ai-dynamo

@ai-dynamo-dynamo source repo

27 skills
0 followers
1 week ago last updated

▌
Dynamo Clone Hotpath Audit · ai-dynamo-dynamo bundle
Audit Dynamo Rust hot-path `.clone()` calls, explain which clones are removable and why, and only apply clone-removal patches when explicitly requested.

2 installs
▌
Perform Adversarial Review · ai-dynamo-dynamo
Adversarially reviews an evidence-backed Dynamo optimization proposal and DGD draft for comparability, duplication, attribution, correctness, feasibility, and worthwhile GPU spend. Use after hypothesis-generator writes knowledge-consult.md and deploy-draft.yaml and before recipe-deployer creates the next deployment iteration.

2 installs
▌
Create Optimization Hypothesis · ai-dynamo-dynamo
Materializes one evidence-backed proposal from a flexible knowledge-consult.md into a challenger-ready deploy-draft.yaml by applying only its selected DGD change to the current successful manifest. Use after consult-perf-knowledge writes a proposed consultation in the current deployment iteration's next-candidate directory.

2 installs
▌
Repo Codeowners · ai-dynamo-dynamo
Works with Dynamo's generated CODEOWNERS - finds out who reviews a change, fixes a failing codeowners CI check, changes review routing, or grants an external contributor area-scoped ownership. Use when the codeowners check fails on a PR, a new directory is unclaimed, someone asks who reviews a path or PR, review routing needs to change, or a contributor should be added as a code owner.

2 installs
▌
Graham Code Review · ai-dynamo-dynamo
Reviews code changes in the style of Graham King's ai-dynamo/dynamo reviews — exacting Rust and systems-level standards covering error handling, tracing discipline, unnecessary clones, async and concurrency correctness, log levels, and minimal diff surface. Use when reviewing Rust changes, code under lib/ or components/src/dynamo, or any performance-critical or networking path that needs a strict senior-engineer review.

2 installs
▌
Author Baseline Dgd · ai-dynamo-dynamo
Drafts a candidate baseline DynamoGraphDeployment from interview requirements when no catalog recipe matches the user's model, hardware, and backend, presenting per-decision evidence for the user's confirmation. Use only from user-interviewer at interview time, at rung 3 of the baseline-source ladder, and never to deploy or to replace a baseline the user already provided.

2 installs
▌
Troubleshoot Dynamo · ai-dynamo-dynamo bundle
Diagnose failed or unhealthy Dynamo deployments. Use when pods, model-cache jobs, PVCs, workers, frontend/router health, endpoints, or benchmark jobs fail; use deploy-dynamo-recipe or dynamo-router-starter before this for normal bring-up.

2 installs
▌
Deploy Dynamo Recipe · ai-dynamo-dynamo
Deploys one assigned DynamoGraphDeployment and proves it with an OpenAI-compatible smoke test. Use when user-interviewer has captured the user-provided baseline DGD or hypothesis-challenger has approved a later DGD.

2 installs
▌
Dynamo Agent Harness · ai-dynamo-dynamo bundle
Drives persistent Claude Code, Codex, or OpenCode agent sessions through a Dynamo OpenAI/Anthropic-compatible endpoint over Agent Client Protocol (ACP). Use when an agent must delegate a bounded task to another coding-agent harness running a model served by Dynamo, continue that harness across multiple turns, exercise tool calls, or validate agent request traces.

2 installs
▌
Run Aiperf Benchmark · ai-dynamo-dynamo
Launches, monitors, debugs, and collects one run-scoped AIPerf Kubernetes benchmark without changing its workload semantics. Use after perf.yaml and aiperf-config.yaml have been configured for a smoke-tested Dynamo deployment.

2 installs
▌
Dynamo Router Starter · ai-dynamo-dynamo bundle
Start or patch Dynamo router modes and run router endpoint smoke checks. Use for round-robin, KV-aware, least-loaded, or device-aware routing setup; use deploy-dynamo-recipe for recipe deployment and troubleshoot-dynamo for failure diagnosis.

2 installs
▌
Analyze Aiperf Results · ai-dynamo-dynamo
Validates and normalizes raw AIPerf outputs, then evaluates valid results against target SLOs and comparable prior candidates. Use after an AIPerf Job completes to produce benchmark audit, summary, and performance analysis artifacts.

2 installs
▌
Consult Perf Knowledge · ai-dynamo-dynamo
Consults the repository performance rules and applicable Dynamo and engine guides to select one evidence-backed optimization proposal, then writes the generator's knowledge-consult.md reasoning record. Use after perf-analyzer completes a valid AIPerf analysis and before create-optimization-hypothesis materializes a DGD draft.

2 installs
▌
Dynamo Kv Replay Parity · ai-dynamo-dynamo bundle
Runs deterministic byte-parity and paired performance campaigns for Dynamo offline KV-aware replay across native-G1 vLLM and SGLang configurations, including forced scheduler-pressure and disaggregated handoff lifecycles. It is used when validating replay refactors, routing changes, scheduler-event changes, or performance-sensitive offline simulation changes against a baseline revision.

2 installs
▌
Synthesize User Workload · ai-dynamo-dynamo bundle
Synthesizes a canonical user_workload.yaml and captures the user's immutable DynamoGraphDeployment from an optimization user's initial request, attachments, and minimal follow-up interview. Use as the first skill in a new Dynamo recipe optimization run, or to validate supplied workload and DGD inputs before deployment or benchmarking.

