ca93a0aa4e
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>
3.5 KiB
3.5 KiB
Output Formats and Conventions
Referenced from SKILL.md § Output Generation.
Output directory convention
All generated files MUST be saved inside a dedicated output folder per customer/initiative:
examples/output-<customer>-<initiative>/
Examples:
examples/output-meli-im06/— MELI MySQL engagementexamples/output-meli-im30/— MELI ElasticSearch engagementexamples/output-acme-migration/— ACME cloud migration
This folder contains ALL outputs for that engagement: .pptx, .drawio, .yaml specs, .pdf, scorecards. The folder is gitignored via examples/output-*/ — never commit customer data.
YAML spec files (architecture, workload-profile, diagram-spec) are saved IN the output folder, not loose in examples/. This keeps everything grouped and portable.
Format options
Default output is a slide deck (.pptx). The architect can specify:
| Format | Output |
|---|---|
deck (default) |
10-12 slide presentation |
deck + drawio |
+ editable architecture diagram |
deck + doc |
+ technical document (15-25 pages) |
deck + xlsx |
+ cost spreadsheet with formulas |
deck + pdf |
+ customer-facing PDF (branded, no internal refs) |
pdf |
Customer PDF only |
full |
Everything (pptx + drawio + docx + xlsx + pdf) |
doc only |
Technical document without slides |
deliver |
Handover + go-live checklist + success criteria |
Slide deck structure
Slide count adapts to engagement tier (6-8 small, 10-12 standard, 12-16 complex):
- Title — customer, project, date (dark background)
- Value Story — business driver, hypothesis, desired outcomes
- Service Tiering — workload-to-tier mapping (Platinum/Gold/Silver/Bronze) with SLA, RTO/RPO
- Architecture Principles — selected ECAL principles (Design/Deployment/Service) that govern the architecture
- Architecture Diagram — fills 85% of slide
- Architecture Decisions — 4-6 key decisions with rationale
- HA/DR — topology + RTO/RPO per tier
- Security & Compliance — controls grid, compliance badges
- Environment Catalogue — Prod/Pre-Prod/Dev-Test/DR per workload with sizing and isolation
- Cost Estimate — PAYG vs BYOL table with assumptions (all environments)
- Cost Comparison (optional) — vs current state or competitor
- Migration Approach — phased timeline, tools, downtime strategy
- Operational RACI — responsibility matrix (customer vs Oracle/partner)
- Risk Register — severity-coded risk table
- Well-Architected Scorecard — 5-pillar traffic-light indicators
- Next Steps — concrete SMART actions with dates
Use tools/oci_deck_gen.py for generation. Colors: teal #2D5967, copper #AA643B, purple #804998. Font: Segoe UI. Design standards: config/output-formats.yaml.
Architecture diagram
Use tools/oci_diagram_gen.py with OCI official styles from kb/diagram/oci-toolkit-styles.yaml. Containers, service blocks, connections, and typography rules are defined there.
Service categorization
| Category | Color | Use |
|---|---|---|
| Infrastructure | Teal #2D5967 |
Compute, OKE, LB, Gateways, WAF, Bastion, Storage, Monitoring |
| Database | Copper #AA643B |
ADB-S/D, DBCS, ExaCS, MySQL, PostgreSQL, NoSQL, GoldenGate |
| Integration | Purple #804998 |
DRG, Streaming, Queue, OIC, FastConnect, Service Connector Hub |
| Dormant | Light gray #DFDCD8 |
Standby/inactive resources (DR tier) |
| Legacy | Medium gray #70665E |
Non-OCI systems (MQ Series, legacy middleware) |