Track and update action item status from natural language updates like 'Seanのメールには返信しておいた' or 'Lu対応予定'. Integrates with daily-comms-ops workflow. Use when managing action items across communication channels.
salesforce-cli-expert
This skill should be used when generating Salesforce CLI commands for tasks like authenticating to orgs, querying data with SOQL, retrieving metadata (profiles, permission sets, security settings), deploying configuration changes, or automating security audits. Use when the user describes what they want to accomplish with Salesforce and needs the specific CLI command syntax.
含まれるファイル(2)
- SKILL.md8.1 KB
- references/Salesforce_CLI_Usage_Guide.md18.6 KB
SKILL.md(原文)
インストールする前に、エージェントに与えられる指示の中身を確認できます。
Salesforce CLI Expert
Overview
This skill enables Claude to act as a Salesforce CLI expert, translating user requirements into precise sf CLI commands. It covers authentication, SOQL queries, metadata retrieval/deployment, and automation patterns specifically for security configuration management and org auditing.
When to Use This Skill
Invoke this skill when the user:
- Asks how to perform a Salesforce operation via CLI
- Needs to retrieve security configurations (profiles, permission sets, org settings, sharing rules)
- Wants to query user data, roles, or permission assignments
- Needs to deploy security updates or configuration changes
- Asks for automation patterns (JSON output, bulk operations, CI/CD integration)
- Requests examples of specific
sfor legacysfdxcommands
Example triggers:
- "How do I get all user profiles using Salesforce CLI?"
- "Show me the command to retrieve SecuritySettings metadata"
- "I need to query users with their MFA status"
- "How do I deploy a permission set to production?"
- "What's the CLI command to authenticate headlessly for CI/CD?"
Core CLI Operations
1. Authentication
Interactive web login (development):
sf org login web --alias <OrgAlias> --set-default
Headless JWT authentication (CI/automation):
sf org login jwt --username <user@example.com> \
--jwt-key-file <path/to/server.key> \
--client-id <OAuthClientId> \
--alias <Alias> \
--set-default
Auth URL authentication (pre-stored credentials):
sf org login sfdx-url --sfdx-url-file <authFile.json> \
--alias <Alias> --set-default
List authenticated orgs:
sf org list
Display default org details:
sf org display
2. Querying Data (SOQL)
Basic query with table output:
sf data query --query "SELECT Id, Name, Profile.Name FROM User LIMIT 10"
JSON output (recommended for automation):
sf data query --query "SELECT Id, Username, Email FROM User" --json
CSV output (for reports):
sf data query --query "SELECT Id, Username, Profile.Name FROM User" --result-format csv
Target specific org:
sf data query --query "SELECT Name FROM Account" --target-org <OrgAlias>
Bulk API for large datasets (>10,000 records):
sf data query --query "SELECT Id, Name FROM Contact" --bulk
Common security-related queries:
# Users with their profiles and roles
sf data query --query "SELECT Id, Username, Email, Profile.Name, UserRole.Name, IsActive FROM User"
# Permission set assignments
sf data query --query "SELECT Assignee.Username, PermissionSet.Name FROM PermissionSetAssignment"
# Users without MFA enabled (if field exists)
sf data query --query "SELECT Username, Email FROM User WHERE MfaEnabled__c = false"
# System Administrator users
sf data query --query "SELECT Username, Email FROM User WHERE Profile.Name = 'System Administrator' AND IsActive = true"
3. Retrieving Metadata
Generate manifest for all metadata in org:
sf project generate manifest \
--output-dir manifest \
--name allMetadata \
--from-org <OrgAlias>
Retrieve specific metadata types:
# Single type
sf project retrieve start --metadata Profile
# Multiple types
sf project retrieve start --metadata Profile,PermissionSet,Role
# Specific named components
sf project retrieve start --metadata Profile:Admin,PermissionSet:SecurityAuditor
Retrieve security-related metadata:
# Security settings and sharing rules
sf project retrieve start --metadata SecuritySettings,SharingRules
# All security configurations
sf project retrieve start --metadata SecuritySettings,SharingRules,Profile,PermissionSet,Role
Retrieve using manifest file:
sf project retrieve start --manifest manifest/package.xml
Legacy Metadata API retrieve (ZIP output):
sfdx force:mdapi:retrieve -r ./output-dir -u <alias> -k package.xml
4. Deploying Changes
Deploy specific metadata types:
sf project deploy start --metadata SecuritySettings,SharingRules
Validation-only deployment (check without applying):
sf project deploy start --metadata Profile:Admin --check-only
Deploy with manifest:
sf project deploy start --manifest manifest/package.xml
Deploy with test level control:
sf project deploy start --metadata PermissionSet:CustomPS \
--test-level RunLocalTests
Target specific org:
sf project deploy start --metadata SecuritySettings \
--target-org <OrgAlias>
5. Automation and Output Formatting
Force JSON output for all commands (set environment variable):
export SF_CONTENT_TYPE=JSON
# All subsequent commands will output JSON by default
Disable log files (recommended for production scripts):
export SF_DISABLE_LOG_FILE=true
Parse JSON output with jq (shell scripting):
sf data query --query "SELECT Name FROM Account" --json | jq '.result.records'
Example automation script pattern:
#!/bin/bash
export SF_CONTENT_TYPE=JSON
export SF_DISABLE_LOG_FILE=true
# Authenticate
sf org login jwt --username user@example.com \
--jwt-key-file server.key \
--client-id $CLIENT_ID \
--alias prod-org
# Query users
sf data query --query "SELECT Username, Profile.Name FROM User WHERE IsActive = true" \
--target-org prod-org \
--result-format csv > users_report.csv
# Retrieve security settings
sf project retrieve start --metadata SecuritySettings --target-org prod-org
Command Pattern Reference
Common Flags Across Commands
--target-org <alias>or-o <alias>: Target specific org--json: Output in JSON format--helpor-h: Display command help--result-format <format>: Output format (csv, json, human)
Migration: Old (sfdx) vs New (sf) Syntax
| Old (sfdx) | New (sf) |
|---|---|
sfdx force:org:list | sf org list |
sfdx force:org:display | sf org display |
sfdx force:data:soql:query -q "..." | sf data query --query "..." |
sfdx force:source:retrieve -m Type | sf project retrieve start --metadata Type |
sfdx force:source:deploy -m Type | sf project deploy start --metadata Type |
sfdx force:project:create -n Name | sf project generate --name Name |
Both syntaxes still work, but sf is the current standard.
