Auto-refresh KB pricing, align skill with Anthropic best practices

Why this set of changes:
- KB pricing was drifting silently — domain files (database.yaml,
  storage.yaml, etc.) had prices 30-800% off the live Oracle API and
  nobody read them. The skill was auditing as stale on every check
  with no path to fix it.
- The skill itself violated Anthropic's spec (`name` field had
  uppercase/spaces) and was over the 500-line guideline (647 lines),
  hurting discovery and load performance.
- Welcome flow occasionally improvised the menu instead of reading
  SKILL.md, missing options.

Pricing — single source of truth, fully automated:
- Extend tools/refresh_sku_catalog.py with --refresh-domain compute,
  pulls shape-level prices from the Oracle public pricing API
  (apexapps.oracle.com), preserves manual fields (notes, GPU specs,
  free-tier annotations, estimation_helpers), recomputes derived
  monthly values, and protects $0 free-tier prices from overwrite.
- Delete 12 redundant pricing/<domain>.yaml files. They duplicated
  oci-sku-catalog.yaml with worse abstractions and were nobody's
  source of truth (no tool consumed them).
- Migrate the genuinely valuable knowledge from those 12 files
  (billing models, BYOL rules, free-tier rules, ECPU vs OCPU,
  X11M elastic model, hyperscaler comparisons, service nuances)
  into kb/field-knowledge/pricing-knowledge.yaml — non-numeric,
  no refresh needed.
- Result: pricing freshness check goes from 13 stale files to 0.

KB freshness automation:
- Add tools/kb_freshness.py — wrapper around kb_linter.check_freshness()
  with --check, --auto-refresh, --json, --quiet modes. Bridges stale
  files to their refresh tools (SKU catalog, compute domain, arch
  center). Wired into the welcome flow as a pre-flight banner that
  asks the user before refreshing.
- Fix pre-existing kb_linter bug: it crashed on the 45 multi-doc
  YAML files (frontmatter + body pattern) because it used safe_load
  instead of safe_load_all. Freshness check was effectively dead.
- Standardize timestamp field: linter now accepts last_verified,
  last_updated, and last_refreshed; refresh_arch_catalog writes
  last_verified instead of last_refreshed.
- Add make freshness / make freshness-refresh targets.

Skill alignment with Anthropic Agent Skills best practices:
- Rename `name: OCI Deal Accelerator` to `oci-deal-accelerator`
  to comply with the [a-z0-9-]{1,64} spec.
- Refactor SKILL.md from 674 to 445 lines via progressive disclosure:
  extract WA review output format, ECAL readiness format, and output
  conventions into docs/skill/*.md referenced from the main file.
- Add scripts/sync-skill.py + make sync-skill: source of truth is
  root SKILL.md, .agents/skills/oci-deal-accelerator/SKILL.md is
  auto-generated. make lint validates sync.
- Add evaluations/ with 3 manual baseline scenarios (welcome-flow,
  full-proposal, wa-review) per the Anthropic best-practices guidance
  to "build evaluations first."

Welcome flow hardening:
- Tighten CLAUDE.md to MANDATE reading SKILL.md before showing the
  menu (no improvising), and document the freshness pre-flight check
  with the ask-before-refresh user flow.
- Update SKILL.md welcome flow to instruct: parse kb_freshness JSON,
  show banner with stale count + oldest file, prompt user to refresh
  (only when an automated tool exists), fall back silently on errors.

Linter hygiene (zero remaining issues):
- Expand config/kb-tags.yaml taxonomy with features, operations,
  metrics, limitations sections covering 31 previously-unknown tags
  used in field findings (rac, ecpu, refreshable-clone, hnsw, etc.).
- Assign owners for kb/compatibility/, kb/competitive/,
  kb/well-architected/ (Diego Cabrera as default until team grows);
  kb/pricing/ marked as "Auto-refreshed" since it no longer needs
  human ownership.
- kb_linter accepts top-level `date` as fallback for contributor
  block; migrate FF-202603-008 from legacy `reported_by` to
  contributor block.
- Result: linter goes from 45 issues to 0.

Other:
- Recompute estimation_helpers monthly values in compute.yaml after
  the price refresh (they were derived from the old E5/A1 numbers).
- Add kb/README.md — contributor guide (directory map, frontmatter
  spec, refresh tooling, review cadence).

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

CLAUDE.md

@@ -37,8 +37,9 @@ AI skill aligned with Oracle ECAL framework (Define → Design → Deliver) that
 │   │   ├── networking-basic.yaml
 │   │   └── (dirs: database-ha/, database-dr/, networking-hub-spoke/, etc.)
 │   ├── sizing/                 # CPU conversion ratios, IOPS, scaling rules
-│   ├── pricing/                # Simplified pricing for estimation
-│   │   └── oci-sku-catalog.yaml  # ~160 OCI SKUs for BOM generation
+│   ├── pricing/                # Auto-refreshed from Oracle public pricing API
+│   │   ├── oci-sku-catalog.yaml  # 200+ OCI SKUs across 20 categories (BOM source of truth)
+│   │   └── compute.yaml          # Shape-level estimation pricing
 │   ├── competitive/            # AWS/Azure/GCP service mapping
 │   ├── well-architected/       # 5-pillar WA Framework checklists
 │   ├── compatibility/          # Feature matrices (ADB, etc.)
@@ -163,10 +164,16 @@ make lint           # check YAML syntax
 
 ## Welcome Flow
 
-When the user starts a conversation without providing discovery notes or a specific request (e.g., a greeting like "hola", "hey", or empty context), present the welcome message and capability menu defined in `SKILL.md` § Welcome Flow. Specifically:
+When the user starts a conversation without providing discovery notes or a specific request (e.g., a greeting like "hola", "hey", or empty context):
 
-1. Show the welcome banner and numbered capability menu from SKILL.md
-2. Follow the behavior rules for each option (1-10)
-3. After completing any task, offer the next-step menu (A-E)
+**MANDATORY:** Use the `Read` tool to open `SKILL.md` and read the entire `## Welcome Flow` section **before** showing anything to the user. Reproduce the welcome banner and the 14-option capability menu **verbatim** from that file. Do NOT paraphrase, reorder, summarize, translate, or reconstruct the menu from memory, folder structure, or prior conversations. If `SKILL.md` cannot be read for any reason, tell the user instead of improvising a menu.
+
+**Pre-flight check (also defined in SKILL.md):** Before showing the welcome message, run `python tools/kb_freshness.py --check --json`. If `stale_count > 0`, follow the banner-and-prompt logic in SKILL.md § Welcome Flow → Pre-flight. If the tool errors, silently skip the banner — never block the user.
+
+Then:
+
+1. Show the welcome banner and numbered capability menu exactly as defined in SKILL.md (14 options across DESIGN & PROPOSE, VALIDATE & CHECK, STRATEGY & BUSINESS, KNOWLEDGE BASE, ECAL GOVERNANCE, SA TOOLS)
+2. Follow the behavior rules in SKILL.md for each option (1-14)
+3. After completing any task, offer the next-step menu (A-E) as defined in SKILL.md
 4. If the user sends discovery notes directly, skip the menu and go straight to full proposal flow
 5. If the user asks a specific question, skip the menu and answer directly