Rename authoring super-skill al-feature-author -> al-code-author

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>
This commit is contained in:
Jesper Schulz-Wedde 2026-07-01 14:48:10 +02:00
parent 2401443ef8
commit aabffb1e73
4 changed files with 16 additions and 14 deletions

View file

@ -71,7 +71,7 @@ The output contract is defined in the DO meta-skill so that every action skill
The orchestrator parses this **without skill-specific logic**. This is the point of the contract: orchestrators and action skills evolve independently.
> **Authoring skills.** The same four-step pattern also drives *authoring* skills, which generate code rather than review it. They consume an `object-spec` and emit a `code-artifact` (the full generated AL as an escaped string, with per-artifact `references`, `notes`, and task-level `open-questions`) instead of a findings-report. The orchestrator maps each artifact to **file creation or scaffolding** in the target repo rather than to PR comments or build gates. The object-type leaves are `microsoft/skills/author/al-api-page-author.md` (API page) and `microsoft/skills/author/al-table-author.md` (master table and its setup table); the `code-artifact` contract is defined in [`skills/do.md`](skills/do.md). The authoring family's top-level skill is the `microsoft/skills/author/al-feature-author.md` super-skill: it takes a `feature-spec`, decomposes it into per-object specs, composes the object-type author leaves, reconciles cross-object references, and emits a whole-PR `code-artifact` — the authoring counterpart to how `al-code-review` takes a PR and composes the review leaves.
> **Authoring skills.** The same four-step pattern also drives *authoring* skills, which generate code rather than review it. They consume an `object-spec` and emit a `code-artifact` (the full generated AL as an escaped string, with per-artifact `references`, `notes`, and task-level `open-questions`) instead of a findings-report. The orchestrator maps each artifact to **file creation or scaffolding** in the target repo rather than to PR comments or build gates. The object-type leaves are `microsoft/skills/author/al-api-page-author.md` (API page) and `microsoft/skills/author/al-table-author.md` (master table and its setup table); the `code-artifact` contract is defined in [`skills/do.md`](skills/do.md). The authoring family's top-level skill is the `microsoft/skills/author/al-code-author.md` super-skill — the authoring counterpart to how `al-code-review` takes a PR and composes the review leaves: it takes a `feature-spec`, decomposes it into per-object specs, composes the object-type author leaves, reconciles cross-object references, and emits a whole-PR `code-artifact`.
### 7. Orchestrator integrates
The orchestrator turns findings into PR comments, build gates, or IDE diagnostics, and links the references back to the knowledge files so the PR author — human or agent — can read the guidance.