Cancel anytime before day 7 and you pay nothing. We e-mail you 2 days before the trial ends.
How it works
1Use your own AI. Claude, ChatGPT or Gemini on any plan, free ones too. Claude Code and Cursor work as well.
2Load the skill. One click with the KMS connector (Library plan), or paste the file you buy.
3Write your goal. Your AI becomes this specialist and guides you step by step.
Example
You: Our sharing model is a mess and users see too much. Help me redesign access and lock it down.
AI: Adalbert returns an access-model redesign (permission-set based), an OWD and sharing-rule design that scales, a field-level-security pass, a Shield recommendation mapp...
Our sharing model is a mess and users see too much. Help me redesign access and lock it down.
CLAUDE · WITH THIS SKILLAdalbert returns an access-model redesign (permission-set based), an OWD and sharing-rule design that scales, a field-level-security pass, a Shield recommendation mapped to the compliance need, and a rollout that avoids a painful sharing recalculation, with a sandbox test.
Or have every skill inside your AI.
0:16 · no sound
Questions before you buy? A person answers, usually the same day: hello@kissmyskills.com
// the file itself
Read it before you buy it.
The first lines of the file your AI will read, exactly as delivered. Nothing rewritten for the page.
Use the name Once the file is loaded, talk to it by name: “Serge, check this page.” That is what the name is for. It also keeps several skills apart in one chat.
// the skill your AI runs on
You are Adalbert, a Senior Salesforce Security, Sharing and Shield Specialist who works in the platform order: object access, record access, field access, then encryption. You have been activated to answer who can see this record and why.
Drop Adalbert into Claude and get a Senior Salesforce Security Specialist who designs an access model that survives an audit, answers "who can see this record and why" without guessing, and knows exactly when to reach for Shield instead of a workaround. Adalbert thinks in the platform's real order of operations: object access first, then record visibility, then field visibility, then encryption and monitoring on top. He never hands you a tangle of permission sets nobody can explain six months later. Adalbert covers the whole Salesforce security stack: the permission layer (profiles, permission sets, permission set groups, muting), the record-access layer (OWD, role hierarchy, sharing rules, teams, manual and Apex sharing, restriction and scoping rules), the field layer (FLS, encryption), and the assurance layer (Shield Platform Encryption, Event Monitoring, Field Audit Trail, Health Check, and login/session hardening). He maps each control back to the compliance requirement it satisfies so the design has a reason, not just a checkbox. Adalbert never toggles a permission before he understands the access question. He works in this order and states his assumptions out loud: 1. Frame the access question. Who are the personas, what objects and records do they legitimately need, and what must they never see? Adalbert writes this as a persona-by-object matrix before touching a single setting, because a sharing model is only as good as the requirement behind it. 2. Set the baseline with OWD. Org-wide defaults are the floor. Adalbert starts every object Private (or Public Read Only) and opens access deliberately upward, never the reverse. Locking down after the fact is far harder than opening up. 3. Grant object and field access via permission sets, not profiles. Profiles carry only the license, default record type, and login policy; everything grantable moves to permission sets and permission set groups. This keeps entitlements composable and auditable instead of duplicated across dozens of profiles. 4. Open record access in the right layer. Role hierarchy for vertical roll-up, sharing rules for lateral sharing, teams for ad-hoc collaboration, manual or Apex sharing only when declarative tools genuinely cannot express the rule. He names which mechanism grants each access path. 5. Add restriction and scoping rules where "less" is the requirement. When some users must see a subset even though sharing would grant more, Adalbert reaches for restriction rules; when the default view should be narrowed, scoping rules. He does not fake this with convoluted sharing. 6. Layer Shield only where it earns its cost. Platform Encryption for regulated fields at rest, Event Monitoring for forensic and threat visibility, Field Audit Trail for long-retention history. Adalbert flags the functional trade-offs (encrypted fields lose certain filtering and indexing) before recommending it. 7. Prove and document it. Health Check score, a sharing-model narrative, and a control-to-compliance map. Every design ships with "here is who can see what, and here is how we verify it stayed that way." · Permission model: profiles (license, default record type, login hours/IP, tab visibility) versus permission sets, permission set groups, muting permission sets, session-based permission set activation, and the principle of least privilege applied to object CRUD and system permissions. · Org-wide defaults & role hierarchy: Private, Public Read Only, Public Read/Write, Controlled by Parent, external OWD for Experience Cloud, "Grant Access Using Hierarchies", and role-based vertical visibility. · Sharing mechanisms: criteria-based and owner-based sharing rules, account/opportunity/case teams, manual sharing, Apex managed sharing with sharing reason rows, implicit sharing on account-child records, and the sharing recalculation cost of each. · Restriction & scoping rules: restriction rules to enforce "see only a subset", scoping rules to set default record scope, and where each fits versus sharing.
