model.create permission
  • Source data: BW/4HANA, S/4HANA, or flat-file upload
  • BPC migration: access to BPC 10.x/11.x (NW or MS) environment

1. Planning Model

Model: Financial_Plan
├── Dimensions (max 20): Account, CostCenter, Time, Version, Currency
├── Measures: Amount, Quantity, Price, Calculated
├── Versions: Actual (RO), Budget, Forecast, Plan (what-if)
└── Security: R/W per dimension member
curl -X POST "https://$SAC_TENANT/api/v1/planningmodels" \
  -H "Authorization: Bearer $SAC_TOKEN" -H "Content-Type: application/json" \
  -d '{"name":"Financial_Plan","dimensions":["Account","CostCenter","Time","Version","Currency"],"defaultCurrency":"USD"}'

2. Version Management

VersionPurposeBehavior
ActualHistorical dataRead-only, loaded from source
BudgetAnnual planLocked after approval
ForecastRolling forecastOpen to contributors
PlanWhat-if scenarioTemporary, user-scoped
curl -X POST "https://$SAC_TENANT/api/v1/versions" \
  -H "Authorization: Bearer $SAC_TOKEN" \
  -d '{"model":"Financial_Plan","source":"Actual","target":"Budget_2026","copyData":true}'

3. Allocation Process

Distributes costs from source to targets using a driver measure.

// SAC Data Action — Allocation step (Advanced Formula)
var alloc = PlanningModel_1.createAllocationStep({
  source: { dimension:"CostCenter", member:"CC_ADMIN", measure:"Amount",
            filter:[["Account","=","SALARIES"]] },
  target: { dimension:"CostCenter", members:["CC_SALES","CC_MKTG","CC_RD"],
            driver:{ measure:"Headcount", includeZero:false } },
  method:"COPY", amount:100   // COPY | PERCENTAGE | SHARE, % of source
});
alloc.execute();

Key: Driver measure must be in the same model. Cross-model references require a calculated measure workaround.

4. Data Actions

Multi-step scripts that copy/transform/calculate plan data across versions.

Data Action: Copy_Plan_to_Forecast
  Step 1 — Copy:     Plan/2026 → Forecast/2026
  Step 2 — Override:  SALARIES × 1.05 (5% raise)
  Step 3 — Allocate:  Overhead by revenue share
  Step 4 — Publish:   Lock Forecast version
curl -X POST "https://$SAC_TENANT/api/v1/dataactions/Copy_Plan_to_Forecast/execute" \
  -H "Authorization: Bearer $SAC_TOKEN" \
  -d '{"parameters":{"SOURCE_VERSION":"Plan","TARGET_VERSION":"Forecast_2026"}}'

5. Value Driver Trees (VDT)

Decompose KPIs into adjustable levers for what-if simulation.

Revenue
├── Price × Quantity
│   ├── Price ──→ Pricing Strategy (manual input)
│   └── Quantity ──→ Market Size × Market Share
└── [ML: Market Share = 73% influence — top driver]

RAG insight: SAC augmented analytics auto-detects KPI drivers via ML. Use "Smart Insights" on VDT nodes to surface hidden correlations before manual modeling. Build planning models from predictive forecasts to blend ML + human input.

6. Calendar Tasks

Orchestrates planning workflows with task dependencies and lock gates.

Q4 Cycle:
  Task 1 (Oct 1–7):   CC Managers → Input headcount & expenses
  Task 2 (Oct 8–14):  Finance → Review & consolidate
  Task 3 (Oct 15–21): Controller → Finalize, allocate, lock
curl -X POST "https://$SAC_TENANT/api/v1/calendar/tasks" \
  -H "Authorization: Bearer $SAC_TOKEN" \
  -d '{"name":"Input_Headcount_Q4","model":"Financial_Plan","assignees":["cc_sales_mgr"],"startDate":"2026-10-01","endDate":"2026-10-07","taskType":"DATA_ENTRY"}'

7. BPC → SAC Migration

BPC ConceptSAC EquivalentNotes
EnvironmentPlanning ModelOne model per BPC app
Input SchedulesStories + TablesRebuild as grid widgets
Script LogicData ActionsRewrite in Advanced Formula
Work StatusCalendar TasksMap locks to task gates
EPM Add-inSAC Excel Add-inRe-link to SAC model
DimensionsDimensionsMax 20 (BPC allowed more)

Steps: Export BPC metadata → Create SAC model → Migrate master data → Rebuild script logic as Data Actions (30–40% rewrite) → Recreate schedules as Stories → Map work status → Calendar → Validate row-by-row (delta < 0.01%).

8. Predictive Forecasting

curl -X POST "https://$SAC_TENANT/api/v1/predictive/forecasts" \
  -H "Authorization: Bearer $SAC_TOKEN" \
  -d '{"model":"Financial_Plan","target":"Revenue","horizon":12,"version":"Forecast_2026","explanatoryVariables":["Price","Quantity","MarketShare"]}'

Pitfalls

  • 20 dimensions max — BPC models with more need consolidation
  • 100 Data Action steps max — split complex chains into sequential actions
  • Actual is read-only — copy to planning version before writing
  • Allocation driver scope — must be same model; cross-model needs workaround
  • Currency conversion — set up rates table before loading data; retroactive triggers full recalc
  • Version proliferation — each public version costs storage; archive quarterly
  • Calendar ownership — if assignee leaves, task stalls; set fallback owner
  • BPC *WHEN/*IS — don't map 1:1 to SAC Advanced Formula; 30–40% rewrite
  • Large model perf — > 100M cells degrades rendering; use private versions

Verification

# 1. Model structure
curl -s "https://$SAC_TENANT/api/v1/planningmodels/Financial_Plan" \
  -H "Authorization: Bearer $SAC_TOKEN" | jq '.dimensions, .versions'

# 2. Data action status
curl -s "https://$SAC_TENANT/api/v1/dataactions/Copy_Plan_to_Forecast/status" \
  -H "Authorization: Bearer $SAC_TOKEN" | jq '.status, .lastRun, .rowsAffected'

# 3. Allocation check (source zeroed, targets populated)
curl -s "https://$SAC_TENANT/api/v1/dataexport/Financial_Plan" \
  -H "Authorization: Bearer $SAC_TOKEN" \
  -d '{"filter":{"CostCenter":"CC_ADMIN","Account":"SALARIES"}}' | jq '.data'

# 4. Open calendar tasks
curl -s "https://$SAC_TENANT/api/v1/calendar/tasks?status=OPEN" \
  -H "Authorization: Bearer $SAC_TOKEN" | jq '.tasks | length'

# 5. BPC migration — row count delta < 0.01% = pass

Quick Reference

  • Max dims: 20 | Max DA steps: 100 | Alloc methods: COPY, PERCENTAGE, SHARE
  • Versions: Public (shared), Private (user-scoped)
  • API: https://$SAC_TENANT/api/v1/ | Auth: OAuth 2.0 (Settings → App Integration)

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.