Token导航 LogoToken导航

Agent Skill · 开发

sf-integration-procedure(SF 整合程序)

sf-integration-procedure 用于处理 GitHub 仓库、Issue、Pull Request 和代码协作信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要围绕仓库状态、代码变更或协作事项进行整理时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

sf-integration-procedure 是开发类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为调用外部服务;许可证信息还不明确,第三方扫描有提醒项,按安装量在开发类的 21,746 个 Skill 里排第 17,229。

总安装 428周安装 18GitHub Stars 401下载 150核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
unknown

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:sf-integration-procedure(SF 整合程序)
来源仓库:https://github.com/jaganpro/sf-skills
仓库路径:skills/sf-integration-procedure
安装命令:
npx skills add https://github.com/jaganpro/sf-skills --skill sf-integration-procedure
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/jaganpro/sf-skills --skill sf-integration-procedure

这个 Skill 是做什么的

开发类 Skill 面向写代码、改代码和排查问题,一般会读写仓库文件,部分还会执行构建或测试命令。

用于处理 GitHub 仓库、Issue、Pull Request 和代码协作信息。适合在需要围绕仓库状态、代码变更或协作事项进行整理时使用。可结合来源仓库和原始 README 核验具体用法。安装前建议确认权限范围、维护状态及是否触发联网或文件读写。安装方式:通过 npx 从指定 GitHub 仓库添加技能。

来源仓库内路径:skills/sf-integration-procedure

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/jaganpro/sf-skills --skill sf-integration-proc…;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要调用外部服务,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

sf-integration-procedure 怎么安装?

在终端执行 npx skills add https://github.com/jaganpro/sf-skills --skill sf-integration-procedure。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

sf-integration-procedure 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

sf-integration-procedure 需要什么权限?

权限级别是调用外部服务。该 Skill 可能调用第三方服务、云服务或外部模型 API,使用前需要确认账号、额度、数据发送范围和服务条款。

sf-integration-procedure 是免费的吗?

公开资料没有标注明确许可证,收费和商用限制都无法确认。正式使用前请到来源仓库核对授权说明。

sf-integration-procedure 用的人多吗?

公开数据是累计安装 428 次,近一周安装 18 次,下载 150 次,GitHub 401 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

sf-integration-procedure 安全吗?

第三方扫描有提醒项,说明存在需要人工确认的行为。安装前请打开源码看清它读了什么、联网到哪里。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。

先想清楚的地方

  • 许可证没有明确标注,能不能商用、能不能再分发都不确定。
  • 第三方扫描存在提醒项或未通过项,需要人工逐条确认。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理开发类任务、又不想每次都手写提示词的人。

不太适合

  • 需要明确授权才能用到公司项目里的场景。
  • 需要厂商级技术支持和 SLA 的生产系统。

开发类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
skill-vetter

技能审查员 · OpenClaw

8,779,018986操作浏览器MIT-0通过
ontology

本体论 · OpenClaw

6,636,960576只读MIT-0通过
entra-app-registration

内部应用程序注册 · Codex、Claude

6,631,872764接触敏感数据未明确通过
entra-app-registration

内部应用程序注册 · Codex、Claude

3,757,680201接触敏感数据未明确通过
nano-banana-pro

纳米香蕉专业版 · OpenClaw

3,526,898364接触敏感数据MIT-0有提醒
sf-integration-procedure

SF 整合程序 · 本页

428401调用外部服务未明确有提醒

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

sf-integration-procedure: OmniStudio Integration Procedure Creation and Validation

Expert OmniStudio Integration Procedure (IP) builder with deep knowledge of server-side process orchestration. Create production-ready IPs that combine DataRaptor/Data Mapper actions, Apex Remote Actions, HTTP callouts, conditional logic, and nested procedure calls into declarative multi-step operations.

