Naming/framing change only - the authoring counterpart to al-code-review is
now the role-level al-code-author. The Action/Output substance is unchanged:
the decompose -> per-object fan-out -> roll up -> reconcile logic and the
Membership worked example stay exactly as they were and correctly describe the
skill's current mode (greenfield feature authoring).
- git mv al-feature-author.md -> al-code-author.md; id al-code-author,
title "AL code author", reframed description. Intro now states the role
(authoring counterpart to al-code-review, produces a whole PR of code) and
is honest that greenfield feature authoring is its first and currently only
mode (other modes such as defect-fix-from-bug-report are future extensions).
inputs [feature-spec], outputs [code-artifact], sub-skills [al-api-page-author,
al-table-author] and dimension fields all unchanged.
- skills/do.md: one-word consistency tweak in the Composition Relevance example
(a feature author -> a code author). Behavior-preserving; the findings/Action
rollup path is byte-identical.
- README.md, agent-consumption.md: author family's top-level skill is now
al-code-author.
R26 generalization and the al-table-author leaf from #67 are unchanged.
Knowledge article count unchanged at 199.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Turn the object-granularity al-object-author super-skill into the
feature/PR-level al-feature-author - the true authoring counterpart of
al-code-review, which takes a whole PR. feature-spec in -> whole-PR
code-artifact out.
- microsoft/skills/author/al-feature-author.md (renamed from
al-object-author.md): takes inputs [feature-spec]; decomposes it into a
cross-referenced object graph, allocates a contiguous object-ID block,
applies the mandatory affix, resolves cross-object references (API page
SourceTable = authored master), fans each derived object-spec out to the
worklisted leaves, rolls up their artifacts, reconciles the refs, and
enumerates the objects no current leaf authors (List/Card pages,
permission set, install codeunit) as open-questions. Worked example:
a Membership feature -> 3 artifacts (master table + setup table from
al-table-author, API page from al-api-page-author) rolling up to completed.
- skills/do.md (composition v1.1, STABLE-CONTRACT): add feature-spec to the
standard inputs; extend Relevance so a super-skill's inputs need not equal
its leaves' - it may derive the leaves' inputs by decomposing its own;
generalize Action rollup to findings-report OR code-artifact. Review
(findings) semantics read identically - behavior-preserving.
- .github/scripts/validate_frontmatter.py: add feature-spec to STANDARD_INPUTS.
#67 R26 generalization unchanged.
- README.md, agent-consumption.md: author family's top-level skill is now
al-feature-author.
The al-table-author leaf and the R26 generalization from #67 are unchanged.
Knowledge article count unchanged at 199.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Add the second AL author leaf (al-table-author) and the al-object-author
super-skill that composes the author leaves, mirroring how al-code-review
composes the review leaves.
- microsoft/skills/author/al-table-author.md: new leaf that generates a BC
master table (and its setup singleton) from an object-spec, applying the
data-modeling knowledge (No. from number series in OnInsert via Codeunit
"No. Series", setup singleton, Last Date Modified in OnModify AND OnRename,
Blocked as inert data enforced in referencing code). Emits code-artifact.
- microsoft/skills/author/al-object-author.md: new super-skill composing
al-api-page-author + al-table-author; invokes all leaves whose inputs are
satisfied and rolls up artifacts/open-questions/outcome per do.md.
- .github/scripts/validate_frontmatter.py: generalize R26 leaf detection from
the al-*-review.md filename glob to a structural definition (an action-skill
sibling without sub-skills). Behavior-preserving for the review folder;
enables author super-skills. STABLE-CONTRACT change.
