Flemming Bakkensen
Community@FBakkensen
Flemming Bakkensen provides a 22-skill agentic development pipeline for AL/Business Central, covering design, TDD implementation, refactoring, mutation testing, and release documentation.
Agent Skills by Flemming Bakkensen
Showing 22 vetted skills indexed across 1 GitHub repositories.
al-refine
Generates Test Specifications and Verification Plans for AL/Business Central tasks.
al-refactor
Refactors AL/Business Central code through four parallel review lenses while keeping builds green.
al-grill-adr
Interviews users to resolve Business Central domain terminology and records decisions in CONTEXT.md and ADRs.
al-debug-logging
Adds temporary DEBUG-* FeatureTelemetry probes to AL code to inspect runtime behavior via telemetry.jsonl.
al-build
Compiles, publishes, and tests AL/Business Central apps through a single PowerShell build gate.
al-steer
Analyzes AL task folders to name next steps, blockers, and replan triggers.
al-event-model
Drafts user-facing journey timelines as event-model.md in Business Central vocabulary.
al-validate-breaking-changes
Runs AppSource-style breaking-change validation against a cached baseline and flips the task status.
al-second-opinion
Dispatches artifacts to GitHub Copilot CLI for independent cross-family gap review.
al-provision
Runs the provision task to refresh the AL build environment and flips task status.
al-mutate
Validates AL test rigor by injecting one mutation at a time and classifying killed, surviving, or equivalent mutants.
al-quiz
Quizzes developers on recently shipped AL/Business Central changes one question at a time.
al-scope
Decomposes architecture.md into slice-grouped task files for AL/Business Central development.
al-user-verification
Guides users through manual verification of AL/Business Central feature slices in the Web Client.
al-agentic-dev-overview
Emits a static orientation document describing the al-agentic-dev plugin pipeline and skill catalogue.
al-code-review
Reviews AL/Business Central code diffs at slice and feature gate boundaries with parallel review lenses.
al-design
Produces feature-level architecture documents for AL and Business Central development.
al-page-script
Guides users to record and replay Business Central Page Scripting E2E test scenarios.
al-implement
Drives AL tasks red to green through TDD for Business Central.
al-research
Verifies AL and Business Central facts against authoritative sources with verbatim quotes and citations.
release-notes
Generate release notes from per-PR analysis of merged pull requests since the last release.
grill-me
Interviews the user question-by-question to stress-test plans and design decisions.
Frequently Asked Questions About Flemming Bakkensen
FAQPage SchemaWhat tasks can I accomplish with FBakkensen's AL skills?▼
You can run the full AL/Business Central feature lifecycle: grill requirements into ADRs, model events, design architecture, scope tasks, provision build environments, implement via TDD, refactor with green tests, mutation-test rigor, review code, verify slices with users, validate breaking changes, and generate release notes.
Who are these AL agentic development skills designed for?▼
They target AL/Business Central developers and consultants building BC extensions who want a structured, agent-assisted pipeline. The skills assume familiarity with BC vocabulary, the tasks/ folder convention, and artifacts like event-model.md, architecture.md, and CONTEXT.md.
How do the AL skills execute builds and tests in practice?▼
The al-build skill runs compilation, publishing, and test execution as a single gated command after any AL code change. al-provision refreshes the compiler, symbols, and breaking-change baseline via provision.ps1, while al-validate-breaking-changes runs validate-breaking-changes.ps1 against that baseline.
What prerequisites do these Business Central skills require?▼
Skills expect an AL/Business Central project with a tasks/ folder, provisioned BC containers for test execution and Page Scripting replay, and design artifacts like event-model.md or architecture.md for later pipeline stages. al-second-opinion additionally requires the GitHub Copilot CLI pinned to a GPT model.
How does the pipeline ensure test quality beyond passing tests?▼
The al-mutate skill injects one mutation at a time into AL code, runs the script-backed build gate, and reports killed, surviving, and equivalent mutants. This exposes weak assertions after refactoring or on legacy code, ensuring tests genuinely fail when behavior breaks rather than merely passing green.