gj-solution-plan
Draft technical solution plans from confirmed GitLab requirements. Use when a requirement needs impact analysis, architecture options, interface/data/permission changes, risk assessment, test scope, release notes, rollback notes, and Tech Lead review output.
Works with
---
name: gj-solution-plan
description: Draft technical solution plans from confirmed GitLab requirements. Use when a requirement needs impact analysis, architecture options, interface/data/permission changes, risk assessment, test scope, release notes, rollback notes, and Tech Lead review output.
license: MIT
---
# GJ Solution Plan
## Workflow
1. Read the confirmed requirement, acceptance criteria, linked project issue, and milestone.
2. Load minimal context from `.ai/context-index.yml`, `docs/context`, relevant `docs/modules`, and active ADRs.
3. Identify impacted modules, files, interfaces, data, permissions, operations, and rollout paths.
4. Present the recommended solution and rejected alternatives.
5. Check documentation impact:
- Create or update `docs/technical/solutions/<feature>.md` when architecture,
interface, data, permission, compatibility, rollout, or rollback decisions
become durable.
- Update `docs/modules/*.md` when module behavior or boundaries change.
- Propose ADR updates when the decision is cross-module or long-lived.
6. List risks, owner ack needs, test scope, rollout, and rollback.
7. Write a GitLab-ready solution Issue or comment for Tech Lead review.
## Output
```markdown
## Solution Plan
Requirement:
Recommended solution:
Alternatives considered:
Impact scope:
Interface / data / permission changes:
Documentation impact:
Implementation notes:
Test scope:
Release and rollback:
Risks and owner ack:
Tech Lead review checklist:
```
## References
Read `references/demo-run.md` for the order approval solution example.More Deployment & CI/CD skills
finetuning
microsoft/azure-skills
Fine-tune models on Microsoft Foundry using SFT (supervised), DPO (preference), or RFT (reinforcement with graders). Covers dataset preparation, training job submission, deployment, and evaluation. USE FOR: fine-tune, SFT, DPO, RFT, training data, grader, distillation, fine-tuned model, training job, large file upload, calibrate grader, deploy fine-tuned model, evaluate fine-tuned model. DO NOT USE FOR: general model deployment without fine-tuning (use deploy-model), agent creation (use agents), prompt optimization without training (use prompt-optimizer).
prisma-compute
prisma/skills
Prisma Compute deployment and hosting guide. Use whenever the user mentions Prisma Compute, `prisma.compute.ts`, `defineComputeConfig`, deploying or hosting a Prisma app, `@prisma/cli app deploy`, `compute:deploy`, `create-prisma --deploy`, `PRISMA_SERVICE_TOKEN`, Compute auth/workspaces, apps/deployments/build logs/domains, localhost vs `0.0.0.0`, deploy port binding, or framework deploy readiness for Hono, Elysia, Next.js, TanStack Start, Astro, Nuxt, Svelte, Nest, Turborepo, or custom/prebuilt artifacts.
azure-quotas
microsoft/azure-skills
Check/manage Azure quotas and usage across providers. For deployment planning, capacity validation, region selection. WHEN: \"check quotas\", \"service limits\", \"current usage\", \"request quota increase\", \"quota exceeded\", \"validate capacity\", \"regional availability\", \"provisioning limits\", \"vCPU limit\", \"how many vCPUs available in my subscription\".
