What is playwright-praman-sap-testing?

Instructions for using Playwright Praman to create automated browser tests for SAP UI5 applications. UI5 is SAP's web interface framework, and Playwright controls a browser to check real user interactions.

Use it to plan, generate, or repair end-to-end tests for SAP screens, forms, controls, and tables.

It gives agents a fixed list of supported controls and test APIs, reducing guesses about what the testing package can do.

playwright-praman-sap-testing — Skill by mrkanitkar/playwright-praman

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add mrkanitkar/playwright-praman --skill playwright-praman-sap-testing

Clone the repo

git clone --depth 1 https://github.com/mrkanitkar/playwright-praman

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/mrkanitkar/playwright-praman/playwright-praman-sap-testing/github.svg)](https://agentmods.dev/skills/mrkanitkar/playwright-praman/playwright-praman-sap-testing)

Your own site

<a href="https://agentmods.dev/skills/mrkanitkar/playwright-praman/playwright-praman-sap-testing"><img src="https://agentmods.dev/badge/skills/mrkanitkar/playwright-praman/playwright-praman-sap-testing/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/mrkanitkar/playwright-praman/playwright-praman-sap-testing"><img src="https://agentmods.dev/badge/skills/mrkanitkar/playwright-praman/playwright-praman-sap-testing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 8,082 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00000	$0.08082
Opus 5.5	$0.00000	$0.03233
Sonnet 5.5	$0.00000	$0.01616
Haiku 4.5	$0.00000	$0.00808

Measured 5d ago against content hash 71ae112e0a39, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

playwright-praman-sap-testing scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (test-template.ts), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/playwright-praman-sap-testing/SKILL.md · 734 lines

How it starts

The opening of the file, as written. The whole thing — 734 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Praman SAP Test Automation — Agent Skill Reference

Package: playwright-praman Import: import { test, expect } from 'playwright-praman' Purpose: Primary instruction set for Praman AI agents (planner, generator, healer)

Step 0: MANDATORY PREFLIGHT (Static Capability Reference)

Do NOT call runtime APIs — pramanAI.capabilities.forAI() is only available inside running tests, not during agent planning. Instead, use this static capability table, which is generated from capabilities.yaml and carries signatures read from the source.

PRAMAN_CAPABILITIES

ui5
  control(...), controls(selector), click(selector), fill(selector, value), press(selector),
  select(selector, key), check(selector), uncheck(selector), clear(selector), getText(selector),
  getValue(selector), waitForUI5(...), waitFor(selector, options?), inspect(...), clearCache(),
  destroy()

control
  setValue(...), fireChange(...), open(...), close(...), setSelectedKey(...)

ui5.table
  detectType(...), getRows(...), getRowCount(...), getCellValue(...), getData(...),
  selectRow(...), selectAll(...), deselectAll(...), waitForData(...),
  getSelectedRows(page, tableId, options?), getColumnNames(page, tableId),
  findRowByValues(page, tableId, columnValues),
  getCellByColumnName(page, tableId, rowIndex, columnName, options?),
  clickRow(page, tableId, rowIndex), selectRowByValues(page, tableId, columnValues, options?),
  ensureRowVisible(page, tableId, rowIndex),
  setTableCellValue(page, tableId, rowIndex, colIndex, value), getRowCountAlt(...),
  filterByColumn(page, tableId, columnIndex, filterValue, options?),
  sortByColumn(page, tableId, columnIndex, options?), getSortOrder(page, tableId, columnIndex),
  getFilterValue(page, tableId, columnIndex), exportData(...), clickSettings(...)

ui5.dialog
  waitFor(...), getOpen(...), isOpen(...), dismiss(...), confirm(...), waitForClosed(...),
  getButtons(...)

ui5.date
  setDatePicker(...), getDatePicker(...), setDateRange(...), getDateRange(...),
  setTimePicker(...), getTimePicker(...), setAndValidate(...)

ui5.odata
  getModelData(page, path, options?), getModelProperty(page, path, options?), waitForLoad(...),
  fetchCSRFToken(page, serviceUrl), getEntityCount(page, path, options?),
  hasPendingChanges(page, options?), createEntity(page, serviceUrl, entitySet, data, options?),
  updateEntity(page, serviceUrl, entitySet, key, data, options?),
  deleteEntity(page, serviceUrl, entitySet, key, options?),
  queryEntities(page, serviceUrl, entitySet, options?),
  callFunctionImport(page, serviceUrl, functionName, params?, method?, options?)

