controlling-al-access

Controls visibility of AL objects and fields using Access property (Public, Internal, Protected, Local), hides internal helpers from external apps, exposes public API surfaces, and configures internalsVisibleTo for multi-app scenarios. Use when making codeunits private, hiding staging tables, protecting fields from partners, or sharing internals between companion apps.

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

75%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, actionable skill body with sequenced steps and validation gates, concrete AL examples, and useful reference tables. The main weaknesses are mild redundancy (security-boundary caveat stated twice, two overlapping tables) and implicit rather than explicit gate-failure recovery.

Suggestions

Deduplicate the 'not a security boundary / RecordRef-FieldRef runtime bypass' note — state it once in Important Notes and reference it from Validation Gates.

Add a short 'If a validation gate fails' branch (e.g. compile error persists → recheck Access property spelling and object ID range) to make the feedback loop explicit.

Merge or cross-link the Access Level Summary table and the Quick Reference table to remove overlap, or move the larger Design Patterns block into a references/ file as the skill grows.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with concrete code and tables, but the 'NOT a security boundary / RecordRef-FieldRef bypass' point is restated in both the Validation Gates note and the Important Notes section, and the Access Level Summary table overlaps the Quick Reference table.	4 / 5
Actionability	Provides concrete, mostly copy-paste-ready AL code with a Quick Reference recommendation table; minor gaps include the <ID>/<PREFIX> placeholders and the Secret Manager example abbreviating the IsolatedStorage call to a comment.	4 / 5
Workflow Clarity	Clear Step 1/2/3 sequence with an explicit Validation Gates checklist (compile-error checkpoints after each step), but error-recovery guidance for a failed gate is implied rather than spelled out.	4 / 5
Progressive Disclosure	Well-organized into clearly labeled sections with one-level-deep external links to Microsoft Learn; no bundle files exist so the body is self-contained, though some inline content (Design Patterns, Quick Reference) could be split into references if the skill grows.	4 / 5
	Total	16 / 20 Passed

Description

92%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, specific description that clearly states capabilities and concrete use-when triggers tied to AL Access modifiers. Minor room to surface a couple more natural trigger synonyms, but it is comprehensive and low-conflict.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions with enumerated Access levels — 'Controls visibility... using Access property (Public, Internal, Protected, Local)', 'hides internal helpers', 'exposes public API surfaces', 'configures internalsVisibleTo' — giving comprehensive coverage rather than vague abstraction.	5 / 5
Completeness	Explicitly answers both what ('Controls visibility... configures internalsVisibleTo') and when ('Use when making codeunits private, hiding staging tables...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Natural developer phrases like 'making codeunits private', 'hiding staging tables', 'protecting fields from partners', and 'sharing internals between companion apps' cover the common cases well, though a few natural synonyms (e.g. 'Access property' as a trigger, 'exposing API') are only implicit in the what-clause.	4 / 5
Distinctiveness Conflict Risk	Narrowly scoped to AL/Business Central Access modifiers and internalsVisibleTo, with distinct triggers that make overlap with unrelated skills unlikely.	5 / 5
	Total	19 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: emgreppi/Business-Central-AI-Skill
Path: controlling-al-access/SKILL.md
Commit: 52f8705

Reviewed: 1 day ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.