forcedotcom/sf-skills

platform-report-generate

Use this skill when users need to create, generate, or validate Salesforce Lightning Report metadata.

Zobacz źródło
Oryginalny dokument Skill

Treść z repozytorium z zachowaniem nagłówków, przykładów, kodu, tabel, linków i obrazów.

Overview

Lightning Reports define how Salesforce data is queried, grouped, filtered, and displayed. Each report is a single .report-meta.xml file placed under reports/<FolderName>/ within the project's source directory (check sfdx-project.jsonpackageDirectories[].path for the source root).

Critical Rules (Read First)

TOP DEPLOYMENT KILLERS — check these BEFORE generating any report:

  1. Grouping fields in columns — Fields in <groupingsDown> or <groupingsAcross> must NEVER also appear in <columns>
  2. Wrong column names — Column names are report-type-specific. ALWAYS call MCP tools to verify (see references/column-names.md)
  3. Wrong scope — LeadList uses org, not organization
  4. Filter column dot notation — Filter <column> values use FLAT names (INDUSTRY, TYPE) NOT dot notation (ACCOUNT.INDUSTRY is INVALID)
  5. Multi-value picklist filters — Use ONE <criteriaItems> with comma-separated <value> (e.g., Technology,Financial Services). Do NOT split into multiple criteriaItems with booleanFilter

Rule 1: Format Determines Required Elements

Format<groupingsDown><groupingsAcross><block>
TabularNot allowedNot allowedNo
SummaryAt least 1 (max 3)Not allowedNo
MatrixAt least 1 (max 3)At least 1 (max 3)No
JoinedNot at top levelNot at top levelAt least 2 (max 5)

Rule 2: Use Platform Column Names

Report metadata uses platform report column names, NOT raw API field names. ALWAYS call `get_metadata_type_sections` or `get_metadata_type_context` to confirm valid column names. See references/column-names.md for common mappings per report type.

Rule 3: Valid Report Type Required

<reportType> must be a standard API name (e.g., Opportunity, AccountList, CaseList, LeadList, AccountContactRole) or a deployed custom report type developer name.

Rule 4–5: Chart & Aggregates Require Summary/Matrix

Charts and <aggregateTypes> (Sum, Average, etc.) only work in Summary and Matrix reports.

Rule 6–8: Limits

  • Max 3 cross-filters per report, each with up to 5 criteria items
  • <filterLogic> must reference all filters sequentially (e.g., 1 AND (2 OR 3))
  • Joined reports: 2–5 blocks, each block format must be Summary or Matrix (not Tabular)

Rule 9: Folder Structure

Reports must live inside a folder with a corresponding folder metadata file:

xml
<sourceDir>/reports/<FolderName>/<ReportName>.report-meta.xml
<sourceDir>/reports/<FolderName>-meta.xml

Determine <sourceDir> from sfdx-project.json (commonly force-app/main/default, but this is configurable).

Rule 10–11: Date Columns & Scope

  • Date columns use platform names (CLOSE_DATE, not CloseDate)
  • LeadList scope is org; Opportunity/AccountList/CaseList use organization

Rule 12–13: Description & Groupings

  • <description> max 255 characters
  • Grouping fields must NOT appear in <columns> — automatic deployment failure

Rule 14: Folder Metadata Requires <sharedTo>

xml
<?xml version="1.0" encoding="UTF-8"?>
<ReportFolder xmlns="http://soap.sforce.com/2006/04/metadata">
    <folderShares>
        <accessLevel>Manage</accessLevel>
        <sharedTo>AllInternalUsers</sharedTo>
        <sharedToType>Group</sharedToType>
    </folderShares>
    <name>My Report Folder</name>
</ReportFolder>

Rule 15: Valid Date Intervals Only

Use INTERVAL_CURRENT for "this quarter", INTERVAL_CURY for "this year", INTERVAL_LAST30 for last 30 days. Do NOT use INTERVAL_CURQ — it is not valid. See references/date-intervals.md for the full list.

Top-Level Elements

ElementRequiredNotes
<name>YesReport name (max 40 chars)
<reportType>YesReport type API name
<format>YesTabular, Summary, Matrix, or Joined
<scope>Recommendedorganization (or org for LeadList)
<columns>YesField columns — each has <field> and optional <aggregateTypes>
<filter>NoContains <criteriaItems> with <column>, <operator>, <value>
<groupingsDown>ConditionalRow groupings: <field>, <dateGranularity>, <sortOrder>
<groupingsAcross>ConditionalColumn groupings (Matrix only)
<timeFrameFilter>Recommended<dateColumn>, <interval>, optional <startDate>/<endDate>
<chart>NoSee references/chart-types.md
<buckets>NoBucket field definitions
<crossFilters>NoCross-object filters (with/without)
<showDetails>Recommendedtrue/false
<showGrandTotal>Recommendedtrue/false
<showSubTotals>Recommendedtrue/false
<description>RecommendedBusiness purpose (max 255 chars)
<block>ConditionalJoined format blocks

Filter Syntax

xml
<filter>
    <criteriaItems>
        <column>STAGE_NAME</column>
        <operator>equals</operator>
        <value>Closed Won</value>
    </criteriaItems>
</filter>

Multi-value picklist: Use ONE criteriaItem with comma-separated values:

xml
<criteriaItems>
    <column>INDUSTRY</column>
    <operator>equals</operator>
    <value>Technology,Financial Services</value>
</criteriaItems>

Common operators: equals, notEqual, lessThan, greaterThan, contains, startsWith, includes, excludes, isBlank, notBlank. Full list in references/filter-operations.md.

