Complete AL review knowledge readiness (#108)

* Complete AL review knowledge readiness

Fill telemetry and Query coverage, strengthen thin review domains, correct audited content defects, and add deterministic cheap-model evaluation and reference-integrity safeguards.

Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com>

Copilot-Session: 9825b012-e653-496a-9310-c1f4b6f8ac27

* Generalize review fixture discovery

Derive smoke cases from the leaf, domain, and paired-sample conventions so new leaves require no scoring-contract changes. Keep only exceptional selection/context overrides and fail when retrieval metadata cannot rank the selected article.

Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com>

Copilot-Session: 9825b012-e653-496a-9310-c1f4b6f8ac27

* Preserve published field IDs in sample

Keep the existing Email and Contact Email field IDs unchanged, clarify that the sample represents an independent baseline, and use a local breaking-change rule for the generic smoke evaluation.

Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com>

Copilot-Session: 9825b012-e653-496a-9310-c1f4b6f8ac27

* Clarify published field identity rules

State explicitly that a published field keeps its ID, name, and type while a replacement is added as a separate field under an unused ID.

Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com>

Copilot-Session: 9825b012-e653-496a-9310-c1f4b6f8ac27

* Align field obsoletion sample baselines

Use Email field ID 3 as the shared baseline so the bad example demonstrates a same-ID rename while the good example retains the original field and adds a separate replacement.

Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com>

Copilot-Session: 9825b012-e653-496a-9310-c1f4b6f8ac27

---------

Co-authored-by: Jesper Schulz-Wedde <jesper.schulzwedde@microsoft.com>

skills/bcquality-al-review/SKILL.md

@@ -63,11 +63,19 @@ plugin-root environment variable, prefer it.
    `microsoft/skills/review/al-code-review.md`. For each dispatched skill, read the
    file and execute its Source → Relevance → Worklist → Action steps, reading
    `PLUGIN_ROOT/skills/read.md` and `PLUGIN_ROOT/skills/do.md` on demand.
+   When `al-code-review` composes its leaves and the host supports child contexts or
+   separate model calls, run each leaf in an isolated context and roll up the returned
+   JSON. Pass each call the exact index rows for that leaf's domain so references can
+   be copied verbatim. This is the preferred execution profile for fast/small models;
+   do not force one generation to retain all domain knowledge at once.
 
 4. **Emit findings.** Produce the rolled-up findings report in the DO output contract,
    including each review finding's producer-supplied `domain` label (`outcome`,
    `findings`, `references`, `confidence`, `suppressed`). Do not invent a different
    shape; downstream consumers parse the DO contract without skill-specific logic.
+   Apply DO's reference-integrity gate before returning: every knowledge-backed path
+   must exist in the installed tree, must have been opened in full, and must be copied
+   verbatim. Never synthesize a plausible article slug.
 
 If Entry returns `no-match` or `failed`, return the dispatch record unchanged so the
 caller can log the reason.

skills/do.md

@@ -171,6 +171,8 @@ Consumers that render output MAY treat agent findings differently from knowledge
 
 **`findings[].message`** — human-readable explanation of the finding. Single short paragraph. No markdown formatting assumptions.
 
+**Applicability is not a finding.** Loading an article into the worklist only means its rule must be evaluated. If the changed code does not violate the article's normative guidance, emit nothing for that article. An `info` finding still requires a concrete observation defined by the article; skills MUST NOT use `info` to list guidance that merely happened to be relevant.
+
 **`findings[].location`** — optional. When present:
 
 - `file` MUST be a repo-relative path using forward slashes.
@@ -186,6 +188,15 @@ Findings without a `location` are permitted (for example, repository-wide observ
 
 The first reference is the **primary** reference: the knowledge file the finding most directly cites. Additional references provide supporting context and are not ranked. `references` MAY be empty only for **agent findings** (see the `findings[].id` section above for the full encoding); any other finding MUST have at least one reference.
 
+**Reference-integrity gate (mandatory).** A knowledge-backed finding may cite only a path copied verbatim from the current knowledge index or from a file discovered by the index fallback, and the skill must have opened that exact file in full before citing it. Never construct a plausible slug or infer a path from a topic name. Immediately before emitting the JSON document:
+
+1. Verify every non-empty `references[].path` exists in the live checkout and was opened during this skill run.
+2. Verify every citation-based `findings[].id` exactly equals `references[0].path`.
+3. Remove any candidate that cannot satisfy both checks; it is not a knowledge-backed finding. Do not convert it into an agent finding merely to preserve it.
+4. If reference integrity cannot be checked reliably, return `outcome: "failed"` rather than emitting fabricated or unverified citations.
+
+This gate applies independently to every leaf result and again to a super-skill's rolled-up result.
+
 **`findings[].confidence`** — the skill's confidence that the finding is a true positive, given the evidence it evaluated. Not applicability confidence, not severity confidence. Values: `high`, `medium`, `low`.
 
 **`findings[].from-sub-skill`** — optional. Set only by super-skills. The `skill.id` of the sub-skill that produced the finding, or the literal string `"agent"` for an agent finding the super-skill produced from its own cross-cutting reasoning. Absent on findings emitted directly by a leaf skill — including agent findings the leaf emits within its own domain, which appear in the leaf's own report without this field.

skills/write.md

@@ -85,7 +85,10 @@ Before opening a pull request:
 - No fenced code blocks.
 - File is under 100 lines.
 - File covers one concern.
+- Frontmatter `domain` exactly matches the containing domain folder.
 - File is in the correct layer and domain folder.
 - Name is kebab-case and descriptive.
+- Every companion sample is referenced by filename from the article, and every referenced sample exists.
+- Every review-leaf domain has at least one article with both `.good.al` and `.bad.al` companions; the evaluation harness derives positive and clean controls from that convention automatically.
 
 Agents scaffolding new files SHOULD run this checklist programmatically before emitting the file.