ui5Navigation
  navigateToApp(page, appId, options?), navigateToTile(page, tileTitle, options?),
  navigateToIntent(page, intent, params?, options?), navigateToHash(page, hash, options?),
  navigateToHome(page, options?), navigateBack(page, options?), navigateForward(page, options?),
  searchAndOpenApp(page, appTitle, options?), getCurrentHash(page)

sapAuth
  login(page, config), loginFromEnv(page), logout(page), isAuthenticated(page),
  isSessionExpired(timeoutMs?), getSessionInfo()

fe.listReport
  getTable(...), getFilterBar(page, options?), setFilter(...), search(...), clearFilters(...),
  navigateToItem(page, tableId, rowIndex, options?), getVariants(...),
  selectVariant(page, variantName, options?), getFilterValue(...)

fe.objectPage
  navigateToSection(page, sectionIdentifier, options?), getSectionData(page, sectionIdentifier),
  clickButton(...), clickEdit(...), clickSave(...), getSections(...), getHeaderTitle(page),
  isInEditMode(page)

fe.table
  getRowCount(...), getCellValue(...), findRow(...), clickRow(...), getColumnNames(...)

fe.list
  getItemCount(...), getItemTitle(...), findItemByTitle(...), clickItem(...), selectItem(...)

intent.core
  fillField(ui5, vocabulary, label, value), clickButton(ui5, text),
  selectOption(ui5, vocabulary, label, option), assertField(ui5, vocabulary, label, expected),
  confirmAndWait(ui5), waitForSave(ui5, options?),
  navigateAndSearch(ui5, ui5Nav, vocabulary, appId, criteria, options?)

intent.procurement
  createPurchaseOrder(ui5, ui5Nav, vocabulary, input, options?),
  approvePurchaseOrder(ui5, ui5Nav, input, options?),
  searchPurchaseOrders(ui5, ui5Nav, vocabulary, criteria, options?),
  createPurchaseRequisition(ui5, ui5Nav, vocabulary, input, options?),
  confirmGoodsReceipt(ui5, ui5Nav, input, options?), searchVendors(ui5, ui5Nav, options?)

intent.sales
  createSalesOrder(ui5, ui5Nav, vocabulary, input, options?),
  createQuotation(ui5, ui5Nav, vocabulary, input, options?),
  approveQuotation(ui5, ui5Nav, input, options?),
  searchSalesOrders(ui5, ui5Nav, vocabulary, criteria, options?),
  searchCustomers(ui5, ui5Nav, options?), checkDeliveryStatus(ui5, ui5Nav, input, options?)

intent.finance
  createJournalEntry(ui5, ui5Nav, vocabulary, input, options?),
  postVendorInvoice(ui5, ui5Nav, vocabulary, input, options?),
  processPayment(ui5, ui5Nav, vocabulary, input, options?)

intent.manufacturing
  createProductionOrder(ui5, ui5Nav, vocabulary, input, options?),
  confirmProductionOrder(ui5, ui5Nav, vocabulary, input, options?)

intent.masterData
  createVendorMaster(ui5, ui5Nav, vocabulary, input, options?),
  createCustomerMaster(ui5, ui5Nav, vocabulary, input, options?),
  createMaterialMaster(ui5, ui5Nav, vocabulary, input, options?)

pramanAI
  discoverPage(page, options?), buildContext(...), capabilities(), recipes(), agentic(...),
  llm(...), vocabulary(...)

