- oci_pdf_gen.py: auto-detect new env catalogue schema (name/sizing/cost_pct)
- business-case-spec.yaml: rewritten to match oci_bizcase_gen.py expected
schema (tco.current_state/proposed_oci with annual_* fields, roi with
three_year_roi_pct/total_investment/annual_net_benefit, value_drivers
with category/driver/quantification, roadmap.phases, recommendation.summary)
- bom-spec.yaml: all SKUs verified against oci-sku-catalog.yaml (B110627
B110629 B110632 for ExaCS X11M, B95703 for ADB-S BYOL, B88326 for
FastConnect 10G, B91628 for Object Storage, B92092 for Vault)
- diagram-spec.yaml: full dual-region architecture (231 cells, 15 services)
- Now generates: PharmaCorp business case 11 slides, correct env catalogue
in PDF, 13 SKU lines in BOM with real prices
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- oci_pdf_gen.py: add_environment_catalogue now auto-detects new schema
(name/sizing/cost_pct) vs legacy (environment/tier/databases/ocpus),
same fix as oci_deck_gen.py. Also normalizes cost_notes string to list.
- business-case-spec.yaml: created PharmaCorp spec (was using MELI).
Fixed schema: risks as {migration_risks, do_nothing_risks}, roadmap
as {phases, total_duration}, recommendation as {summary, next_steps}.
- diagram-spec.yaml: rewrote to match generator format
(tenancy.regions[].vcns[].subnets[].services[] with explicit IDs).
Now generates 231 cells, 11 containers, 15 services, 10 connections.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
The diagram-spec.yaml was using a flat regions/subnets format but
the generator expects tenancy.regions[].vcns[].subnets[].services[]
with explicit IDs. Rewrote with full pharma architecture:
- Queretaro (primary): Hub VCN with 4 subnets (DB, App, Public, Mgmt),
ExaCS X11M, EBS app tier, WAF, Vault, DRG, monitoring
- Sao Paulo (DR): DR VCN with ExaCS standby, FSDR, Object Storage
- 10 connections: dual FastConnect, Data Guard, FSDR, WAF chain, RMAN
Result: 231 cells, 11 containers, 15 services, 10 connections (was empty)
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Skill repo: git.tech-lad.com.br/diegoecab/oci-deal-accelerator
- MCP repo: github.com/Diegoecab/arch-mcp-oracle
- Both links on Get Started slide and closing slide
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Slide 10: MCP Server — zero setup, 14 tools over HTTP, supported
clients (Claude, Codex, Cursor, Windsurf), 1-command connection.
"Zero Python. Zero repo cloning. SA opens IDE and starts working."
- Slide 12: Get Started — Option A (MCP, recommended), Option B
(clone repo), link to github.com/Diegoecab/arch-mcp-oracle.
Placeholder for final get-started link.
- Updated closing slide with MCP repo URL.
- Takeaways now include MCP as differentiator.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
New slide 4: side-by-side table comparing Generic LLM vs OCI Deal
Accelerator across 8 dimensions (pricing, architecture, field gotchas,
competitive, WA validation, compliance, output format, improves over
time). Red header for generic LLM, green for skill.
Key message: "The LLM is the engine. The KB + tools are the fuel.
The SA is the driver."
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Two new slides replace the generic "Under the Hood":
- Slide 8: The Knowledge Base Is the Moat — 40+ YAML files of field
knowledge, auto-refreshed pricing, 123 reference architectures,
honest competitive mapping. Without KB = chatbot, with KB = domain expert.
- Slide 9: Self-Updating KB + Collaborative Field Intelligence —
auto-refresh (SKU API, Arch Center crawler), collaborative model
(findings_cli add/confirm with attribution), governance (health
dashboard, staleness detection, domain owners).
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
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>
- New tools/oci_bom_gen.py: generates .xlsx BOM from YAML spec with
Oracle Redwood styling, Excel formulas, and Oracle disclaimer.
Supports standard BOM (--output) and AppCA import format (--appca)
- New tools/refresh_sku_catalog.py: refreshes SKU catalog prices from
Oracle's public pricing API (apexapps.oracle.com)
- New kb/pricing/oci-sku-catalog.yaml: ~160 OCI SKUs across 14
categories, validated against Oracle API
- New templates/bom-spec.yaml: input spec template for BOM generation
- Add SA TOOLS section to SKILL.md (options 13-14)
- Register BOM generator in oci_output.py
- New tools/oci_bom_gen.py: generates .xlsx BOM from YAML spec with
Oracle Redwood styling, Excel formulas, and Oracle disclaimer.
Supports standard BOM (--output) and AppCA import format (--appca)
- New tools/refresh_sku_catalog.py: refreshes SKU catalog prices from
Oracle's public pricing API (apexapps.oracle.com)
- New kb/pricing/oci-sku-catalog.yaml: ~160 OCI SKUs across 14
categories, validated against Oracle API
- New templates/bom-spec.yaml: input spec template for BOM generation
- Add SA TOOLS section to SKILL.md (options 13-14)
- Register BOM generator in oci_output.py