- README.md, agent-consumption.md: one-line note that the author family now
has the al-object-author super-skill.
do.md is unchanged. Knowledge article count unchanged at 199.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Add the first authoring action skill (al-api-page-author) and extend the
stable DO contract with a second output kind (code-artifact) plus the
object-spec input. Reuses existing web-services API knowledge with no new
knowledge articles; article count unchanged.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Make domain-skill knowledge discovery index-aware
The 6 AL domain review skills and read.md now enumerate candidate articles
from the BCQuality knowledge index (knowledge-index.json) instead of opening
every file under the domain folder to read its frontmatter. The worklist
selection predicate is unchanged (keywords intersect diff tokens, or topic
matches a changed object type) - only the discovery source changes, so the
same articles are selected. Full article bodies are read only for worklisted
entries.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Reconcile §Source wording with the lean knowledge index
The BCQuality filter now emits a lean index whose per-article description is a
one-line hint rather than the full verbatim Description. Update the six domain
skills' §Source to say the index carries a one-line description hint (keywords,
title, and a one-line description) instead of the full description. The
worklist selection predicate is unchanged: keywords drive selection and the
agent opens worklisted articles in full for their rule bodies.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Own the knowledge-index generator in BCQuality
The knowledge index is an acceleration of the skills' Source step, and its
schema is part of that contract — so BCQuality should own the generator rather
than each consumer re-implementing it. Add tools/Build-KnowledgeIndex.ps1 (the
parser + lean-description shaping + emit, lifted verbatim from the
BCAppsBCQuality filter prototype) and document the index in agent-consumption.md.
Consumers prune their clone to policy, then call this script; the index stays
in lockstep with the Source contract and every orchestrator gets the same
faithful index for free. The worklist selection predicate is unchanged.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Own knowledge-index generation in BCQuality (runtime + CI), not the consumer
The index is now produced by BCQuality itself: Entry's preparation step
rebuilds knowledge-index.json over the live, already-pruned clone at the start
of every run, and a new CI workflow validates the generator's health
(determinism, full coverage, selection-input integrity). Consumers no longer
invoke or know about the index.
Rebuilding over the pruned clone (vs shipping a committed full-corpus index)
keeps the index exact for any consumer policy: it can never list a denied
article, so policy-excluded rules cannot leak into discovery. READ now states
the index is discovery-only -- a finding must cite an article opened in full,
and rows whose file is absent are discarded before ranking.
- skills/entry.md: new 'Preparation -- knowledge index' precondition
- skills/read.md: index ownership + discovery-only invariant
- microsoft/skills/review/*.md (6): 'BCQuality builds' (not 'the filter emits')
- agent-consumption.md 5a: runtime+CI ownership rationale
- .github/workflows/knowledge-index.yml + scripts/Test-KnowledgeIndex.ps1: generator guard
- .gitignore: never commit the runtime index
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Make runtime index build non-interactive and self-contained
entry.md now gives the exact build command (pwsh ./tools/Build-KnowledgeIndex.ps1)
so the agent's preparation step is unambiguous, and the generator's -BCQualityRoot
parameter is optional (defaults to the clone root) so it runs in non-interactive
-p mode without prompting.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Resolve knowledge-index root to absolute path (cross-platform fix)
Get-ChildItem.FullName is always absolute, so deriving the relative article
path via Substring(\.Length) requires an absolute root. A relative root
such as '.' (used by the CI guard's 'Test-KnowledgeIndex.ps1 -Root .') left the
full path almost intact on Linux, producing bogus 'home/runner/.../knowledge'
paths and failing the coverage check. Normalise both the generator's
-BCQualityRoot and the test's -Root with Resolve-Path before use.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
---------
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Co-authored-by: Jesper Schulz-Wedde <jesper.schulzwedde@microsoft.com>
Let super-skills surface findings the agent identifies on its own,
clearly tagged so consumers can render them differently from
knowledge-backed ones.
- skills/do.md: permit references:[] when from-sub-skill='agent';
define the agent-finding encoding (id 'agent:<slug>', confidence
capped at medium, self-contained message); restrict agent findings
to super-skills only.
- microsoft/skills/review/al-code-review.md: add a self-review pass
to Action that validates agent-identified candidates against
BCQuality (cite if matched, suppress if contradicted, surface as
agent finding otherwise). Add example finding.
- agent-consumption.md, README.md: describe the additive model and
the from-sub-skill: 'agent' marker so consumer orchestrators know
to render unbacked findings.
