docs(ultraplan-local): v2.3.0 — skill-factory Fase 1

Doc sync for /ultra-skill-author-local release:

- CHANGELOG.md: 2.3.0 section above 2.2.0 with full feature narrative,
  pipeline diagram, non-goals, new files list, new stats file
- README.md: command table row + new ## /ultra-skill-author-local section
  describing pipeline, modes, IP-hygiene utility, non-goals
- CLAUDE.md: row in Commands table (committed in Step 1)
- ../../README.md: bumped ultraplan-local row v2.2.0 → v2.3.0,
  expanded division-of-labor with sixth bullet for /ultra-skill-author-local,
  added v2.3 narrative paragraph

Plan: .claude/projects/2026-04-18-skill-factory-fase-1-mvp/plan.md (step 12)

README.md

@@ -61,20 +61,23 @@ Key commands: `/config-audit posture`, `/config-audit feature-gap`, `/config-aud
 
 ---
 
-### [Ultra {brief | research | architect | plan | execute} - local](plugins/ultraplan-local/) `v2.2.0`
+### [Ultra {brief | research | architect | plan | execute} - local](plugins/ultraplan-local/) `v2.3.0`
 
-Deep requirements gathering, research, Claude Code feature matching, implementation planning, and self-verifying execution with specialized agent swarms, adversarial review, and failure recovery.
+Deep requirements gathering, research, Claude Code feature matching, implementation planning, self-verifying execution, and skill-factory authoring with specialized agent swarms, adversarial review, IP-hygiene scoring, and failure recovery.
 
-Five commands, one pipeline with clear division of labor:
+Five core commands plus an authoring command, one pipeline with clear division of labor:
 
 - **`/ultrabrief-local`** — Capture intent. Dynamic, quality-gated interview: a section-driven completeness loop (Phase 3) followed by a `brief-reviewer` stop-gate (Phase 4, max 3 review iterations). Required sections must reach an initial-signal gate AND pass review across completeness, consistency, testability, scope clarity, and research-plan validity before `brief.md` is written. Identifies research topics with copy-paste-ready `/ultraresearch-local` commands. Optional auto-orchestration runs research + planning in foreground. Always interactive.
 - **`/ultraresearch-local`** — Gather context. Deep multi-source research with triangulation: 5 local agents + 4 external agents + Gemini bridge, producing structured briefs with confidence ratings. Makes no build decisions.
 - **`/ultra-cc-architect-local`** *(optional, v2.2)* — Match Claude Code features to the task. Reads `brief.md` + `research/*.md`, consults a seeded CC-feature catalog skill (hooks, subagents, skills, output styles, MCP, plan mode, worktrees, background agents), and produces `architecture/overview.md` with brief-anchored rationale plus `architecture/gaps.md` with issue-ready drafts for missing catalog entries. Hallucination gate (enforced by `architecture-critic`) blocks proposals for features not covered by the catalog.
 - **`/ultraplan-local`** — Transform intent into an executable contract. Per-step YAML manifests (`expected_paths`, `commit_message_pattern`, `bash_syntax_check`). Plan-critic is a hard gate on manifest quality. Requires a task brief as input (`--brief` or `--project`). Auto-discovers the architecture note when present and cross-references its `cc_features_proposed` against exploration findings.
 - **`/ultraexecute-local`** — Execute the contract disciplined. Manifest-based verification, independent Phase 7.5 audit from git log + filesystem (ignores agent bookkeeping), Phase 7.6 bounded recovery dispatch for missing steps. Step 0 pre-flight catches sandbox push-denial before any work. `--validate` mode offers a fast schema-only sanity-check between planning and execution.
+- **`/ultra-skill-author-local`** *(authoring, v2.3, skill-factory Fase 1)* — Generate one `cc-architect-catalog` draft skill from a curated local source file with IP-hygiene enforcement. Sequential pipeline: `concept-extractor` → `skill-drafter` → `ip-hygiene-checker`. Drafts land in `skills/cc-architect-catalog/.drafts/` for manual review and `mv` promotion. Pure-Node n-gram containment scorer (`scripts/ngram-overlap.mjs`) enforces verdict bands; rejected drafts are deleted. Channel 2 of the skill-factory strategy — manual, one-source-at-a-time, no automation.
 
 All artifacts land in one project directory: `.claude/projects/{YYYY-MM-DD}-{slug}/` contains `brief.md`, `research/NN-*.md`, `architecture/` *(v2.2)*, `plan.md`, `sessions/`, and `progress.json`. `--project <dir>` works across `/ultraresearch-local`, `/ultra-cc-architect-local`, `/ultraplan-local`, and `/ultraexecute-local`.
 
+v2.3 (non-breaking) ships the skill-factory Fase 1 MVP: `/ultra-skill-author-local` plus four supporting agents (1 opus orchestrator + 3 sonnet workers) and `scripts/ngram-overlap.mjs` (pure Node stdlib, word-5-gram containment + longest-run secondary signal, calibrated against three source/draft fixture pairs). Catalog growth is now tractable without touching the architect's hallucination gate. Non-goals stay explicit: no automation, no batch, no decision-layer skills, no remote sources — manual `mv` from `.drafts/` to catalog root is the promotion mechanism.
+
 v2.2 (non-breaking) adds the optional `/ultra-cc-architect-local` step between research and planning. The architect phase is backed by a versioned catalog skill (`cc-architect-catalog`) with 10 seed entries across three layers (reference, pattern, decision). Gaps are captured as issue-ready drafts so the catalog grows from real usage rather than speculation. `/ultraplan-local` auto-discovers the architecture note — existing pipelines keep working unchanged.
 
 v2.1 (non-breaking) replaced the hardcoded Q1–Q8 interview with a dynamic, quality-gated loop; `brief-reviewer` emits machine-readable per-dimension JSON scores so `/ultrabrief-local` can use it as an internal stop-gate. v2.0 (breaking) extracted the interview from planning: briefs are reviewable artifacts that downstream agents (`brief-reviewer`, `plan-critic`, `scope-guardian`) validate independently. `/ultraplan-local` requires `--brief` or `--project`. See `plugins/ultraplan-local/MIGRATION.md`.