Quick Reference

Scoring: 110 points across 6 categories. Thresholds: ✅ 90+ (Deploy) | ⚠️ 67-89 (Review) | ❌ <67 (Block - fix required)


Core Responsibilities

  1. IP Generation: Create well-structured Integration Procedures from requirements, selecting correct element types and wiring inputs/outputs
  2. Element Composition: Assemble DataRaptor actions, Remote Actions, HTTP callouts, conditional blocks, loops, and nested IP calls into coherent orchestrations
  3. Dependency Analysis: Validate that referenced DataRaptors, Apex classes, and nested IPs exist and are active before deployment
  4. Error Handling: Enforce try/catch patterns, conditional rollback, and response validation across all data-modifying steps

CRITICAL: Orchestration Order

sf-omnistudio-analyze -> sf-datamapper -> sf-integration-procedure -> sf-omniscript -> sf-flexcard (you are here: sf-integration-procedure)

Data Mappers referenced by the IP must exist FIRST. Build and deploy DataRaptors/Data Mappers before the IP that calls them. The IP must be active before any OmniScript or FlexCard can invoke it.


Key Insights

InsightDetails
ChainingIPs call other IPs via Integration Procedure Action elements. Output of one step feeds input of the next via response mapping. Design data flow linearly where possible.
Response MappingEach element's output is namespaced under its element name in the response JSON. Use %elementName:keyPath% syntax to reference upstream outputs in downstream inputs.
CachingIPs support platform cache for read-heavy orchestrations. Set cacheType and cacheTTL in the procedure's PropertySet. Avoid caching procedures that perform DML.
VersioningType/SubType pairs uniquely identify an IP. Use SubType for versioning (e.g., Type=AccountOnboarding, SubType=v2). Only one version can be active at a time per Type/SubType.

Core Namespace Discriminator: OmniStudio Core stores both Integration Procedures and OmniScripts in the OmniProcess table. Use IsIntegrationProcedure = true or OmniProcessType = 'Integration Procedure' to filter IPs. Without a filter, queries return mixed results.

CRITICAL — Creating IPs via Data API: When creating OmniProcess records, set IsIntegrationProcedure = true to make the record an Integration Procedure. The OmniProcessType picklist is computed from this boolean and cannot be set directly. Also, Name is a required field on OmniProcess (not documented in standard OmniStudio docs). Use sf api request rest --method POST --body @file.json for creation — the sf data create record --values flag cannot handle JSON textarea fields like PropertySetConfig.

Workflow Design (5-Phase Pattern)

Phase 1: Requirements Gathering

Before building, evaluate alternatives: Sometimes a single DataRaptor, an Apex service, or a Flow is the better choice. IPs are optimal when you need declarative multi-step orchestration with branching, error handling, and mixed data sources.

Ask the user to gather:

  • Purpose and business process being orchestrated
  • Target objects and data sources (Salesforce objects, external APIs, or both)
  • Type/SubType naming (e.g., Type=OrderProcessing, SubType=Standard)
  • Target org alias for deployment

Then: Check existing IPs via CLI query (see CLI Commands below), identify reusable DataRaptors/Data Mappers, and review dependent components with sf-omnistudio-analyze.

Phase 2: Design & Element Selection

Element TypeUse CasePropertySet Key
DataRaptor Extract ActionRead Salesforce databundle
DataRaptor Load ActionWrite Salesforce databundle
DataRaptor Transform ActionData shaping/mappingbundle
Remote ActionCall Apex class methodremoteClass, remoteMethod
Integration Procedure ActionCall nested IPipMethod (format: Type_SubType)
HTTP ActionExternal API calloutpath, method
Conditional BlockBranching logic--
Loop BlockIterate over collections--
Set ValuesAssign variables/constants--

Naming Convention: [Type]_[SubType] using PascalCase. Element names within the IP should describe their action clearly (e.g., GetAccountDetails, ValidateInput, CreateOrderRecord).

Data Flow: Design the element chain so each step's output feeds naturally into the next step's input. Map outputs explicitly rather than relying on implicit namespace merging.

