open/ms-ai-architect
1
0
Fork 0
Code Issues Releases 1 Activity

feat(ms-ai-architect): Sesjon 7 steg 3 - K5 progressive disclosure (3 skills PASS)

Browse source 
Lukker K5-FAIL (navngitte fil-lenker / totale ref-filer ≥ 0,20) ved å følge
infrastructure-forbildet (0,97): full-sti `references/<mappe>/<fil>.md`-pekere
til kjernefiler, ikke bare mappe-refs.

Funn: security + advisor hadde filene navngitt allerede, men som BARE filnavn
uten `references/`-prefiks → ufanget av både eval-regex og kb-integrity (samme
klasse som de døde ref-paths i steg 2). Fiks = konverter til full sti:
- security:  10→16 navngitte (0,16→0,26). Konverterte 5 perf-filer (§3) + owasp (§1).
- advisor:    1→25 navngitte (0,016→0,40). Konverterte ~18 bare-filnavn i Kunnskaps-
              basen + la til model-catalog-2026 og entry-points for copilot-extensi-
              bility/prompt-engineering (40 filer som manglet ALLE navngitte pekere).
- engineering: 0→35 navngitte (0,0→0,23). Genuint 0 før; la til `> Kjernefiler:`-linje
              med 4-6 kuraterte filer per §1-7.

Bivirkning: kb-integrity-checks 115→181 (de nye full-sti-refsene valideres nå),
orphan-warnings 260→223. Verifisert: K5 PASS alle 5 · K3/refTall ikke regredert ·
validate 239 · kb-eval 15 · kb-update 122 · kb-integrity 181/181.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01REiKFhP4w6xGXXqWKpPCJJ
This commit is contained in:
Kjell Tore Guttormsen 2026-06-20 05:44:53 +02:00
commit abac74fe67
3 changed files with 47 additions and 28 deletions
Download patch file Download diff file Expand all files Collapse all files

12
skills/ms-ai-security/SKILL.md
View file

@ -87,7 +87,7 @@ Map each threat to the solution under assessment. Use the reference files for de
| LLM09 | Misinformation | RAG grounding, Groundedness Detection, citation patterns, confidence scoring | `owasp-llm-top10-azure-mitigations.md` |
| LLM10 | Unbounded Consumption | Rate limits, token budgets, PTU for capacity, Cost Management alerts | — |
All reference files are in `references/ai-security-engineering/`. LLM04/06/08/09 deler den konsoliderte filen `owasp-llm-top10-azure-mitigations.md`; LLM10 dekkes av rate-limit-/kostnadsfiler.
All reference files are in `references/ai-security-engineering/`. LLM04/06/08/09 deler den konsoliderte filen `references/ai-security-engineering/owasp-llm-top10-azure-mitigations.md`; LLM10 dekkes av rate-limit-/kostnadsfiler.
Kjøretids-trusseldeteksjon for AI-endepunkter dekkes av `defender-threat-protection-ai-services.md` (Defender for Cloud AI threat protection — GA for AI applications, Preview for AI agents; merk: **ikke** tilgjengelig i Azure Government).
@ -155,11 +155,11 @@ Optimize latency, throughput, and scalability for AI workloads. Key strategies:
- **Load testing:** Establish baseline, simulate peak traffic, identify breaking points, long-running soak tests
For detailed implementation guidance, see specific files in `references/performance-scalability/`:
- `latency-optimization-azure-openai.md` — Latency tuning
- `auto-scaling-ai-infrastructure.md` — Scaling patterns
- `rate-limit-management.md` — TPM/RPM quota management
- `load-testing-ai-services.md` — Load testing methodology
- `gpu-compute-sizing.md` — GPU VM-sizing for selvhostet inferens (brukt av `/architect:cost --capacity`)
- `references/performance-scalability/latency-optimization-azure-openai.md` — Latency tuning
- `references/performance-scalability/auto-scaling-ai-infrastructure.md` — Scaling patterns
- `references/performance-scalability/rate-limit-management.md` — TPM/RPM quota management
- `references/performance-scalability/load-testing-ai-services.md` — Load testing methodology
- `references/performance-scalability/gpu-compute-sizing.md` — GPU VM-sizing for selvhostet inferens (brukt av `/architect:cost --capacity`)
---