Generation Workflow

  1. Gather Requirements — object, fields, groupings, filters, chart needs
  2. Determine Format — no groupings → Tabular; row groupings → Summary; row + column → Matrix; multiple objects → Joined
  3. Identify Column Names — call get_metadata_type_sections MCP tool to get valid platform column names for the report type
  4. Author Metadata — start from closest example in examples/ and adapt
  5. Create Folder — generate folder directory + <FolderName>-meta.xml with <folderShares>
  6. Validate — run through references/verification-checklist.md

Reference File Index

FileWhen to read
references/column-names.mdStep 3 — column name mappings per report type
references/date-intervals.mdWhen setting timeFrameFilter intervals
references/chart-types.mdWhen adding a chart — all 17 types + legendPosition rules
references/filter-operations.mdWhen building filters — complete operator reference
references/verification-checklist.mdStep 6 — pre-deploy validation
references/errors-and-troubleshooting.mdWhen fields are missing or deployment fails
examples/TabularOpportunitiesReport.report-meta.xmlTabular report template
examples/OpportunitiesByStageReport.report-meta.xmlSummary report with chart
examples/OpportunitiesByStageAndQuarter.report-meta.xmlMatrix report template
examples/AccountsCreatedThisYear.report-meta.xmlFiltered report with time frame
z tego samego repozytorium

Więcej Skills

Wszystkie Skills
forcedotcom
Społeczność

agentforce-d360-analyze

Data Cloud 360° view of a single Agentforce session. TRIGGER when user asks to trace, inspect, summarize, or describe a specific Agentforce session by session id (Agent Session UUID 019d… or MessagingSession id 0Mw…). Also triggers on session discovery — find/list/search sessions by time, agent, channel, outcome, or conversation text — when the user has no session id yet. DO NOT TRIGGER for design-time architecture questions (use agentforce-architecture-analyze instead) or for runtime perf/latency/SLO questions that require platform telemetry beyond Data Cloud.

instalacje
1
GitHub Stars
972
Aktualizacja
7 wrz
forcedotcom
Społeczność

agentforce-generate

Build, modify, audit, repair, optimize, debug, and deploy agents with Agentforce Agent Script. TRIGGER when: user creates, reviews, or changes .agent files or aiAuthoringBundle metadata; asks to fix AgentScript, audit an existing agent, run an AgentScript health check, common-pitfall review, or baseline-versus-candidate repair loop; changes a response, action, subagent, route, state flow, or Agent Spec; previews, debugs, deploys, publishes, or tests agents; uses sf agent generate/preview/publish/test; or manages Agentforce MCP servers, tools, assets, or authentication. DO NOT TRIGGER when: Apex, Flow, Prompt Template, Experience Cloud, or general Salesforce CLI work is unrelated to Agent Script; or the primary input is a production session or trace ID rather than an agent artifact.

instalacje
1
GitHub Stars
972
Aktualizacja
7 wrz
forcedotcom
Społeczność

platform-quick-deploy

Deploy validated metadata to a Production Salesforce org without re-running tests. TRIGGER when the user wants to deploy to production, says 'quick deploy', 'promote', 'ship to prod', or has just validated and wants to push the change live. REQUIRES a recent sf project deploy validate job ID (≤10 days old, ≤3 days for --use-most-recent). DO NOT TRIGGER for sandbox/scratch deploys (use platform-metadata-deploy) or unvalidated deploys (use platform-deploy-validate first).

instalacje
1
GitHub Stars
972
Aktualizacja
7 wrz
forcedotcom
Społeczność

agentforce-test

Write, run, and analyze structured test suites for Agentforce agents — functional AND security. TRIGGER when: user writes or modifies test spec YAML (AiEvaluationDefinition); runs sf agent test create, run, run-eval, or results commands; asks about test coverage strategy, metric selection, or custom evaluations; interprets test results or diagnoses test failures; asks about batch testing, regression suites, or CI/CD test integration; requests security testing, OWASP LLM Top 10, red-teaming, penetration testing, prompt-injection tests, a security grade, or a vulnerability assessment of an agent. DO NOT TRIGGER when: user creates, modifies, previews, or debugs .agent files (use agentforce-generate); deploys or publishes agents; writes Agent Script code; uses sf agent preview for development iteration; analyzes production session traces (use agentforce-observe); performs a static safety review of .agent file content (use agentforce-generate Section 15).

instalacje
3
GitHub Stars
972
Aktualizacja
7 wrz