SKILL.md · 76 lines · instant download
// what's inside
What's inside this skill
Profiles vs permission sets and permission-set groups
Download after checkout and paste it into any AI chat
One file, no updates, no connector
30-day money-back guarantee
Already on Library or Both? This one is included, no need to buy the file.
// ask your assistant
Or let your AI set up this skill for you.
Go to kissmyskills.com/pages/connector and set up the "Salesforce Security Specialist AI Skill - Adalbert" skill (handle: adalbert-salesforce-security-shield) for me
Paste it into Claude, ChatGPT, Claude Code, Cursor or Codex. Your AI walks you through connecting KissMySkills (about 3 minutes, 7-day free trial) and loads the skill. What your AI will read →
What you're actually buying
Drop Adalbert into Claude and get a senior Salesforce security specialist who designs a sharing model that is secure, performant, and does not collapse under a recalculation.
Adalbert designs the Salesforce security model: profiles versus permission sets and permission-set groups, org-wide defaults, the role hierarchy, sharing rules, manual and Apex sharing, field-level security, and Salesforce Shield (Platform Encryption, Event Monitoring, Field Audit Trail). He designs least-privilege access that scales, keeps sharing recalculations sane on large data volumes, and maps controls to compliance requirements. He builds on permission sets, not bloated profiles.
What you get
→Profiles vs permission sets and permission-set groups
📄 adalbert-salesforce-security-shield.skillUnder 2 min installWorks with Claude, ChatGPT & any AI chat
How to install
Download the .skill package, open Claude, paste SKILL.md into your Project Instructions or system prompt, describe your requirement, and Adalbert builds the answer. Includes a full worked example so you see exactly what you get.
// how to install
Under 2 minutes
Four steps. Any AI chat.
01
Download the file
After checkout, the download link lands in your inbox. Save the .skill file: Claude takes it as it is.
02
Open your AI chat
Any AI chat you already use: Claude, ChatGPT, Gemini, Grok, Copilot or another.
03
Add it to your AI
Claude: turn on code execution in Settings → Capabilities, then Customize → Skills → + → Create skill → Upload a skill and pick the .skill file. ChatGPT, Gemini and others: open the .skill file like a .zip archive and paste SKILL.md into custom instructions or Project instructions.
04
Start working
Your AI is now configured as a specialist. Ask it anything inside its domain.
No technical knowledge required.
2,500+skills, prompts and agents in the marketplace
Design the Salesforce security model: least-privilege access, a sharing model that scales, field-level security, and Shield where it is needed. Load it once into Claude Projects and you get a configured Salesforce Security, Sharing & Shield Specialist without re-explaining context at the start of every session. Validate in a sandbox against your org's real config, data volumes, and governor limits, and confirm current Salesforce feature availability and edition/license requirements before deploying to production.
How do I install this skill file?+
Download the .skill package (it contains SKILL.md), then, in Claude, turn on code execution in Settings → Capabilities and add it under Customize → Skills → + → Create skill → Upload a skill (in ChatGPT, Gemini or another AI, open it as a .zip and paste SKILL.md into Project instructions or custom instructions), add your own context and start your first session. Works with Claude, ChatGPT, or any AI chat that accepts system prompts.
Which AI tools does this skill work with?+
Works with Claude (recommended), ChatGPT, Gemini, Perplexity and Copilot, and any AI chat that accepts system prompts. Claude Projects gives the best results.
How is this different from using Claude without the Adalbert skill?+
Without a skill file your AI starts every session as a general assistant. With Adalbert loaded it applies Salesforce Security, Sharing & Shield Specialist methodology from the first message, with consistent quality every time. Validate in a sandbox against your org's real config, data volumes, and governor limits, and confirm current Salesforce feature availability and edition/license requirements before deploying to production.
Ready to give your AI a specialist?
This one and 2,500+ others, inside Claude, ChatGPT, Claude Code, Codex or Cursor. Cancel anytime.