Results for “scope”

Validate and use CUDA graph capture in Megatron Bridge, including local full-iteration graphs and Transformer Engine scoped graphs for attention, MLP, and MoE modules.

Executes multi-stage release plans by reading a PHASE-PLAN.md, implementing each stage, running validation and critique gates, committing with clean scope, and advancing automatically, halting on repeated failures or unresolvable issues.

Turn raw MATLAB code into a published .mltbx toolbox — full pipeline from scope definition through packaging and release. Drives 8 phases with human checkpoints, enforcing ordering and dependencies. Use when asked to package, create a toolbox, or run the files-to-package pipeline.

Design and apply Azure role-based access control with least privilege at the right scope. Use this skill when users ask about permissions, role assignments, access errors, or governance. Covers built-in roles, custom roles, managed identities, PIM, and access reviews per Well-Architected principles.

Inspect GitHub PR checks with gh, pull failing GitHub Actions logs, summarize failure context, then create a fix plan and implement after user approval. Use when a user asks to debug or fix failing PR CI/CD checks on GitHub Actions and wants a plan + code changes; for external checks (e.g., Buildkite), only report the details URL and mark them out of scope.

Inspect GitHub PR checks with gh, pull failing GitHub Actions logs, summarize failure context, then create a fix plan and implement after user approval. Use when a user asks to debug or fix failing PR CI/CD checks on GitHub Actions and wants a plan + code changes; for external checks (e.g., Buildkite), only report the details URL and mark them out of scope.

Scan container images for known vulnerabilities using Anchore Grype with SBOM-based matching and configurable severity thresholds.

基础设施运维专家入口。用于 Codex CLI 的 $expert-ops 调用。 适用于监控告警、可观测性、云基础设施与 IaC、安全加固、成本优化、备份恢复、容量规划和完整基础设施健康评估。 触发词：运维、SRE、Prometheus、Grafana、Terraform、Ansible、云架构、安全加固、成本优化、备份恢复、容量规划

Guides a structured planning pipeline for coding tasks, from scoping and research to plan creation, review, and handoff.

Run Comet's Opik — open-source LLM observability, evaluation, and optimization — from one routing-first skill: install the Python/TypeScript SDK, stand up a server (Comet.com cloud, Docker Compose via `./opik.sh`, or Kubernetes/Helm), wire tracing through `@opik.track` or one of 50+ framework integrations (OpenAI, Anthropic, LangChain, LangGraph, LlamaIndex, CrewAI, DSPy, Ollama, Bedrock, Vercel AI SDK, …), score outputs with LLM-as-a-judge metrics (Hallucination, Moderation, Answer Relevance, Context Precision), and run Datasets/Experiments evaluations including PyTest CI gates. Use when the user wants LLM tracing, prompt evaluation, production LLM monitoring, agent optimization, or guardrails with Opik. Triggers on: opik, comet opik, opik configure, opik.sh, llm observability, llm tracing, llm as a judge, hallucination metric, prompt evaluation, opik dashboard, opik guardrails, agent optimizer.

Inspect GitHub PR checks with gh, pull failing GitHub Actions logs, summarize failure context, then create a fix plan and implement after user approval. Use when a user asks to debug or fix failing PR CI/CD checks on GitHub Actions and wants a plan + code changes; for external checks (e.g., Buildkite), only report the details URL and mark them out of scope.

Top-layer project orchestration skill for Nick's workflow. Use when a request involves multiple stages, skills, or deliverables and the work needs to stay aligned from idea to scope to design to schema to build to QA to deploy. Coordinates the right sequence, enforces stage gates, prevents drift and overbuilding, tracks status/blockers/next actions, and creates clear handoffs between strategist, design, schema, Supabase, build, QA, and launch work.

Composite skill — promote the long-lived `release` branch to `main`, cut a single version that batches every PR accumulated since the last tag, then clean up. Chains pr-merge-readiness (on release→main PR) → version-bump (semver from commits) → changelog-update (promote [Unreleased] → versioned) → ship (tag + GitHub release) → stale-branch cleanup → optional ship-it for deploy. Use this INSTEAD of releasing every small fix individually. Many small commits become one well-scoped release.

Expert knowledge for Azure Role-based access control development including troubleshooting, best practices, decision making, limits & quotas, security, configuration, and integrations & coding patterns. Use when designing Azure RBAC/ABAC scopes, custom roles, PIM, CLI/PowerShell/REST role ops, or ARM/Bicep templates, and other Azure Role-based access control related development tasks. Not for Azure Active Directory B2C (use azure-active-directory-b2c), Azure Information Protection (use azure-information-protection), Azure Policy (use azure-policy), Azure Security (use azure-security).

Auto-review pipeline — reads the full CEO, design, eng, and DX review skills from disk and runs them sequentially with auto-decisions using 6 decision principles. Surfaces taste decisions (close approaches, borderline scope, codex disagreements) at a final approval gate. One command, fully reviewed plan out. Use when asked to "auto review", "autoplan", "run all reviews", "review this plan automatically", or "make the decisions for me". Proactively suggest when the user has a plan file and wants to run the full review gauntlet without answering 15-30 intermediate questions. (gstack) Voice triggers (speech-to-text aliases): "auto plan", "automatic review".

Stand up a self-hostable, typo-tolerant search environment with Typesense — the open-source Algolia / ElasticSearch alternative (single C++ binary, <50ms instant search, no runtime deps). One routing-first skill: pick a server mode (binary download, official Docker image, or managed Typesense Cloud), install an API client (Python/JS/PHP/Ruby official; Go/Dart/C# community), design a collection schema, index documents, and run searches with typo tolerance, faceting/filtering, geo-search, sorting, grouping, synonyms, curation, scoped API keys, and federated multi-search — then wire an InstantSearch.js UI and a Raft-based HA cluster for production. Use when the user wants to build or operate an installable search backend, add site/app/product search, or migrate off Algolia/Elasticsearch. Triggers on: typesense, search engine, typo-tolerant search, algolia alternative, elasticsearch alternative, instantsearch, faceted search, geo search, vector search, self-hosted search, site search, product search.

Single entrypoint for taw-kit. User types `/taw <anything in VN or EN>` — this skill classifies the intent (BUILD / FIX / SHIP / MAINTAIN / ADVISOR) and loads the matching branch file to execute. Replaces the old one-command-per-task model (/taw-new, /taw-add, /taw-fix, /taw-deploy, /taw-security) with a single unified command. Supports dev workflows out of the box: test, upgrade, clean, perf, rollback, refactor, types, seed, review, stack-swap, status, and ADVISOR group (analyze, suggest, coverage, adversarial, scope-check) for opinionated review of existing code. User-visible strings match the user's input language (Vietnamese by default for VN users). Two modes: SAFE (default — clarify + approval, max 1 round-trip) and YOLO (skip gates, smart defaults — for demos/power users). YOLO triggers: prose contains `yolo`, `nhanh nha`, `lam luon`, `khoi hoi`, `auto`, or args start with `yolo`. Trigger phrases (EN + VN) — broad match so user can keep typing plain prose without re-invoking /taw every turn. Grouped by