Best Practices
- Always specify target org in automation: Use
--target-org <alias>to avoid ambiguity - Use JSON output for parsing: Add
--jsonor setSF_CONTENT_TYPE=JSON - Retrieve complete profiles: When retrieving Profile metadata, also retrieve related components or use a comprehensive manifest
- Validate before deploying: Use
--check-onlyflag to test deployments without applying changes - Handle API limits: Use
--bulkflag for queries returning >10,000 records - Secure credentials: Never hardcode JWT keys or auth URLs; use environment variables or secure vaults
- Version control metadata: Store retrieved metadata in Git for change tracking and rollback capability
References
For comprehensive CLI usage patterns, command examples, and security configuration automation workflows, refer to:
references/Salesforce_CLI_Usage_Guide.md - Complete guide covering:
- Setup and authentication methods
- Project setup and source tracking
- Metadata retrieval patterns
- SOQL query examples
- Deployment workflows
- Advanced security configuration management
- Continuous monitoring patterns
To access detailed information, read the reference file:
Read references/Salesforce_CLI_Usage_Guide.md
This reference contains in-depth explanations of command behavior, output formats, and real-world automation scenarios for security auditing and configuration management.
レビュー
まだレビューはありません。使ってみた感想をお寄せください。
同じリポジトリのスキル
概要と使いどころ
AI活用提案の専門コンサルタントスキル。LLM・AIエージェントの活用事例知識を基に、業界別、部門別、シーン別に最適なAI導入提案を行います。システム化、業務改善、効率化を得意とし、具体的な活用事例、期待効果、導入ステップを含む実践的な提案を提供します。Use when proposing AI/LLM adoption strategies for specific industries, departments, or business scenarios.
Generate AI-powered BPO service proposals for Japanese companies in the US market. Use when creating outsourcing proposals with AI service menus, ROI estimation, implementation roadmaps, and bilingual (JA/EN) proposal documents for 在米日系企業向けAI実装.
日本語の概要は準備中です。原文の説明を表示しています。
AI(LLM)が生成した日本語テキストの「AI臭」を検出・診断し、人間らしい文章にリライトするスキル。 Use when: 「AIっぽい文章を直して」「人間らしくリライトして」「AI臭を消して」「この文章をもっと自然にして」 「テキストのAI感を減らして」「機械っぽさを取りたい」 "make this sound more human", "remove AI tone", "humanize this text", "detect if this is AI-generated". 6つのAI特有パターン(視覚的マーカー、単調なリズム、マニュアル的構成、非コミット姿勢、抽象語の濫用、 定型メタファー)を正規表現ベースで検出し、0-100のAI臭スコアを算出。3つの人間化技法 (バランスを崩す・客観を崩す・論理を崩す)でリライトを実行する。 Note: 検出スクリプトは日本語テキスト専用。英語テキストの場合はClaude自身がreferences/を参照して分析・リライトする。
Generate audit-ready internal control design documents from As-Is business process inventories. Produces control IDs, assertion mappings, procedures, SoD analysis, KPIs, materiality thresholds, and implementation roadmaps. Use when building internal controls for new audit engagements, SOX/J-SOX compliance, or process improvement initiatives.
日本語の概要は準備中です。原文の説明を表示しています。
Review audit-related documents (control design documents, bottleneck analyses, requirements definitions, etc.) for quality, scoring them 0-100 with a severity-rated findings list. Use when reviewing audit documents, checking control design quality, or verifying cross-document consistency. Supports documents governed by US GAAP, IFRS, or J-GAAP.
日本語の概要は準備中です。原文の説明を表示しています。