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>
79 lines
3.5 KiB
Markdown
79 lines
3.5 KiB
Markdown
# WA Review Output Format
|
|
|
|
This document defines how option 5 (Well-Architected Review) presents its results.
|
|
Referenced from `SKILL.md` § Welcome Flow → Behavior Rules → option 5.
|
|
|
|
The WA review MUST produce **two layers of output**: (a) the formatted terminal scorecard shown to the user, and (b) the structured YAML files saved to disk. The terminal output is the primary deliverable — the YAML is the backing data. Never produce YAML-only output without the formatted scorecard.
|
|
|
|
## Terminal scorecard banner
|
|
|
|
```
|
|
══════════════════════════════════════════════════════
|
|
✅ OCI WELL-ARCHITECTED REVIEW — [Customer Name]
|
|
══════════════════════════════════════════════════════
|
|
Overall: [STATUS] — X/Y checks passed
|
|
HIGH: N │ MEDIUM: N │ LOW: N
|
|
══════════════════════════════════════════════════════
|
|
|
|
[emoji] SECURITY & COMPLIANCE X/Y passed
|
|
[emoji] RELIABILITY & RESILIENCE X/Y passed
|
|
[emoji] PERFORMANCE & COST X/Y passed
|
|
[emoji] OPERATIONAL EFFICIENCY X/Y passed
|
|
[emoji] DISTRIBUTED CLOUD X/Y passed | N/A
|
|
```
|
|
|
|
Pillar emoji: 🟢 all passed, 🟡 medium gaps only, 🔴 any HIGH gap, ⬜ N/A
|
|
|
|
## HIGH severity gaps table
|
|
|
|
Present all HIGH gaps grouped by pillar in a markdown table:
|
|
|
|
```
|
|
### HIGH severity gaps that must be addressed:
|
|
|
|
**[Pillar Name] (N HIGH)**
|
|
| ID | Gap | Fix |
|
|
|---|---|---|
|
|
| CHECK-ID | Finding description | Recommended action |
|
|
```
|
|
|
|
## MEDIUM and LOW gaps
|
|
|
|
- **MEDIUM gaps:** List as a compact bullet list grouped by pillar (ID + one-line finding + fix). Skip the table format to keep it concise.
|
|
- **LOW gaps:** Mention count only, list individual items only if ≤ 5.
|
|
|
|
## Analysis section
|
|
|
|
After the gap tables, add a "Why so many gaps?" paragraph if total gaps > 20, explaining the root cause (e.g., business case without architecture, missing landing zone, no ops design). This contextualizes the score for the SA.
|
|
|
|
## Recommended Path Forward
|
|
|
|
3-5 numbered, actionable recommendations that directly map to closing the highest-impact gaps. Reference skill options where applicable (e.g., "Generate the architecture — option 1 or 2").
|
|
|
|
## Files Generated
|
|
|
|
Always list the files saved at the end of the review:
|
|
|
|
```
|
|
📁 Files saved:
|
|
- examples/<customer>-wa-scorecard.yaml
|
|
- examples/<customer>-wa-architecture.yaml
|
|
- examples/<customer>-wa-workload-profile.yaml
|
|
```
|
|
|
|
## After WA Review menu
|
|
|
|
```
|
|
What do you want to do?
|
|
→ [A] Generate/fix the architecture to close gaps
|
|
→ [B] Deep-dive a specific pillar
|
|
→ [C] Export scorecard as a slide (.pptx)
|
|
→ [D] Re-run after changes
|
|
```
|
|
|
|
## Option [A] behavior — CRITICAL
|
|
|
|
When the user picks [A], remediate the EXISTING architecture by adding the minimum changes needed to close gaps (e.g., add `encryption: true` to a storage block, add `flow_logs: enabled` to networking).
|
|
|
|
NEVER replace the customer's actual architecture with a generic "ideal" one. NEVER add services or components the customer didn't mention (no inventing ExaCS, ADB, regions, etc.). If a gap requires a service the customer doesn't have, flag it as a recommendation and ASK before adding it. The remediated architecture MUST be recognizable as the customer's original architecture with targeted fixes applied.
|