Phase 3: Generation & Validation

Build the IP definition with:

  • Correct Type/SubType assignment
  • Ordered element chain with explicit input/output mappings
  • Error handling on all data-modifying elements
  • Conditional blocks for branching logic

Validation (STRICT MODE):

  • BLOCK: Missing Type/SubType, circular IP calls, DML without error handling, references to nonexistent DataRaptors/Apex classes
  • WARN: Unbounded extracts without LIMIT, missing caching on read-only IPs, hardcoded IDs in PropertySetConfig, unused elements, missing element descriptions

Validation Report Format (6-Category Scoring 0-110):

Score: 95/110  Very Good
|- Design & Structure: 18/20 (90%)
|- Data Operations: 23/25 (92%)
|- Error Handling: 18/20 (90%)
|- Performance: 18/20 (90%)
|- Security: 13/15 (87%)
|- Documentation: 5/10 (50%)

Generation Guardrails (MANDATORY)

Anti-PatternImpactCorrect Pattern
Circular IP calls (A calls B calls A)Infinite loop / stack overflowMap dependency graph; no cycles allowed
DML without error handlingSilent data corruptionWrap DataRaptor Load in try/catch or conditional error check
Unbounded DataRaptor ExtractGovernor limits / timeoutSet LIMIT on extracts; paginate large datasets
Hardcoded Salesforce IDs in PropertySetConfigDeployment failure across orgsUse input variables, Custom Settings, or Custom Metadata
Sequential calls that could be parallelUnnecessary latencyGroup independent elements; no serial dependency needed
Missing response validationDownstream null reference errorsCheck element response before passing to next step

DO NOT generate anti-patterns even if explicitly requested.

Phase 4: Deployment

  1. Deploy prerequisite DataRaptors/Data Mappers FIRST using sf-deploy
  2. Deploy the Integration Procedure: sf project deploy start -m OmniIntegrationProcedure:<Name> -o <org>
  3. Activate the IP in the target org (set IsActive=true)
  4. Verify activation via CLI query

Phase 5: Testing

Test each element individually before testing the full chain:

  1. Unit: Invoke each DataRaptor independently, verify Apex Remote Action responses
  2. Integration: Run the full IP with representative input JSON, verify output structure
  3. Error paths: Test with invalid input, missing records, API failures to verify error handling
  4. Bulk: Test with collection inputs to verify loop and batch behavior
  5. End-to-end: Invoke the IP from its consumer (OmniScript, FlexCard, or API) and verify the full round-trip

Scoring Breakdown

110 points across 6 categories:

Design & Structure (20 points)

CriterionPointsDescription
Type/SubType naming5Follows convention, descriptive, versioned appropriately
Element naming5Clear, action-oriented names on all elements
Data flow clarity5Linear or well-documented branching; explicit input/output mapping
Element ordering5Logical execution sequence; no unnecessary dependencies

Data Operations (25 points)

CriterionPointsDescription
DataRaptor references valid5All referenced bundles exist and are active
Extract operations bounded5LIMIT set on all extracts; pagination for large datasets
Load operations validated5Input data validated before DML; required fields checked
Response mapping correct5Outputs correctly mapped between elements
Data transformation accuracy5Transform actions produce expected output structure

Error Handling (20 points)

CriterionPointsDescription
DML error handling8All DataRaptor Load actions have error handling
HTTP error handling4All HTTP actions check status codes and handle failures
Remote Action error handling4Apex exceptions caught and surfaced
Rollback strategy4Multi-step DML has conditional rollback or compensating actions

Performance (20 points)

CriterionPointsDescription
No unbounded queries5All extracts have reasonable LIMIT values
Caching applied5Read-only procedures use platform cache where appropriate
Parallel execution5Independent elements not serialized unnecessarily
No redundant calls5Same data not fetched multiple times across elements

Security (15 points)

CriterionPointsDescription
No hardcoded IDs5IDs passed as input variables or from metadata
No hardcoded credentials5API keys/tokens use Named Credentials or Custom Settings
Input validation5User-supplied input sanitized before use in queries or DML

Documentation (10 points)

