Claude Marketplaces
SkillsMCP serversMarketplacesDigestTools
Submit

This week in Claude

Every Monday: Claude Code, Agent SDK, MCP, and the Anthropic platform moves worth your time.

Skills by category
Frontend DevelopmentBackend & APIsTesting & QASecurityDevOps & CI/CDGit & Pull RequestsDocumentationCode Review & QualityAI & Agent BuildingSkill Development
MCP servers by category
Sales & MarketingWeb & Browser AutomationDatabasesAI & LLM ToolsCloud & InfrastructureCommunication & MessagingDeveloper ToolsDesign & CreativeDocuments & KnowledgeSearch & Web Crawling
Marketplaces by category
AI Agents & OrchestrationLLM IntegrationDevelopment ToolsFrontend & UIBackend & APIsDatabasesTesting & Code QualityDevOps & CloudSecurity & ComplianceGit & Version Control
Claude Marketplaces

An independent directory of skills, plugins and MCP servers for Claude Code. Not affiliated with Anthropic.

Browse

  • Skills
  • MCP servers
  • Marketplaces
  • Weekly digest
  • Skill index
  • MCP index
  • Marketplace index

Site

  • About
  • Tools
  • Submit
  • Feedback
  • Privacy
  • llms.txt
  • Plugins reference

Maker

  • Snug
  • Agent Caffeine
  • knobs
  • Wax
  • Vectoys
  • mertduzgun.com
Crafted at
Skills
jaganpro avatar

Sf Permissions

jaganpro/sf-skills

This is what you reach for when someone asks "who can see this field?" or "why does this user have access to X?" in Salesforce. It analyzes permission sets and permission set groups, traces hierarchies, and pinpoints exactly which grants give access to objects, fields, Apex classes, flows, or custom permissions. The workflow is smart about using stable metadata names over record IDs and clearly separates direct assignments from inherited group permissions. Inspired by Oumaima Arbani's PSLab, it handles the detective work of access auditing and then hands off to other skills when you need to actually create or deploy permission changes. The output focuses on evidence: what was analyzed, which permissions granted access, and whether it came directly or through a group.

installs
1.4K
GitHub stars
424
last updated
Jul 14, 2026
View on GitHubSave

Install

$ npx -y skills add jaganpro/sf-skills --skill sf-permissions --agent claude-code

Installs into .claude/skills of the current project.

Files

sf-permissions

Use this skill when the user needs permission analysis and access auditing: Permission Set / Permission Set Group hierarchy views, “who has access to X?” investigations, user-permission analysis, or permission-set metadata review.

When This Skill Owns the Task

Use sf-permissions when the work involves:

  • permission set / permission set group analysis
  • user access investigation
  • finding which permission grants object / field / Apex / flow / tab / custom-permission access
  • auditing or exporting permission configuration
  • reviewing permission metadata impacts

Delegate elsewhere when the user is:

  • creating new metadata definitions → sf-metadata
  • deploying permission sets → sf-deploy
  • analyzing Apex-managed sharing logic → sf-apex

Required Context to Gather First

Ask for or infer:

  • target org alias
  • whether the question is about an object, field, Apex class, flow, tab, custom permission, or specific user
  • whether the goal is hierarchy visualization, access detection, export, or metadata generation
  • whether the output should be terminal-focused or documentation-friendly

Recommended Workflow

1. Classify the request

Request shapeDefault capability
“who has access to X?”permission detector
“what does this user have?”user analyzer
“show me the hierarchy”hierarchy viewer
“export this permset”exporter
“generate metadata from analysis”generator or handoff

2. Connect to the correct org

Verify sf auth before running permission analysis.

3. Use the narrowest useful query

Prefer focused analysis over broad org-wide scans unless the user explicitly wants a full audit.