Strictly additive: existing knowledge-backed flow is unchanged and
backward compatible.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
The knowledge corpus now covers performance, security, privacy, upgrade,
style, and UI. Previously only two leaf reviewer skills existed
(al-performance-review, al-security-review), so four of the six domains
had knowledge with no skill sourcing from them. A community reader
landing in privacy/, upgrade/, style/, or ui/ would see articles with
no apparent consumer.
Three changes:
1. Move existing review skills into `microsoft/skills/review/`. The
`review/` subfolder groups all review-kind skills together and leaves
room for future non-review action skills at the `microsoft/skills/`
level. Updates references in README.md, agent-consumption.md, and
skills/entry.md to the new paths.
2. Add four new leaf reviewer skills — al-privacy-review,
al-upgrade-review, al-style-review, al-ui-review — each following
the same DO template as al-performance-review/al-security-review but
sourcing from the corresponding knowledge domain. al-upgrade-review
and al-ui-review return `not-applicable` when the diff contains no
upgrade surface or no page files, respectively.
3. Update al-code-review to compose all six leaf skills and retarget
the dangling references in every populated JSON example
(`use-setloadfields.md`, `no-plaintext-secrets-in-telemetry.md`,
`avoid-implicit-commit.md` — none of which exist in the corpus) to
real knowledge files: `call-setloadfields-before-filters.md`,
`use-secrettext-for-credentials.md`, `never-hardcode-secrets-in-al.md`.
Validator passes with 0 errors / 0 warnings.
Add a new skill kind, 'entry-point', and its sole instance at
skills/entry.md. When an orchestrator points an agent at BCQuality,
the agent's first call is Entry: it receives a task context and
returns a dispatch record naming the action skill(s) to invoke.
Routing logic lives in Entry, not in the orchestrator.
Entry structurally follows DO's Source -> Relevance -> Worklist ->
Action pattern but the units it selects are action skills (not
knowledge files) and its output is a dispatch record (not a
findings-report).
Contract highlights:
- Inputs semantics in DO clarified as any-of: orchestrator supplies
whichever listed input types it has; skill must return
'not-applicable' if the subset is insufficient. This matches
the existing al-* canonical skills which declare
[pr-diff, file-path] as alternatives.
- Relevance admits candidates whose inputs intersect
inputs-available, not whose inputs are a subset.
- Dispatched inputs are the intersection, not the full
inputs-available set, to avoid leakage between skills.
- Super-skill precedence in Worklist supersedes a sub-skill only
when the goal is a broader match for the super than the sub.
When the goal specifically names a concern the sub handles
(e.g., 'performance review'), the sub wins and the super is
dropped with reason 'narrower-sub-skill-selected'.
- Skill layer precedence is defined here as custom > community >
microsoft, matching READ's rule for knowledge files.
- skipped[] carries 'superseded-by' for layer-precedence,
sub-skill, and super-skill drops, for traceability.
Propagate the concept through:
- skills/README.md: distinguish the runtime entry-point skill from
the three meta-skill contracts.
- skills/do.md: acknowledge entry-point alongside meta-skills as
the only kinds that live outside a layer.
- README.md: rewrite the Skills and Agent bootstrapping sections
so the bootstrap instruction is 'invoke /skills/entry.md first'.
- agent-consumption.md: update the Mermaid flow and step narrative
to show Entry dispatch, with READ and DO read on demand.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
- skills/read.md (READ, Schema + Use) — knowledge-file contract:
frontmatter schema, required/optional sections (normative vs
non-normative), layer precedence with applicability-based conflict
detection, explicit frontmatter matching semantics (including
partial-context handling).
- skills/do.md (DO, Action Skill) — action-skill template:
frontmatter schema, required sections, four-step pattern
(Source -> Relevance -> Worklist -> Action), and the output contract
as a JSON schema with outcome, findings, structured references,
confidence, and mandatory suppression recording. Includes a worked
example.
- skills/write.md (WRITE, New Knowledge) — authoring guide:
atomicity, size, section guidance, field-by-field choices, file
naming, layer choice, pre-PR checklist. Defers to READ for the
format spec.
- README.md — link the three files from the meta-skills section and
update the output-contract paragraph to include outcome and
suppressed.
- agent-consumption.md — update step 5 (Agent emits structured output)
to match the richer DO contract.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