capability-registry
  forAI(), byCategory(category)

ui5Shell
  expectShellHeader(...), clickHome(), openNotifications(), openUserMenu()

ui5Footer
  clickSave(...), clickApply(), clickCancel(), clickEdit(), clickDelete(), clickCreate()

flpLocks
  getLockEntries(...), getNumberOfLockEntries(username?), deleteAllLockEntries(username?),
  cleanup()

flpSettings
  getLanguage(...), getDateFormat(), getTimeFormat(), getTimezone(), getNumberFormat(),
  getAllSettings()

testData
  generate(...), save(filename, data), load(filename), cleanup()

matchers
  toHaveUI5Text(...), toBeUI5Visible(...), toBeUI5Enabled(...), toHaveUI5Property(...),
  toHaveUI5ValueState(...), toHaveUI5RowCount(...), toHaveUI5CellText(...),
  getControlProperty(page, controlId, propertyName),
  getControlAggregation(page, controlId, aggregationName)

selectors
  serializeUI5SelectorToCSS(selector)

screencast
  highlightControls()

proxy
  contextRetryDelay(attempt)

webStorage
  webStorage(...), webStorageHelper(...)

ui5Overlays
  register(rule), registerAll(rules), dispose()

ui5Clock
  install(time?), setFixedTime(time), fastForward(ticks), pauseAt(time), resume(), runFor(ticks)

ui5Wait
  waitForControlState(locator, predicate, options?)

odata
  odataTest()

visualRegression
  visualRegressionTest(), VisualRegressionOptions()

ui5Diagnostics
  collectPageDiagnostics(page)

fixtures
  attachBridgeNavigationReset(page, logger?)

intent.quality
  createInspectionLot(ui5, ui5Nav, vocabulary, input, options?),
  recordResults(ui5, ui5Nav, vocabulary, input, options?),
  createQualityNotification(ui5, ui5Nav, vocabulary, input, options?)

intent.warehouse
  createGoodsMovement(ui5, ui5Nav, vocabulary, input, options?),
  createTransferOrder(ui5, ui5Nav, vocabulary, input, options?)

intent.assetManagement
  acquireAsset(ui5, ui5Nav, vocabulary, input, options?),
  retireAsset(ui5, ui5Nav, vocabulary, input, options?),
  transferAsset(ui5, ui5Nav, vocabulary, input, options?)

intent.hr
  createEmployee(ui5, ui5Nav, vocabulary, input, options?),
  recordTime(ui5, ui5Nav, vocabulary, input, options?),
  requestAbsence(ui5, ui5Nav, vocabulary, input, options?)

cli.scaffold
  GLOBAL_TEARDOWN_TEMPLATE(), MASTER_DATA_HELPER_TEMPLATE(), PLAYWRIGHT_WORKFLOW_TEMPLATE()

Read the full file on GitHub · 734 lines

Files

What ships with it

25 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

5d ago Changed · +28 lines 71ae112e0a39
7d ago First seen · 706 lines · 0 tokens per session scan A 58aafbf62dec

Subscribe to this mod's changes

playwright-praman-sap-testing is a skill published in the GitHub repository mrkanitkar/playwright-praman (10 stars, last pushed 5d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 8,082 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-03.

Browser automation E2E testing Testing TypeScript automation playwright sap ui5

playwright-cli

Automate browser interactions, test web pages and work with Playwright tests.

microsoft/playwright · 19 tokens

playwright-component-testing

Set up component testing with Playwright using a story gallery — scaffold stories and a gallery dev page driven by the built-in mount fixture, no dedicated component-testing runtime. Use when asked to test React or Vue components in isolation with Playwright, or to migrate off @playwright/experimental-ct-react / -vue.

microsoft/playwright · 69 tokens

playwright-trace

Inspect Playwright trace files from the command line — list actions, view requests, console, errors, snapshots and screenshots.

microsoft/playwright · 29 tokens

ux-acceptance-coordinator

Coordinate black-box, agent-driven UX acceptance journeys against a disposable EmDash admin site. Use when preparing, dispatching, verifying, or reporting a manual browser journey performed by a separate tester agent. Do not use for deterministic Playwright tests or ordinary code review.

emdash-cms/emdash · 59 tokens

ux-acceptance-tester

Perform a goal-driven, black-box UX acceptance journey in a browser and report the path, friction, and observable outcome. Use only in an isolated tester context with a supplied start URL and brief.

emdash-cms/emdash · 46 tokens

Browser Agent QA Testing

Teach agents to use AI browser agents for exploratory and smoke QA with step budgets, evidence-based assertions, guardrails, and Playwright conversion.

PramodDutta/qaskills · 33 tokens