2 installs
▌
Dynamo Frontend Benchmark · ai-dynamo-dynamo bundle
Benchmark and profile the Dynamo frontend (dynamo.frontend HTTP + tokenizer + KV router) against mock workers (dynamo.mocker). Use when measuring frontend throughput/latency, A/B-testing a frontend change, or on-CPU/off-CPU profiling the frontend or mock workers to find bottlenecks. Covers topology setup, CPU isolation, aiperf load generation, perf/BPF profiling, throughput analysis, and the sharp edges of this setup.

2 installs
▌
Dynamo Interconnect Check · ai-dynamo-dynamo bundle
Validate that a Dynamo deployment's NIXL/UCX/NCCL interconnect is ready for disaggregated serving over RDMA/NVLink. Use after deploy-dynamo-recipe brings a deployment up (especially disagg/multi-node) to confirm the KV transport is correct; use troubleshoot-dynamo for diagnosing already-failed pods.

2 installs
▌
Configure Aiperf Benchmark · ai-dynamo-dynamo
Selects and freezes a question-driven AIPerf workload, objective, load policy, and Kubernetes execution manifest for a successfully deployed Dynamo candidate. Use when a candidate needs performance characterization or a comparable measurement against a reference.

2 installs
▌
Dep Create · ai-dynamo-dynamo
Creates or updates Dynamo Enhancement Proposals as GitHub issues, including lightweight DEPs, implementation plans, and retroactive DEPs for ai-dynamo/dynamo. Use when proposing a feature or architecture change, drafting an implementation plan, or filing a retroactive DEP.

2 installs
▌
Dep Status · ai-dynamo-dynamo
Checks Dynamo Enhancement Proposal issue status, lists DEPs by lifecycle state or area, and finds related DEP issues in ai-dynamo/dynamo. Use when asking where a DEP stands or which DEPs exist for an area.

2 installs
▌
Dep Update · ai-dynamo-dynamo
Updates Dynamo Enhancement Proposal lifecycle state in GitHub, including triage, PIC assignment, review, approval, and status label changes. Use when triaging a new DEP, assigning a PIC, or moving a proposal through review and approval.

2 installs
▌
Pr Monitor · ai-dynamo-dynamo
Runs a CI health check on an ai-dynamo/dynamo pull request — report check status, explain why full CI has or has not triggered, root-cause failed job logs, cross-reference failures against main to separate PR-caused regressions from pre-existing flakes, and flag unexpected skips. Use when asked whether a PR's CI is healthy, why checks are failing or missing, or whether a failure is a flake.

2 installs
▌
Dynamo Docs · ai-dynamo-dynamo
Adds, updates, moves, or removes content on the Dynamo Fern docs site — standard docs pages, catalog-driven recipe and feature-benchmark pages, examples, recipes, and translations — keeping everything in line with the documentation style guide. Use for any change under docs/, recipes/, or examples/ (new page, edit, tab or section move, rename, removal, recipe/benchmark page, .zh-CN translation, version cut), when deciding which docs tab a page belongs in (Kubernetes Guide vs CLI Guide vs Reference vs Use Cases), and whenever content needs its frontmatter, headings, links, callouts, or terminology fixed.

2 installs
▌
Debug Session · ai-dynamo-dynamo
Sets up a structured debugging session for a Dynamo bug — pull the report from a Linear ticket, GitHub issue, or pasted text, capture the environment, create a persistent worklog markdown file, and walk through rebuild, reproduction, and investigation steps. Use when starting to investigate a reported Dynamo bug or regression and the investigation should be tracked in a worklog.

2 installs
▌
Visual Review · ai-dynamo-dynamo bundle
Create self-contained interactive HTML code-review dashboards from GitHub or GitLab pull requests, checked-out branch diffs, or supplied unified diffs, with correctness and safe-to-merge scores, smell indicators, interactive component and finding diagrams, structured finding packages, per-finding diff tabs with important references, expandable full context, API manifests, annotated red/green diffs, minimaps, validation cases, and fix prompts. Use when Codex is asked for a visual PR review or any of those visual review artifacts.

2 installs
▌
Fern Components · ai-dynamo-dynamo bundle
Knowledge of Fern's built-in MDX component library (accordions, callouts, cards, steps, tabs, code blocks, API-reference snippets, and more) for authoring docs pages. Use when writing or editing a Fern `.mdx` page and deciding whether a component would present content better than plain Markdown, when a user asks "what Fern components exist" or "how do I use `<X>`", or when reviewing a page for missed opportunities to use a component. Complements dynamo-docs (which owns page placement, nav, frontmatter, and the style guide).

2 installs
▌
Fern Navigation · ai-dynamo-dynamo bundle
Knowledge of Fern's site-level navigation and structure configuration — how a docs site is organized in `docs.yml` (and product/version `.yml` files) using sections, pages, folders, tabs, tab variants, versions, products, changelogs, and site-level settings, plus per-page frontmatter. Use when designing or changing the shape of a Fern docs site (adding a tab, splitting into products, cutting a version, restructuring the sidebar, moving the changelog, tuning the navbar/layout/theme) or when a user asks "what options does Fern give me for navigation" or "how do I configure X in docs.yml". Complements fern-components (in-page MDX components) and dynamo-docs (this repo's page placement, style guide, and .md/.mdx rules).

2 installs

27 published skills