Menu
SkillsMP has collected 29 skills from aiappsgbb/threadlight-skills. Open a skill to review its source and details.
Showing 29 of 29 collected skills.
Generate per-domain Faker-style synthetic data + Cosmos seed/reset scripts for a threadlight process. Reads spec § 11d Demo Data and industry realism rules from threadlight-design, then produces scripts/seed_data.py and scripts/reset_data.py plus the seed…
Take a designed agent project (from threadlight-design or hand-crafted) and generate all deployment artifacts for Microsoft Foundry Hosted Agents. Reads specs/SPEC.md, AGENTS.md, and skills to produce container.py, Dockerfile, pyproject.toml, an azd project,…
Generate a curated, framework-agnostic workspace UI reference for a threadlight process — case-list / inbox / dashboard / console / kanban / map shape with detail pane, action toolbar, audit viewer. Reads spec § 8b Human Interaction (Workspace UX) and…
Full-auto driver for the Threadlight pilot pipeline. One freeform prompt ("Build me an auto-claim triage agent for Contoso Mutual") drives threadlight-design → (optional) threadlight-local-test → threadlight-deploy → threadlight-safe-check → live invoke →…
Use when a Threadlight pilot must reach production through a CI/CD pipeline instead of the agent running `azd up` directly — prod deploys run under a federated identity with scoped RBAC from private-VNet runners and the agent has no standing deploy rights.…
Use when a Threadlight pilot needs native ACS/Rego policy, SAFE business invariants, selected tool or lifecycle bindings, approval requirements, signed policy distribution, or runtime governance before deployment. AgentOps ASSERT/ACS summaries in…
Use when a pilot needs production-readiness review, CISO or customer architecture handoff, current runtime-binding evidence, missing live proof, remediation ownership or an explicit CI readiness gate. Not for deployment, runtime implementation, model…
Use when a Threadlight pilot needs design, pre-deploy or post-deploy completeness checks: manifest drift, missing resources, orphan modules, placeholder images, failed jobs, missing telemetry, or selected runtime governance requiring deployed enforcement…
Spec out a business process or customer use case for an enterprise pilot, then generate agent architecture (AGENTS.md + Skills) — a durable SpecKit specification first (process flow, business rules, data models, tool contracts, mock data, KPIs, governance),…
Run a threadlight-designed PoC locally without `azd up`. Four patterns: (0) **Quickstart** — `python -m threadlight_quickstart` boots MAF Agent + SkillsProvider + stub tools + Streamlit UI on localhost:8501; one LLM dep (Foundry OR AOAI OR GitHub Models via…
Use when a pilot needs consequential-action runtime implementation or evidence: selected native hooks, gateway effect closure, action inventory, pre-deploy enforcement gates, approval anti-replay, payload-free audit, Governance Evidence Pack or GHCP…
Threadlight evals leg: offline batch quality, Foundry Continuous Evaluation and champion-challenger gates. Emits `specs/evals-manifest.json` for pillar 6. Reuses validated opted-in AgentOps batches without reruns or live-wiring claims. USE FOR: continuous…
Generate Teams Adaptive Card flows + bot UX components for the seven canonical action gates (approve, edit-and-approve, reject, escalate, signoff, audit-view, request-info) declared in spec § 8 Human Interaction Points. Pairs with foundry-teams-bot for…
Optional per-agent AgentOps lifecycle evidence. Discovers agentops.yaml opt-in, validates pinned native artifacts, integrity, independently scoped run binding, freshness, Doctor and release consistency, then emits specs/agentops-manifest.json. USE FOR:…
DISCOVER-leg for threadlight pilots: runs or ingests Microsoft AI Red Teaming Agent / PyRIT adversarial scan evidence and emits `specs/redteam-manifest.json` plus `docs/redteam-report.md` so `threadlight-production-ready` pillar 7 has live safety evidence…
Emit the final triage decision (approve_refund / deny_refund / escalate_to_supervisor / request_more_info), recommend a warehouse disposition, and write the audit record. USE FOR producing and persisting the final outcome. DO NOT USE FOR gathering data…
Apply the value ceiling and serial-returner / flagged-account risk gates and route cases to a human supervisor. USE FOR deciding whether a return must be escalated to the returns supervisor. DO NOT USE FOR the base eligibility check (policy-eligibility).
Correlate a return case with its order and customer profile, and validate completeness. USE FOR intake of a new return, matching an RMA to an order, checking required fields/photos. DO NOT USE FOR the eligibility or refund decision (that is policy-eligibility…
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…
Offline self-improvement cold-path for threadlight CI/GHCP runs on Microsoft Foundry. `learn <run_id>` harvests ONE GitHub Actions run (green or red, no baseline needed) and emits a grounded learnings digest: phase parity, a reality-tuned failure taxonomy…
CONNECT-leg: evidence-based swap of a scaffolded mock Foundry tool for a real endpoint. Extracts the contract a tool source actually reads, generates conformance tests, checks conformance vs a captured real sample, and gates mock -> real on conformance AND…
GROUND leg: assesses ACL/citation/refusal probe evidence into a threadlight.ground/v1 manifest (GRD-001..004: ACL, citation, refusal, freshness/coverage/baseline). Each SPEC knowledge_source's enabled control must be evidenced under its own source_id, never…
Manual, live/cost-bearing skill that runs a budget-capped load-test profile through k6 or locust (or an injected test adapter) and emits `specs/load-manifest.json` under the shared threadlight.load/v1 envelope, so pilots get real latency/throughput/error-rate…
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,…
UPGRADE leg: PLAN-ONLY compatibility/preview-drift scanner. Scans dependency pins, hosted-agent runtime policy, governance profile, and model families against a compatibility-matrix.json, emitting threadlight.upgrade/v1 with UPG-001 (matrix/dependency…
Check a return against Contoso Retail return policy — 30-day window, final-sale rules, item condition — and cite the governing clause. USE FOR deciding whether a return is eligible for refund. DO NOT USE FOR high-value/fraud gating (fraud-escalation) or…
Scaffold non-interactive trigger receivers for a threadlight process — ACA-first (jobs, app HTTP receivers, KEDA-scaled consumers) with Azure Functions only when narrow constraints demand it. Reads spec § 10b Triggers (Receiver contract) and produces the…
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…
Triage incoming support tickets — read open tickets, classify severity, route to the right team, and update status.