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>

README.md

@@ -86,31 +86,27 @@ Any SA can contribute knowledge to the skill. The KB lives in `kb/` as editable
 | **OCI service info** | `kb/services/<service>.yaml` | Create or edit the service YAML |
 | **Architecture pattern** | `kb/patterns/` | Add YAML following existing format |
 | **Architecture Center reference** | `kb/architecture-center/catalog.yaml` | `python tools/refresh_arch_catalog.py --url <url>` |
-| **Updated pricing** | `kb/pricing/<category>.yaml` | Edit with data from [OCI Price List](https://www.oracle.com/cloud/price-list/) |
+| **Updated pricing** | `kb/pricing/oci-sku-catalog.yaml` (SKUs) or `kb/pricing/compute.yaml` (shapes) | `python tools/refresh_sku_catalog.py --refresh` (SKUs) or `--refresh-domain compute` (shapes). Both auto-pull from the Oracle public pricing API. |
 | **Feature compatibility** | `kb/compatibility/adb-feature-matrix.yaml` | Edit the matrix, mark `verified_in_field: true` |
 | **Competitive comparison** | `kb/competitive/` | Add or edit YAML with real pros AND cons |
 
 **Fastest path**: if you hit something in an engagement that another SA should know about, use menu option 11 (Report a field finding) — the skill walks you through the format and adds it to the tracker automatically.
 
-### OCI Pricing (13 categories)
+### OCI Pricing
 
-Comprehensive pricing from the [OCI Price List](https://www.oracle.com/cloud/price-list/) covering compute, database, storage, networking, AI/ML, containers, integration, observability, developer, analytics, hybrid/VMware, and security services. Source date: 2025-09-11.
+All pricing is auto-refreshed from the [Oracle public pricing API](https://apexapps.oracle.com/pls/apex/cetools/api/v1/products/?currencyCode=USD). No manually maintained pricing files.
 
 ```
 kb/pricing/
-├── compute.yaml            # VMs, bare metal, GPU (B200/B300/H200/H100/A100/L40S)
-├── database.yaml           # ADB (ECPU), DBCS, ExaCS, MySQL, PostgreSQL, NoSQL, Redis
-├── storage.yaml            # Block, object, file, data transfer
-├── networking.yaml         # LB, NLB, FastConnect, DNS, egress
-├── ai-ml.yaml              # GenAI, Data Science, Vision, Speech, Digital Assistant
-├── containers-serverless.yaml  # OKE, Functions, Container Instances
-├── integration.yaml        # OIC, API Mgmt, Streaming, Queue, GoldenGate
-├── observability.yaml      # Monitoring, Logging, APM, DR, Email
-├── developer.yaml          # APEX, Visual Builder, DevOps, Blockchain
-├── analytics.yaml          # OAC, Essbase, Big Data, Data Flow
-├── hybrid-vmware.yaml      # OCVS, Compute C@C, Managed Mac, Roving Edge
-├── security.yaml           # Access Governance, Vault, Cloud Guard
-└── pricing-models.yaml     # PAYG, UCM, Reserved, BYOL
+├── oci-sku-catalog.yaml    # 200+ SKUs across 20 categories — single source of truth
+│                             Refresh: python tools/refresh_sku_catalog.py --refresh
+└── compute.yaml            # Shape-level estimation pricing (VMs, BM, GPU)
+                              Refresh: python tools/refresh_sku_catalog.py --refresh-domain compute
+
+kb/field-knowledge/pricing-knowledge.yaml
+                            # Stable pricing context: billing models, BYOL rules,
+                              free tiers, service nuances, hyperscaler comparisons.
+                              Non-numeric — no refresh needed.
 ```
 
 ### DBExpert Database Services Catalog