When choosing identifiers, prefer stable metadata names first:

  • PermissionSet.Name
  • PermissionSetGroup.DeveloperName
  • CustomPermission.DeveloperName
  • object and field API names such as Account or Account.AnnualRevenue
  • Assignee.Username / email for user-centric checks

Use Salesforce record IDs only when:

  • the underlying object model requires ParentId or SetupEntityId, or
  • you are drilling into records returned by a prior read-only query in the same investigation

4. Render findings clearly

Use:

  • ASCII tree or table output for terminal work
  • Mermaid only when documentation benefit is clear
  • concise summaries of which permission source grants access

5. Hand off creation or deployment work

Use:

  • sf-metadata for richer metadata generation
  • sf-deploy for deployment

High-Signal Rules

  • distinguish direct Permission Set grants from grants via Permission Set Groups
  • prefer Name / DeveloperName / API names over org-specific record IDs for first-pass investigation queries
  • be explicit about whether access is object-level, field-level, class-level, flow-level, or custom-permission-based
  • use Tooling API where required for setup entities and advanced visibility questions
  • for agent access questions, verify exact agent-name matching in permission metadata
  • when a follow-up child query requires ParentId or SetupEntityId, resolve the ID from a prior result instead of starting with copied IDs

Output Format

When finishing, report in this order:

  1. What was analyzed
  2. Org / subject scope
  3. Which permissions grant access
  4. Whether access is direct or inherited
  5. Recommended follow-up

Suggested shape:

Permission analysis: <hierarchy / detect / user / export>
Scope: <org, user, permission target>
Findings: <permsets / groups / access level>
Source: <direct assignment or via group>
Next step: <export, generate metadata, or deploy changes>

Cross-Skill Integration

NeedDelegate toReason
generate or modify permission metadatasf-metadatametadata authoring
deploy permission changessf-deployrollout
identify Apex classes needing grantssf-apeximplementation context
bulk user assignment analysissf-datalarger data operations

Reference Map

Start here

  • references/permission-model.md
  • references/soql-reference.md
  • references/workflow-examples.md

Specialized analysis

  • references/agent-access-guide.md
  • references/usage-examples.md

Score Guide

ScoreMeaning
90+strong permission analysis with clear access sourcing
75–89useful audit with minor gaps
60–74partial visibility only
< 60insufficient evidence; expand analysis
SKILL.md on GitHub

Sponsors

SnugThe clipboard manager you and your agent can use, safelyAgent CaffeineClose your lid, come back to finished workWaxBlock anything with supervision, without erasing your iPhoneOpen StepsSponsoredFree and open-source skills that make AI coding agents easier to understand, verify, and control.

Details

Repository
github.com/jaganpro/sf-skills
First seen
Apr 16, 2026

More from jaganpro/sf-skills

All 37
  • Sf Testing1.4K
  • Sf Data1.4K
  • Sf Integration1.4K
  • Sf Diagram Mermaid1.4K
  • Sf Connected Apps1.4K
  • Sf Ai Agentscript1.4K
  • Sf Diagram Nanobananapro1.3K
  • Sf Ai Agentforce1.3K
  • Sf Ai Agentforce Testing1.3K
  • Sf Ai Agentforce Observability1.3K
  • Sf Docs1.2K
  • Sf Ai Agentforce Persona1.2K
  • Sf Datacloud1K
  • Sf Industry Commoncore Omniscript990
  • Sf Industry Commoncore Datamapper987
  • Sf Industry Commoncore Omnistudio Analyze986
  • Sf Industry Commoncore Flexcard984
  • Sf Datacloud Retrieve982
  • Sf Datacloud Connect980
  • Sf Industry Commoncore Integration Procedure980
  • Sf Datacloud Prepare979
  • Sf Datacloud Segment976
  • Sf Datacloud Harmonize973
  • Sf Datacloud Act972

Recommended

1juliusbrussee avatarcavemanjuliusbrussee/cavemanUltra-compressed communication mode. Cuts output tokens 65% (measured) by speaking like caveman while keeping full technical accuracy. Supports intensity levels594.9Kinstalls
2mattpocock avatargrill-memattpocock/skillsA relentless interview to sharpen a plan or design.1.4Minstalls
3shadcn avatarimproveshadcn/improveSurvey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for OTHER models/agents to execute. Strictly read-only on s37.9Kinstalls
4obra avatarsystematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes309.2Kinstalls
5forrestchang avatarkarpathy-guidelinesforrestchang/andrej-karpathy-skillsBehavioral guidelines to reduce common LLM coding mistakes through explicit assumptions, simplicity, and verifiable success criteria.17.9Kinstalls
6vercel-labs avatarfind-skillsvercel-labs/skillsHelps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express int4.1Minstalls