threadlight-qualify

Cowork-safe pre-sales qualification and sizing for Threadlight / Azure AI agent pilots. Turns a declared interview (no Azure, Bicep, az, azd, Docker, or customer credentials) into a deterministic sizing package — sizing.md, sizing-manifest.json, discovery.md, and an optional roi.md. Derives monthly volumes, builds MVP and production profiles, and projects both through the shared cost engine with explicit meter coverage and PTU break-even; Citadel hub sizing stays separate from per-application sizing, and every assumption carries a provenance. USE FOR: qualify a pilot, size an agent workload, pre-sales sizing, sizing manifest, cost per transaction, MVP vs production sizing, ROI estimate, Citadel hub sizing, discovery notes, seed SPEC section 12. DO NOT USE FOR: post-deploy cost projection from a live deployment (use threadlight-consumption-iq); production-readiness gating (use threadlight-production-ready); Bicep/infra changes or deployment (use threadlight-deploy).

Jump to install Review files

Repository: aiappsgbb/threadlight-skills
Last source activity: October 7, 2026 at 14:41
Detected SKILL.md language: English
Stars: 2
Forks: 5

Install options

The review-first prompt is selected by default. You can switch to a direct command or download a local copy.

Install with an AI assistant

Copy this prompt into the AI assistant you're using.

Follow https://skillsmp.com/skill-install/prompt.md to install only the Agent Skill at https://github.com/aiappsgbb/threadlight-skills/tree/main/skills/threadlight-qualify.

A direct command skips the review prompt. Inspect the source before running it.

npx skills add https://github.com/aiappsgbb/threadlight-skills --skill threadlight-qualify

The command stays on one line. Scroll horizontally to inspect it before copying.

Prefer a local copy? Download the files currently available to SkillsMP.

Review the source files

Read SKILL.md and any companion files shown by SkillsMP before deciding whether to install.

File Explorer

9 files

SKILL.md

Source instructions · Read-only preview

name

threadlight-qualify

description

Back to search Back to installation

threadlight-deploy

Generate deployment artifacts for a designed Threadlight project on Microsoft Foundry Hosted Agents: container.py, Dockerfile, pyproject.toml, an azd project and deploy-notes.md for one-command `azd up`. Kratos-export mode enriches/validates a Kratos export and backfills evals/. USE FOR: deploy a Threadlight project to Foundry, make this deployable, generate deployment files, Threadlight hosted-agent packaging, azd up for a Threadlight pilot, Kratos export, foundry-agent.zip, backfill evals. DO NOT USE FOR: generic Foundry hosted-agent deploy, invoke or troubleshoot, azd ai agent, model deployment or agent evaluation outside a Threadlight project (use microsoft-foundry); generic Azure app deployment (use azure-prepare / azure-deploy); designing the process (use threadlight-design); Teams bot (use foundry-teams-bot); MCP server deployment (use threadlight-mcp-aca); non-Threadlight GHCP runtime (see references/hosted-agent/ghcp); azd tenant isolation (use threadlight-tenant-isolation).

2026-10-12

threadlight-consumption-iq

Project Azure cost from deployed Bicep + SPEC § 12, compare viable SKUs, and emit cost-projection.md + cost-manifest.json after safe-check. Also supports no-pilot pre-sales estimates with phased rollout, EA/MCA discount, and a one-pager. Owns opt-in read-only actuals and scope-bound reconciliation from Cost Management, Monitor, and Log Analytics, publishing threadlight-cost-actuals/v1 and threadlight-cost-reconciliation/v1. threadlight-production-ready only consumes verified artifacts. Advisory. USE FOR: Azure consumption projection, post-deploy cost, SKU diff, PAYG vs PTU, load profile, cost manifest, pre-sales estimate, EA/MCA discount, cost actuals, forecast vs actual, reconciliation. DO NOT USE FOR: AOAI-only break-even without a pilot (use paygo-ptu-cost-analyzer); subscription bill analysis, budgets or rightsizing outside a pilot (use cost-analysis / cost-governance / cost-optimization); Bicep mutation (use threadlight-deploy).

2026-10-12

threadlight-customize

Use when an SE or a customer's platform team needs to FORK the Threadlight pipeline and adapt it to one customer's environment — landing zones, identity, RBAC, deploy pipelines, governance — with PRODUCTION ONBOARDING as priority #1. An instructions/runbooks skill (not automation): intake gate, customization map (keep vs per-customer-override), test-in-customer-environment runbook for private-VNet envs, and a fork-runbook (upstream-pin + overlay merge). USE FOR: fork threadlight, customize threadlight, customer onboarding, production onboarding, onboard a customer, adapt the pipeline, tailor threadlight, customer landing zone, customer RBAC, customization map, what to fork vs keep, upstream pin, overlay merge, test in customer environment. DO NOT USE FOR: generating the prod deploy pipeline (use threadlight-cicd); the readiness scorecard (use threadlight-production-ready); the first-run deploy (use threadlight-deploy); a central hub (use threadlight-citadel-spoke / threadlight-citadel-hub).

2026-10-12

View all from this repository

threadlight-qualify

Source facts

Install options

Install with an AI assistant

Review the source files

More from this repository

Install with an AI assistant

More from this repository