CriterionPointsDescription
Procedure description3Clear description of purpose and business context
Element descriptions4Each element has a description explaining its role
Input/output documentation3Expected input JSON and output JSON structure documented

CLI Commands

# Query active Integration Procedures
sf data query -q "SELECT Id,Name,Type,SubType,IsActive FROM OmniProcess WHERE IsActive=true AND IsIntegrationProcedure=true" -o <org>

# Query all Integration Procedures (including inactive)
sf data query -q "SELECT Id,Name,Type,SubType,IsActive,LastModifiedDate FROM OmniProcess WHERE IsIntegrationProcedure=true ORDER BY LastModifiedDate DESC" -o <org>

# Retrieve an Integration Procedure
sf project retrieve start -m OmniIntegrationProcedure:<Name> -o <org>

# Deploy an Integration Procedure
sf project deploy start -m OmniIntegrationProcedure:<Name> -o <org>

# Deploy with dry-run validation first
sf project deploy start -m OmniIntegrationProcedure:<Name> -o <org> --dry-run

Core Namespace Note: The IsIntegrationProcedure=true filter is REQUIRED (or equivalently OmniProcessType='Integration Procedure'). OmniScript and Integration Procedure records share the OmniProcess sObject. Without this filter, queries return both types and produce misleading results.


Cross-Skill Integration

From SkillTo sf-integration-procedureWhen
sf-omnistudio-analyze-> sf-integration-procedure"Analyze dependencies before building IP"
sf-datamapper-> sf-integration-procedure"DataRaptor/Data Mapper is ready, wire it into IP"
sf-apex-> sf-integration-procedure"Apex Remote Action class deployed, configure in IP"
From sf-integration-procedureTo SkillWhen
sf-integration-procedure-> sf-deploy"Deploy IP to target org"
sf-integration-procedure-> sf-omniscript"IP is active, build OmniScript that calls it"
sf-integration-procedure-> sf-flexcard"IP is active, build FlexCard data source"
sf-integration-procedure-> sf-omnistudio-analyze"Verify IP dependency graph before deployment"

Edge Cases

ScenarioSolution
IP calls itself (direct recursion)Block at design time; circular dependency check is mandatory
IP calls IP that calls original (indirect recursion)Map full call graph; sf-omnistudio-analyze detects cycles
DataRaptor not yet deployedDeploy DataRaptors first; IP deployment will fail on missing references
External API timeoutSet timeout values on HTTP Action elements; implement retry logic or graceful degradation
Large collection input to Loop BlockSet batch size; test with realistic data volumes to avoid CPU timeout
Type/SubType collision with existing IPQuery existing IPs before creating; SubType versioning avoids collisions
Mixed namespace (Vlocity vs Core)Confirm org namespace; element property names differ between packages

Debug: IP not executing -> check IsActive flag + Type/SubType match | Elements skipped -> verify conditional block logic + input data shape | Timeout -> check DataRaptor query scope + HTTP timeout settings | Deployment failure -> verify all referenced components deployed and active


Notes

Dependencies (optional): sf-deploy, sf-datamapper, sf-omnistudio-analyze | API: 66.0 | Mode: Strict (warnings block) | Scoring: Block deployment if score < 67 | See references/best-practices.md and references/element-types.md for detailed guidance.

Creating IPs programmatically: Use REST API (sf api request rest --method POST --body @file.json). Required fields: Name, Type, SubType, Language, VersionNumber, IsIntegrationProcedure=true. Then create OmniProcessElement child records for each action step (also via REST API for JSON PropertySetConfig). Activate by setting IsActive=true after all elements are created.

平台分布

Codex

39.06%
按下载量换算59

Claude

29.55%
按下载量换算44

Cursor

19.21%
按下载量换算29

Gemini CLI

9.46%
按下载量换算14

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

可疑

权限和风险

调用外部服务

该 Skill 可能调用第三方服务、云服务或外部模型 API,使用前需要确认账号、额度、数据发送范围和服务条款。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在提醒或未通过项,安装前请自行复核。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills