Microsoft/bcquality
1
0
Fork 0
mirror of https://github.com/microsoft/BCQuality.git synced 2026-08-06 09:26:52 +01:00
Code Issues Projects Releases Packages Wiki Activity Actions

Introduce super-skill composition; refactor al-code-review into super + two leaves

Browse source 
DO contract (skills/do.md)
- New 'sub-skills' optional frontmatter field on action skills: when
  present and non-empty, the skill is a super-skill that composes
  other action skills.
- New 'Composition (super-skills)' section covering section
  interpretation, outcome rollup, summary aggregation, and suppression
  scope.
- Output schema gains three optional fields: 'from-sub-skill' on each
  finding, top-level 'sub-results[]' carrying nested findings-reports,
  and top-level 'skipped-sub-skills[]'.
- Super-skills MUST NOT filter sub-skills by task content; leaves own
  task-level applicability and signal via outcome.
- Findings from a failed sub-skill MUST NOT flow into the parent's
  findings[] or counts, consistent with DO's rule that consumers
  ignore a failed skill's findings. Reports are still preserved in
  sub-results[] for traceability.
- Rolled-up non-citation finding ids MUST be prefixed with the sub-
  skill id to prevent collisions across sub-skills. Citation-based
  ids are already unique via repo path and are not rewritten.
- Outcome rollup rules updated: 'partial' covers S = {partial},
  {partial, partial}, and {partial, failed}. Empty worklist rolls up
  to 'not-applicable' with outcome-reason.
- Nested super-skills are not permitted in v1.

Reference skills (microsoft/skills/)
- al-code-review.md rewritten as the canonical super-skill: lists
  al-performance-review and al-security-review as sub-skills, orch-
  estrates invocation, aggregates output, and includes a worked
  rolled-up JSON example plus the empty-corpus rollup.
- al-performance-review.md added as a leaf reference skill for the
  performance knowledge domain.
- al-security-review.md added as a leaf reference skill for the
  security knowledge domain.
- Both leaves retain the leaf-level rules validated in the prior
  pass: partial-context message requirement, worklist-scoped
  suppression, application-area semantics, and the platform-guarantee
  threshold for blocker severity.

README updated to describe leaf vs super-skill and link all three
reference skills.

Two rubber-duck passes tightened the contract and caught schema
violations in the worked examples before commit.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
This commit is contained in:
Jesper Schulz-Wedde 2026-04-17 13:06:03 +02:00
parent 7ad0c03c4d
commit 5aaa58e8ee
5 changed files with 470 additions and 57 deletions
Download patch file Download diff file Expand all files Collapse all files

2
README.md
View file

@ -36,7 +36,7 @@ Skills define how agents consume knowledge. They come in two flavors:
Schema + Use and New Knowledge are deliberately separate: one is the reader's contract, the other is the writer's guide. New Knowledge depends on Schema + Use but does not duplicate it.
- **Action skills** — concrete skills that follow the Action Skill template to do real work (review code, audit telemetry, etc.). Action skills live inside the layers that own them (`/microsoft/skills/`, `/community/skills/`). The canonical reference implementation is [`microsoft/skills/al-code-review.md`](microsoft/skills/al-code-review.md) — skill authors should use it as a starting point.
- **Action skills** — concrete skills that follow the Action Skill template to do real work (review code, audit telemetry, etc.). Action skills live inside the layers that own them (`/microsoft/skills/`, `/community/skills/`). An action skill is either a **leaf** that evaluates knowledge files directly, or a **super-skill** that composes other action skills (declared via `sub-skills` in frontmatter). The canonical reference is [`microsoft/skills/al-code-review.md`](microsoft/skills/al-code-review.md) (super-skill), which composes [`microsoft/skills/al-performance-review.md`](microsoft/skills/al-performance-review.md) and [`microsoft/skills/al-security-review.md`](microsoft/skills/al-security-review.md) (leaves).
### Agent bootstrapping

209
microsoft/skills/al-code-review.md
View file

@ -3,83 +3,79 @@ kind: action-skill
id: al-code-review
version: 1
title: AL code review
description: Reviews AL source changes against performance, security, UX, telemetry, and testing guidance from BCQuality.
description: Reviews AL source changes by composing the AL review leaf skills (performance, security, ...).
inputs: [pr-diff, file-path]
outputs: [findings-report]
bc-version: [26..28]
technologies: [al]
countries: [w1]
application-area: [all]
sub-skills:
- microsoft/skills/al-performance-review.md
- microsoft/skills/al-security-review.md
---
# AL code review
Reviews AL source changes against applicable BCQuality guidance and emits a findings report. This skill is the canonical reference implementation of the DO contract — skill authors should copy its structure.
Reviews AL source changes by composing the leaf AL review skills. This is the canonical reference implementation of a **super-skill** — skill authors writing composed reviews should copy its structure.
An orchestrator invokes this skill with either a `pr-diff` (the standard PR-review entry point) or a `file-path` (single-file review, typically from an IDE). The skill produces a single JSON document conforming to the DO output contract.
`al-code-review` does not evaluate knowledge files directly. It invokes each of its sub-skills against the same task input, collects their findings-reports, and returns a rolled-up findings-report.
An orchestrator invokes this skill with either a `pr-diff` (the standard PR-review entry point) or a `file-path` (single-file review). The skill produces a single JSON document conforming to the DO output contract, extended with `sub-results` and — when applicable — `skipped-sub-skills`.
## Source
Collect all knowledge files under `*/knowledge/**/*.md`, across every enabled layer (`/microsoft/`, `/community/`, `/custom/`). Files in any domain subfolder are included; the skill does not enumerate domains. Relevance trims the result to the subset that applies.
The sub-skills invoked by this skill are those listed in frontmatter `sub-skills`:
- `microsoft/skills/al-performance-review.md`
- `microsoft/skills/al-security-review.md`
Additional leaf skills (for example, UX, telemetry, testing) are added by updating the `sub-skills` list. The skill does not discover sub-skills implicitly.
## Relevance
Apply the frontmatter matching rules defined in READ (*Frontmatter matching semantics*) against the task context:
A sub-skill is relevant when both of the following hold:
- `bc-version` — the target BC version from the PR branch's `app.json` or the orchestrator-supplied version. If unavailable, the dimension is `unknown` (see READ's partial-context rule).
- `technologies` — `[al]`.
- `countries` — the countries declared in the consuming app's `app.json`. Default to the orchestrator's configured context; if absent, `unknown`.
- `application-area` — the union of application areas declared by the changed objects. Pass the actual set (e.g., `[finance, jobs]` for a PR touching both); do not substitute `[all]`. If the area cannot be determined from the changes, the dimension is `unknown`.
- The orchestrator has supplied inputs that satisfy the sub-skill's declared `inputs`.
- The orchestrator has not disabled the sub-skill via configuration.
Discard files that are not applicable. Retain conditionally applicable files (any dimension `unknown`) only when the orchestrator's configuration permits them; findings derived from those files MUST have `confidence` no higher than `medium`, AND the finding's `message` MUST name the dimension or dimensions that were unknown so reviewers can judge the finding's applicability.
Per the DO contract, the super-skill MUST NOT filter sub-skills by task content. `al-code-review` does not inspect the PR diff to predict whether, for example, there is anything for `al-security-review` to find. Each leaf is responsible for its own task-level applicability decision; leaves signal non-applicability by returning `outcome: "not-applicable"` or `outcome: "no-knowledge"`.
Sub-skills that fail either check are not invoked and are recorded in `skipped-sub-skills`:
- `reason: "configuration"` when the orchestrator disabled the sub-skill.
- `reason: "not-applicable"` when the orchestrator's inputs do not satisfy the sub-skill's declared `inputs`.
## Worklist
Narrow the relevant files to the subset that applies to the changes under review. For each relevant file, compute overlap against:
- The changed AL object names and types (tables, pages, codeunits, reports, queries, xmlports, enums, permission sets).
- The changed procedures, triggers, and fields.
- Tokens extracted from the diff (identifier names, referenced objects, keywords).
A file enters the candidate worklist when its `keywords` intersect the extracted tokens or its topic (derived from filename and Description) matches a changed object type.
Once the candidate worklist is known, resolve layer-precedence conflicts per READ: for any two candidates whose normative guidance (`## Best Practice` or `## Anti Pattern`) directly contradicts, keep the file from the higher-precedence layer and drop the other. Every dropped file MUST be recorded in the output `suppressed` array with `reason: "layer-precedence"`. Files that would have been candidates but are hidden because their layer is disabled in consumer configuration MUST be recorded with `reason: "configuration"`. Files that were never candidates (failed Relevance or did not match task signal) are NOT recorded in `suppressed`.
When the post-conflict worklist is empty because no applicable knowledge exists in the repo, or because configuration suppressed every candidate, emit `outcome: "no-knowledge"`. When the worklist is empty because no applicable knowledge matched the changes, emit `outcome: "completed"` with an empty `findings` array.
The worklist is the list of sub-skills judged relevant by the previous step. Every sub-skill in the worklist will be invoked in the Action step.
## Action
For each worklist entry, evaluate the diff against the file's `## Best Practice` and `## Anti Pattern` sections. Emit findings as follows:
For each sub-skill in the worklist:
- When the diff contains a clear match for an Anti Pattern, emit a finding with severity `major` or `blocker`, the message summarizing the anti-pattern, `location` pointing to the offending line or range, and a `references` entry pointing to the knowledge file. Use `blocker` only when the knowledge file states the anti-pattern violates a platform-level guarantee; when the file does not make that claim, the ceiling is `major`.
- When the diff contains code that contradicts a Best Practice without being a full anti-pattern, emit `minor` with the same reference shape.
- When the skill cannot detect a violation but the file is clearly applicable to the change, emit `info` citing the file so the author is nudged to read it. Repository-wide observations MAY omit `location`.
1. Invoke the sub-skill with the orchestrator's inputs, passing only the subset each sub-skill declares in its `inputs`.
2. Capture the sub-skill's complete findings-report verbatim and append it to `sub-results`.
3. If the sub-skill's `outcome` is `failed`, stop here for this sub-skill: its findings are not reliable per the DO contract and MUST NOT be copied into the super-skill's top-level `findings[]` or counted in `summary.counts`.
4. Otherwise, append each entry from the sub-skill's `findings[]` to the super-skill's top-level `findings[]`, setting `from-sub-skill` to the sub-skill's `skill.id`. For non-citation findings (those whose `id` is a skill-defined slug rather than a reference path), prefix `id` with `<from-sub-skill>:` to prevent collisions across sub-skills. Other finding fields are preserved.
Set `confidence` to:
Aggregate `summary.counts` and `summary.coverage` as the sums across invoked sub-skills whose `outcome` is not `failed`.
- `high` when the detection is based on an unambiguous pattern match (identifier, syntax, object type).
- `medium` when detection relies on heuristics (name similarity, scope inference) or when any frontmatter dimension was `unknown`.
- `low` when the finding is an advisory derived only from applicability (no detection signal).
`suppressed[]` at the super-skill level remains empty. Knowledge-file-level suppression is reported by each sub-skill within its own entry in `sub-results`.
The outcome selection:
- `completed` — the skill evaluated every worklist item. Default when the skill finishes normally, including when the resulting `findings` array is empty.
- `no-knowledge` — no applicable knowledge survived Source, Relevance, configuration filtering, and conflict resolution. `findings` is empty.
- `not-applicable` — the task context lacks an AL dimension (no AL changes in the diff, or `technologies` filter rejected the task).
- `partial` — a time or token budget was hit before the worklist was exhausted. `summary.coverage` reflects the evaluated subset; `outcome-reason` explains the cause.
- `failed` — an unrecoverable error occurred. `outcome-reason` is required.
Derive `outcome` using the DO rollup rules. `outcome-reason` is populated for `partial` and `failed` and SHOULD summarize per-sub-skill state, for example: *"al-security-review failed (tool timeout); al-performance-review completed."*
## Output
Output conforms to the DO output contract. A populated example:
Output conforms to the DO output contract, extended with `sub-results` and `skipped-sub-skills`. A populated example — both leaves ran, each produced findings:
```json
{
"skill": { "id": "al-code-review", "version": 1 },
"outcome": "completed",
"summary": {
"counts": { "blocker": 0, "major": 1, "minor": 1, "info": 1 },
"coverage": { "worklist-size": 3, "items-evaluated": 3 }
"counts": { "blocker": 1, "major": 1, "minor": 1, "info": 1 },
"coverage": { "worklist-size": 4, "items-evaluated": 4 }
},
"findings": [
{
@ -94,7 +90,33 @@ Output conforms to the DO output contract. A populated example:
"references": [
{ "path": "microsoft/knowledge/performance/filter-before-find.md" }
],
"confidence": "high"
"confidence": "high",
"from-sub-skill": "al-performance-review"
},
{
"id": "community/knowledge/performance/use-setloadfields.md",
"severity": "info",
"message": "Posting routine iterates ledger entries; consider whether SetLoadFields applies per the linked guidance.",
"references": [
{ "path": "community/knowledge/performance/use-setloadfields.md" }
],
"confidence": "low",
"from-sub-skill": "al-performance-review"
},
{
"id": "microsoft/knowledge/security/no-plaintext-secrets-in-telemetry.md",
"severity": "blocker",
"message": "A bearer token is passed to Session.LogMessage as part of the CustomDimensions payload. The referenced guidance documents this as a platform-level data-protection violation.",
"location": {
"file": "src/Integration/ApiClient.Codeunit.al",
"line": 85,
"range": { "start-line": 85, "end-line": 89 }
},
"references": [
{ "path": "microsoft/knowledge/security/no-plaintext-secrets-in-telemetry.md" }
],
"confidence": "high",
"from-sub-skill": "al-security-review"
},
{
"id": "microsoft/knowledge/security/avoid-implicit-commit.md",
@ -107,28 +129,89 @@ Output conforms to the DO output contract. A populated example:
"references": [
{ "path": "microsoft/knowledge/security/avoid-implicit-commit.md" }
],
"confidence": "medium"
},
{
"id": "community/knowledge/telemetry/log-posting-failures.md",
"severity": "info",
"message": "Posting routine touched; consider whether failure paths emit telemetry per the linked guidance.",
"references": [
{ "path": "community/knowledge/telemetry/log-posting-failures.md" }
],
"confidence": "low"
"confidence": "medium",
"from-sub-skill": "al-security-review"
}
],
"suppressed": [
"suppressed": [],
"sub-results": [
{
"reference": { "path": "community/knowledge/performance/filter-before-find.md" },
"reason": "layer-precedence"
"skill": { "id": "al-performance-review", "version": 1 },
"outcome": "completed",
"summary": {
"counts": { "blocker": 0, "major": 1, "minor": 0, "info": 1 },
"coverage": { "worklist-size": 2, "items-evaluated": 2 }
},
"findings": [
{
"id": "microsoft/knowledge/performance/filter-before-find.md",
"severity": "major",
"message": "FindSet is called on a record variable without any prior SetRange/SetFilter. This forces a full-table scan.",
"location": {
"file": "src/Sales/PostingRoutines.Codeunit.al",
"line": 140,
"range": { "start-line": 140, "end-line": 144 }
},
"references": [
{ "path": "microsoft/knowledge/performance/filter-before-find.md" }
],
"confidence": "high"
},
{
"id": "community/knowledge/performance/use-setloadfields.md",
"severity": "info",
"message": "Posting routine iterates ledger entries; consider whether SetLoadFields applies per the linked guidance.",
"references": [
{ "path": "community/knowledge/performance/use-setloadfields.md" }
],
"confidence": "low"
}
],
"suppressed": []
},
{
"skill": { "id": "al-security-review", "version": 1 },
"outcome": "completed",
"summary": {
"counts": { "blocker": 1, "major": 0, "minor": 1, "info": 0 },
"coverage": { "worklist-size": 2, "items-evaluated": 2 }
},
"findings": [
{
"id": "microsoft/knowledge/security/no-plaintext-secrets-in-telemetry.md",
"severity": "blocker",
"message": "A bearer token is passed to Session.LogMessage as part of the CustomDimensions payload. The referenced guidance documents this as a platform-level data-protection violation.",
"location": {
"file": "src/Integration/ApiClient.Codeunit.al",
"line": 85,
"range": { "start-line": 85, "end-line": 89 }
},
"references": [
{ "path": "microsoft/knowledge/security/no-plaintext-secrets-in-telemetry.md" }
],
"confidence": "high"
},
{
"id": "microsoft/knowledge/security/avoid-implicit-commit.md",
"severity": "minor",
"message": "An explicit COMMIT inside a posting routine may leave the ledger in an inconsistent state if subsequent steps fail.",
"location": {
"file": "src/Sales/PostingRoutines.Codeunit.al",
"line": 201
},
"references": [
{ "path": "microsoft/knowledge/security/avoid-implicit-commit.md" }
],
"confidence": "medium"
}
],
"suppressed": []
}
]
}
```
The empty-corpus case — BCQuality's state until knowledge files land — produces:
The empty-corpus case — BCQuality's state until knowledge files land — rolls up to `no-knowledge`:
```json
{
@ -139,6 +222,22 @@ The empty-corpus case — BCQuality's state until knowledge files land — produ
"coverage": { "worklist-size": 0, "items-evaluated": 0 }
},
"findings": [],
"suppressed": []
"suppressed": [],
"sub-results": [
{
"skill": { "id": "al-performance-review", "version": 1 },
"outcome": "no-knowledge",
"summary": { "counts": { "blocker": 0, "major": 0, "minor": 0, "info": 0 }, "coverage": { "worklist-size": 0, "items-evaluated": 0 } },
"findings": [],
"suppressed": []
},
{
"skill": { "id": "al-security-review", "version": 1 },
"outcome": "no-knowledge",
"summary": { "counts": { "blocker": 0, "major": 0, "minor": 0, "info": 0 }, "coverage": { "worklist-size": 0, "items-evaluated": 0 } },
"findings": [],
"suppressed": []
}
]
}
```

126
microsoft/skills/al-performance-review.md Normal file
View file

@ -0,0 +1,126 @@
---
kind: action-skill
id: al-performance-review
version: 1
title: AL performance review
description: Reviews AL source changes against performance guidance from BCQuality.
inputs: [pr-diff, file-path]
outputs: [findings-report]
bc-version: [26..28]
technologies: [al]
countries: [w1]
application-area: [all]
---
# AL performance review
Reviews AL source changes against the `performance` knowledge domain in BCQuality and emits a findings report. This is a leaf action skill: it invokes no sub-skills. It is one of the skills composed by `al-code-review`.
An orchestrator invokes this skill with either a `pr-diff` (the standard PR-review entry point) or a `file-path` (single-file review). The skill produces a single JSON document conforming to the DO output contract.
## Source
Collect all knowledge files under `*/knowledge/performance/**/*.md`, across every enabled layer (`/microsoft/`, `/community/`, `/custom/`). Relevance trims the result to the subset that applies.
## Relevance
Apply the frontmatter matching rules defined in READ (*Frontmatter matching semantics*) against the task context:
- `bc-version` — the target BC version from the PR branch's `app.json` or the orchestrator-supplied version. If unavailable, the dimension is `unknown`.
- `technologies` — `[al]`.
- `countries` — the countries declared in the consuming app's `app.json`. Default to the orchestrator's configured context; if absent, `unknown`.
- `application-area` — the union of application areas declared by the changed objects. Pass the actual set; do not substitute `[all]`. If the area cannot be determined from the changes, the dimension is `unknown`.
Discard files that are not applicable. Retain conditionally applicable files (any dimension `unknown`) only when the orchestrator's configuration permits them; findings derived from those files MUST have `confidence` no higher than `medium`, AND the finding's `message` MUST name the dimension or dimensions that were unknown.
## Worklist
Narrow the relevant files to the subset that applies to the changes under review. For each relevant file, compute overlap against:
- The changed AL object names and types — especially tables, pages with SourceTable bindings, reports, queries, and codeunits performing record iteration.
- The changed procedures and triggers, weighted toward those that perform loops, Find/FindSet/FindFirst calls, CalcFields, CalcSums, FlowField access, or cross-table navigation.
- Tokens extracted from the diff that relate to data access (SetRange, SetFilter, SetLoadFields, SetCurrentKey, FindSet, Repeat…Until, CalcFields, CalcSums).
A file enters the candidate worklist when its `keywords` intersect the extracted tokens or its topic (derived from filename and Description) matches a changed object type.
Once the candidate worklist is known, resolve layer-precedence conflicts per READ. Drop lower-precedence files whose normative guidance (`## Best Practice` or `## Anti Pattern`) directly contradicts a higher-precedence candidate, and record each dropped file in `suppressed` with `reason: "layer-precedence"`. Files that would have been candidates but are hidden because their layer is disabled in consumer configuration are recorded with `reason: "configuration"`. Files that never became candidates are NOT recorded in `suppressed`.
When the post-conflict worklist is empty because no applicable performance knowledge exists, or because configuration suppressed every candidate, emit `outcome: "no-knowledge"`. When the worklist is empty because no applicable performance knowledge matched the changes, emit `outcome: "completed"` with an empty `findings` array.
## Action
For each worklist entry, evaluate the diff against the file's `## Best Practice` and `## Anti Pattern` sections. Emit findings as follows:
- When the diff contains a clear match for an Anti Pattern, emit a finding with severity `major` or `blocker`, a message summarizing the anti-pattern, `location` pointing to the offending line or range, and a `references` entry pointing to the knowledge file. Use `blocker` only when the knowledge file states the anti-pattern violates a platform-level guarantee (for example, documented query timeouts or transaction size limits). When the file does not make such a claim, the ceiling is `major`.
- When the diff contains code that contradicts a Best Practice without being a full anti-pattern, emit `minor` with the same reference shape.
- When the skill cannot detect a violation but the file is clearly applicable to the change, emit `info` citing the file. Repository-wide observations MAY omit `location`.
Set `confidence` to:
- `high` when the detection is based on an unambiguous pattern match (identifier, syntax, object type).
- `medium` when detection relies on heuristics or when any frontmatter dimension was `unknown`.
- `low` when the finding is an advisory derived only from applicability.
Outcome selection:
- `completed` — the skill evaluated every worklist item; default when the skill finishes normally, including when the resulting `findings` array is empty.
- `no-knowledge` — no applicable performance knowledge survived Source, Relevance, configuration filtering, and conflict resolution. `findings` is empty.
- `not-applicable` — the task context lacks an AL dimension (no AL changes in the diff, or `technologies` filter rejected the task).
- `partial` — a time or token budget was hit before the worklist was exhausted. `summary.coverage` reflects the evaluated subset; `outcome-reason` explains the cause.
- `failed` — an unrecoverable error occurred. `outcome-reason` is required.
## Output
Output conforms to the DO output contract. A populated example:
```json
{
"skill": { "id": "al-performance-review", "version": 1 },
"outcome": "completed",
"summary": {
"counts": { "blocker": 0, "major": 1, "minor": 0, "info": 1 },
"coverage": { "worklist-size": 2, "items-evaluated": 2 }
},
"findings": [
{
"id": "microsoft/knowledge/performance/filter-before-find.md",
"severity": "major",
"message": "FindSet is called on a record variable without any prior SetRange/SetFilter. This forces a full-table scan.",
"location": {
"file": "src/Sales/PostingRoutines.Codeunit.al",
"line": 140,
"range": { "start-line": 140, "end-line": 144 }
},
"references": [
{ "path": "microsoft/knowledge/performance/filter-before-find.md" }
],
"confidence": "high"
},
{
"id": "community/knowledge/performance/use-setloadfields.md",
"severity": "info",
"message": "Posting routine iterates ledger entries; consider whether SetLoadFields applies per the linked guidance.",
"references": [
{ "path": "community/knowledge/performance/use-setloadfields.md" }
],
"confidence": "low"
}
],
"suppressed": []
}
```
The empty-corpus case — BCQuality's state until performance knowledge files land — produces:
```json
{
"skill": { "id": "al-performance-review", "version": 1 },
"outcome": "no-knowledge",
"summary": {
"counts": { "blocker": 0, "major": 0, "minor": 0, "info": 0 },
"coverage": { "worklist-size": 0, "items-evaluated": 0 }
},
"findings": [],
"suppressed": []
}
```

130
microsoft/skills/al-security-review.md Normal file
View file

@ -0,0 +1,130 @@
---
kind: action-skill
id: al-security-review
version: 1
title: AL security review
description: Reviews AL source changes against security guidance from BCQuality.
inputs: [pr-diff, file-path]
outputs: [findings-report]
bc-version: [26..28]
technologies: [al]
countries: [w1]
application-area: [all]
---
# AL security review
Reviews AL source changes against the `security` knowledge domain in BCQuality and emits a findings report. This is a leaf action skill: it invokes no sub-skills. It is one of the skills composed by `al-code-review`.
An orchestrator invokes this skill with either a `pr-diff` (the standard PR-review entry point) or a `file-path` (single-file review). The skill produces a single JSON document conforming to the DO output contract.
## Source
Collect all knowledge files under `*/knowledge/security/**/*.md`, across every enabled layer (`/microsoft/`, `/community/`, `/custom/`). Relevance trims the result to the subset that applies.
## Relevance
Apply the frontmatter matching rules defined in READ (*Frontmatter matching semantics*) against the task context:
- `bc-version` — the target BC version from the PR branch's `app.json` or the orchestrator-supplied version. If unavailable, the dimension is `unknown`.
- `technologies` — `[al]`.
- `countries` — the countries declared in the consuming app's `app.json`. Default to the orchestrator's configured context; if absent, `unknown`.
- `application-area` — the union of application areas declared by the changed objects. Pass the actual set; do not substitute `[all]`. If the area cannot be determined from the changes, the dimension is `unknown`.
Discard files that are not applicable. Retain conditionally applicable files (any dimension `unknown`) only when the orchestrator's configuration permits them; findings derived from those files MUST have `confidence` no higher than `medium`, AND the finding's `message` MUST name the dimension or dimensions that were unknown.
## Worklist
Narrow the relevant files to the subset that applies to the changes under review. For each relevant file, compute overlap against:
- The changed AL object names and types — especially permission sets, codeunits handling authentication or authorization, objects touching `Isolated Storage`, `OAuth2` flows, web service endpoints, and API pages.
- The changed procedures and triggers, weighted toward those that call `HttpClient`, write to telemetry, read or write secrets, manipulate record-level security, or bypass the permission model (for example, `Record.WritePermission`, direct table access from a non-owning app).
- Tokens extracted from the diff that relate to security concerns (`IsolatedStorage`, `OAuth2`, `Secret`, `Password`, `Token`, `HttpClient`, `Permission`, `Session`, `UserSecurityId`, `Commit`).
A file enters the candidate worklist when its `keywords` intersect the extracted tokens or its topic (derived from filename and Description) matches a changed object type.
Once the candidate worklist is known, resolve layer-precedence conflicts per READ. Drop lower-precedence files whose normative guidance (`## Best Practice` or `## Anti Pattern`) directly contradicts a higher-precedence candidate, and record each dropped file in `suppressed` with `reason: "layer-precedence"`. Files that would have been candidates but are hidden because their layer is disabled in consumer configuration are recorded with `reason: "configuration"`. Files that never became candidates are NOT recorded in `suppressed`.
When the post-conflict worklist is empty because no applicable security knowledge exists, or because configuration suppressed every candidate, emit `outcome: "no-knowledge"`. When the worklist is empty because no applicable security knowledge matched the changes, emit `outcome: "completed"` with an empty `findings` array.
## Action
For each worklist entry, evaluate the diff against the file's `## Best Practice` and `## Anti Pattern` sections. Emit findings as follows:
- When the diff contains a clear match for an Anti Pattern, emit a finding with severity `major` or `blocker`, a message summarizing the anti-pattern, `location` pointing to the offending line or range, and a `references` entry pointing to the knowledge file. Use `blocker` only when the knowledge file states the anti-pattern violates a platform-level guarantee (for example, documented secret-handling rules, permission-model invariants, or data-protection requirements). When the file does not make such a claim, the ceiling is `major`.
- When the diff contains code that contradicts a Best Practice without being a full anti-pattern, emit `minor` with the same reference shape.
- When the skill cannot detect a violation but the file is clearly applicable to the change, emit `info` citing the file. Repository-wide observations MAY omit `location`.
Set `confidence` to:
- `high` when the detection is based on an unambiguous pattern match (identifier, syntax, object type).
- `medium` when detection relies on heuristics or when any frontmatter dimension was `unknown`.
- `low` when the finding is an advisory derived only from applicability.
Outcome selection:
- `completed` — the skill evaluated every worklist item; default when the skill finishes normally, including when the resulting `findings` array is empty.
- `no-knowledge` — no applicable security knowledge survived Source, Relevance, configuration filtering, and conflict resolution. `findings` is empty.
- `not-applicable` — the task context lacks an AL dimension (no AL changes in the diff, or `technologies` filter rejected the task).
- `partial` — a time or token budget was hit before the worklist was exhausted. `summary.coverage` reflects the evaluated subset; `outcome-reason` explains the cause.
- `failed` — an unrecoverable error occurred. `outcome-reason` is required.
## Output
Output conforms to the DO output contract. A populated example:
```json
{
"skill": { "id": "al-security-review", "version": 1 },
"outcome": "completed",
"summary": {
"counts": { "blocker": 1, "major": 0, "minor": 1, "info": 0 },
"coverage": { "worklist-size": 2, "items-evaluated": 2 }
},
"findings": [
{
"id": "microsoft/knowledge/security/no-plaintext-secrets-in-telemetry.md",
"severity": "blocker",
"message": "A bearer token is passed to Session.LogMessage as part of the CustomDimensions payload. The referenced guidance documents this as a platform-level data-protection violation.",
"location": {
"file": "src/Integration/ApiClient.Codeunit.al",
"line": 85,
"range": { "start-line": 85, "end-line": 89 }
},
"references": [
{ "path": "microsoft/knowledge/security/no-plaintext-secrets-in-telemetry.md" }
],
"confidence": "high"
},
{
"id": "microsoft/knowledge/security/avoid-implicit-commit.md",
"severity": "minor",
"message": "An explicit COMMIT inside a posting routine may leave the ledger in an inconsistent state if subsequent steps fail.",
"location": {
"file": "src/Sales/PostingRoutines.Codeunit.al",
"line": 201
},
"references": [
{ "path": "microsoft/knowledge/security/avoid-implicit-commit.md" }
],
"confidence": "medium"
}
],
"suppressed": []
}
```
The empty-corpus case — BCQuality's state until security knowledge files land — produces:
```json
{
"skill": { "id": "al-security-review", "version": 1 },
"outcome": "no-knowledge",
"summary": {
"counts": { "blocker": 0, "major": 0, "minor": 0, "info": 0 },
"coverage": { "worklist-size": 0, "items-evaluated": 0 }
},
"findings": [],
"suppressed": []
}
```

60
skills/do.md
View file

@ -45,6 +45,8 @@ application-area: [all]
`inputs` is a list of abstract input types the skill consumes. Standard values: `pr-diff`, `object-list`, `file-path`, `repository`, `telemetry-query`. `outputs` is always a single-element list naming the output kind; today only `findings-report` is defined.
`sub-skills` is an optional field. When present and non-empty, the skill is a **super-skill** that composes other action skills; see *Composition* below. Values are repo-relative paths to action-skill files.
## Required sections
Every action skill MUST contain these five sections, in order:
@ -91,7 +93,8 @@ Every action skill emits a single JSON document that conforms to this schema:
"references": [
{ "path": "string", "sha": "string" }
],
"confidence": "high | medium | low"
"confidence": "high | medium | low",
"from-sub-skill": "string"
}
],
"suppressed": [
@ -99,6 +102,15 @@ Every action skill emits a single JSON document that conforms to this schema:
"reference": { "path": "string", "sha": "string" },
"reason": "layer-precedence | configuration"
}
],
"sub-results": [
{ "...full nested findings-report..." : null }
],
"skipped-sub-skills": [
{
"skill": { "id": "string", "version": 1 },
"reason": "configuration | not-applicable"
}
]
}
```
@ -119,6 +131,8 @@ An empty `findings` array with `outcome: completed` means the skill ran and foun
**`findings[].id`** — a stable identifier for the rule or concern that produced the finding. For citation-based findings (any finding with a non-empty `references`), `id` MUST equal `references[0].path` — the primary knowledge file's repo-relative path. For skills that detect concerns without a direct citation, `id` is a skill-defined slug (kebab-case, stable across versions of the skill). The same `id` produced in two runs MUST refer to the same concern; consumers MAY deduplicate findings by `id`.
When a super-skill rolls up a non-citation finding from a sub-skill (an `id` that is a slug, not a path), the super-skill MUST prefix the `id` with `<from-sub-skill>:` to avoid collisions across sub-skills (for example, a slug `missing-test` from `al-security-review` becomes `al-security-review:missing-test`). Citation-based findings are already globally unique through their repo-relative path and MUST NOT be rewritten.
**`findings[].severity`** — see the taxonomy below.
**`findings[].message`** — human-readable explanation of the finding. Single short paragraph. No markdown formatting assumptions.
@ -140,11 +154,17 @@ The first reference is the **primary** reference: the knowledge file the finding
**`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. Absent on findings produced directly by the emitting skill.
**`suppressed`** — MUST list every knowledge file that was discarded due to layer precedence or consumer configuration, whenever that file would otherwise have contributed to the worklist. Each entry contains:
- `reference` — the suppressed file (same object shape as `findings[].references`).
- `reason` — `layer-precedence` when another layer won under READ's precedence rules; `configuration` when the consumer disabled the file's layer.
**`sub-results`** — super-skills only. Array of complete findings-reports, one per sub-skill that was invoked (i.e., every sub-skill not listed in `skipped-sub-skills`). Each entry MUST itself conform to this output contract. Leaf skills MUST NOT emit `sub-results`.
**`skipped-sub-skills`** — super-skills only. Array of sub-skills that were declared in frontmatter but not invoked. `reason` is `configuration` when the orchestrator disabled the sub-skill, or `not-applicable` when the super-skill's Relevance step ruled it out.
Severity taxonomy:
- `blocker` — violates platform-level guarantees; the work cannot proceed as-is.
@ -152,6 +172,44 @@ Severity taxonomy:
- `minor` — quality concern; worth flagging but not a gate.
- `info` — observation or context; not actionable on its own.
## Composition (super-skills)
A **super-skill** is an action skill whose frontmatter declares a non-empty `sub-skills: [...]`. A super-skill does not evaluate knowledge files directly; it invokes other action skills and composes their output.
Composition is flat: a super-skill MAY list only leaf skills (skills without their own `sub-skills`). Nested super-skills are not permitted in v1.
### Section interpretation for super-skills
The five required sections still apply. Their meaning shifts from knowledge files to sub-skills:
- `## Source` — names the sub-skills invoked (mirrors `sub-skills` in frontmatter).
- `## Relevance` — rules for deciding which sub-skills apply to the current task. A sub-skill is relevant when its declared `inputs` are satisfied by the orchestrator's provided inputs and the orchestrator has not disabled it via configuration. The super-skill MUST NOT filter sub-skills by task content (for example, by inspecting the diff or the file). Task-level applicability is the sub-skill's own responsibility; sub-skills signal non-applicability by returning `outcome: "not-applicable"` or `outcome: "no-knowledge"`.
- `## Worklist` — the final list of sub-skills to invoke; the rest go to `skipped-sub-skills`.
- `## Action` — invoke each worklisted sub-skill with the appropriate subset of inputs, collect its findings-report verbatim into `sub-results`, and copy its `findings[]` into the super-skill's top-level `findings[]` with `from-sub-skill` set. Findings from a sub-skill with `outcome: "failed"` MUST NOT be copied into the super-skill's top-level `findings[]` and MUST NOT contribute to the super-skill's `summary.counts` (their report is still preserved in `sub-results` for traceability, consistent with DO's rule that consumers ignore a failed skill's findings).
- `## Output` — the super-skill's output contract, including `sub-results` and, if any, `skipped-sub-skills`.
### Outcome rollup
A super-skill's `outcome` is derived from its sub-skills' outcomes. Let S be the multiset of sub-skill outcomes for sub-skills in the worklist (skipped sub-skills do not contribute):
- `failed` — every element of S is `failed`.
- `partial` — S contains at least one `partial`, OR S contains at least one `failed` alongside at least one non-`failed` outcome.
- `not-applicable` — every element of S is `not-applicable`.
- `no-knowledge` — every element of S is `no-knowledge` or `not-applicable`, and at least one is `no-knowledge`.
- `completed` — otherwise (every element of S is `completed`, `no-knowledge`, or `not-applicable`, with at least one `completed`).
When the worklist is empty (every sub-skill was skipped), `outcome` is `not-applicable`; `outcome-reason` SHOULD describe the skip reasons, for example *"all sub-skills disabled by configuration"* or *"no sub-skill accepted the supplied inputs"*.
`outcome-reason` is required for `partial` and `failed` and SHOULD summarize per-sub-skill state.
### Rolled-up summary
`summary.counts` is the sum of sub-skill counts. `summary.coverage.worklist-size` and `items-evaluated` are the sums across invoked sub-skills.
### Suppression scope
A super-skill's top-level `suppressed[]` remains knowledge-file-only and is typically empty. Knowledge-file suppression is reported by the leaf sub-skill inside its own entry in `sub-results`. Sub-skills the super-skill chose not to invoke belong in `skipped-sub-skills`, never in `suppressed`.
## Worked example
A minimal action skill that cites applicable guidance for a changed AL file, without generating findings of its own: