Workshop ALDC
Block 02 · ALDC
🇪🇸 🇬🇧
Block 02

ALDC + Agent Skills + Skills Evidencing

ALDC Core v1.1 architecture presented in 5 layers. The ~44 composable pieces grouped into 4 families. Live installation from VS Code Marketplace. Skills Evidencing — the pattern that makes the agent auditable. skill-diagnostics demo.

Live ALDC installation

The block opens by grounding ALDC. The extension is installed from the Marketplace and the .github/ tree is populated live. From this point, everything discussed has a real reference on screen.

Starting point: the repo-starter has a clean .github/ — only copilot-instructions.md (workshop contract) and skills/skill-diagnostics/SKILL.md (the workshop-specific skill).

starting tree · only 2 files
.github/
├── copilot-instructions.md          ← workshop contract
└── skills/
    └── skill-diagnostics/
        └── SKILL.md                 ← workshop-specific skill

The 3 installation steps

1

Install the extension from Marketplace

Ctrl+Shift+X → search "AL Development Collection" → publisher JavierArmestoGonzalezInstall

2

Copy ALDC to the workspace

Ctrl+Shift+P → "AL Collection: Install Toolkit to Workspace" → Enter. This second step is key: what ends up in the repo is versionable, it doesn't depend on the extension being installed on every machine.

3

Refresh the explorer

Watch .github/ populate with agents/, instructions/, prompts/, skills/, workflows/. The workshop contract and original skill remain intact.

ALDC adds, it doesn't overwrite. The workshop contract is preserved, the custom skill is preserved. Open ecosystem, not a closed platform.

ALDC Architecture · 5 layers

Human · HITL

Human layer

decisions.md · memory.md · approvals. The human signs, the agent executes.

Orchestration

Orchestration layer

al-conductor as thin-router. Doesn't generate code, coordinates subagents.

Roles

Roles layer

al-architect · al-spec.create (workflow) · al-planning · al-implement · al-review (subagents)

Skills

Skills layer

15 on-demand skills loaded by agents. Not code — they are contracts with frontmatter + patterns + constraints.

Contract

Contract layer

copilot-instructions.md · app.json · 7 instructions auto-applied by file type

The 3 non-negotiable pillars

01

Spec-driven

Nothing is implemented without an approved spec.

02

HITL gates

Plan approval, phase commit, PR. Human between phases.

03

Skills Evidencing

Each agent declares which skill it loaded and which pattern it applied.

If something violates one of the three pillars, it's not ALDC.

The 4 families · ~44 real pieces

Real numbers from the repo · ALDC Core v1.1

TypeQuantityWhat they are
Public agents4al-architect, al-conductor, al-developer, al-presales
Subagents3al-planning, al-implement, al-review (invoked by the conductor)
Skills1511 core + 3 BC Agents pack + 1 integration (extension-manifest)
Workflows106 public + 4 from BC Agents pack
Instructions7Auto-applied according to file type
Extra1al-agent-builder (from BC Agents pack)
TOTAL~44composable pieces

Grouped by cycle stage

Diagnostics and analysis
skill-diagnostics, skill-debug, skill-performance
Before writing and during review
Generation and design
skill-api, skill-events, skill-pages, skill-copilot, skill-permissions
Design and implementation
Orchestration
al-conductor, al-planning/implement/review-subagent
TDD + HITL coordination
Evidence and control
Skills Evidencing, memory.md, decisions.md
Cross-cutting, always active

Anatomy of a skill

All ALDC skills share the same canonical structure. Once you understand this anatomy, reading any new skill takes 30 seconds.

An ALDC skill is not a pretty prompt. It's a contract with frontmatter, patterns, workflow, constraints and cross-references. If any part is missing, it's not a skill — it's a trick.

Skills Evidencing · "where did the agent get this decision from?"

Every team that has put LLMs into production has asked this question. And the answer "just because" blocks adoption in any regulated context — audits, AppSource, enterprise contracts.

Skills Evidencing is the mechanism so the question has an answer.

The 5 evidence formats

Agent / roleWhere it emits evidenceFormat
al-architectTop of architecture.md> **Skills applied**: skill-api, skill-events
al-developerStart of each response> **Skills loaded**: skill-debug (root cause analysis)
al-implement-subagentPhase Summary to conductor### Skills Loaded section
al-review-subagentCode reviewSkills Compliance Check table
al-conductorphase-complete.md, plan-complete.mdSkills Applied table + Utilization Summary

Evidence travels bottom-up. The subagent declares what it loaded, the review validates it was applied, the conductor consolidates in the phase-complete. When someone opens the PR, they have the full chain.

Skills Evidencing doesn't replace human review — it facilitates it. The human still decides, but now decides with information. If the subagent says it loaded skill-performance but the code has no SetLoadFields, the review-subagent flags it as Major. The system audits itself.

skill-diagnostics · static audit against the contract

skill-diagnostics is the workshop-specific skill, created to debut today and be incorporated into the ALDC catalog. It complements skill-performance: where performance does runtime triage, diagnostics does static auditing against the project contract.

Anatomy of skill-diagnostics

NEVER modifies code. NEVER invents rules. This is what separates a production skill from a clever prompt.

Invocation in Copilot Chat

natural language invocation
Load skill-diagnostics and scan the workspace. Follow the output format strictly and include the Skills Applied block at the end.

Copilot finds the skill by its frontmatter description. In ALDC Core v1.1 this replaced @file references — it's more natural and the catalog self-publishes to the Copilot Chat ecosystem.

Expected findings in the report

The defective output from Block 1 (or the pre-loaded fallback) contains these intentional defects, each associated with a class and severity:

Table without DataClassification at object level Compliance Blocker
Field without ToolTip Compliance Major
Public procedure without XML doc Code quality Major
Object without entry in permission set Permissions Major
Hardcoded numeric ID on a line Code quality Minor
ID outside the range from app.json Compliance Major

What matters is not the list of findings. It's that each finding is linked to a specific rule from copilot-instructions.md or a declaration in app.json. The report is auditable because the skill evidences its logic. And it doesn't invent rules — if copilot-instructions.md is removed, the skill warns that it will scan with far fewer rules.

Replicate in parallel · 2-3 min

Inspect a real ALDC skill on your machine

After installation, you have .github/skills/ with 15 real skills in your workspace. The exercise is to open one and recognize the canonical pieces.

  1. Open .github/skills/skill-api/SKILL.md or whichever catches your attention
  2. Identify the 4 canonical pieces: frontmatter / Core Patterns / Constraints / cross-references
  3. Ask yourself: what would need to be added to the workshop's copilot-instructions.md for this skill to load automatically in a prompt's context?
What should be clear The 15 ALDC skills share anatomy. Once you know how to read it, each new skill is understood in 30 seconds. And anyone can write their own — we cover this implicitly in Block 3 when we see how agents invoke them.

What this block covers

Live installation

From 2 initial files to ~44 real pieces after installing ALDC from Marketplace.

5-layer architecture

Contract · skills · roles · orchestration · human. The 3 non-negotiable pillars.

The 4 families

Diagnostics · generation · orchestration · evidence. Anatomy of a canonical skill.

Skills Evidencing

The 5 evidence formats that run through the pipeline. Why it makes the agent auditable.

skill-diagnostics demo

Reports · never fixes · never invents rules. The 4 finding classes.

LOADING README…