ai-dynamo
- 32 skills
- 0 followers
- 15 hours ago last updated
- ▌ Pi Headless Dynamo · ai-dynamo bundleDrive the real Pi CLI headlessly against a Dynamo or OpenAI-compatible endpoint for pi-dynamo-provider validation. Use when testing Pi provider installs, session header tracing, Pi subagent runs, saved traces, or parent/child session behavior without manually faking Pi or pi-subagents internals.
- ▌ Nixl Python API · ai-dynamo bundleUse for source-matched NIXL Python API help on agents, descriptors, metadata, transfers, polling, or cleanup. Do NOT use for install/framework setup.
- ▌ Thermonuclear Review · ai-dynamoMaximum-intensity multi-agent review of a velo diff/branch before it becomes a PR. Fans out repo-specific finder dimensions (correctness, concurrency, FFI/unsafe, wire-compat, semver boundary, shutdown contract), adversarially verifies every finding, loops until dry, then reports confirmed findings ranked by severity. Use after each implementation phase, or when the user says "thermonuclear review".
- ▌ Tool Parser Generator · ai-dynamo bundleGenerate optimized tool call parsers for the dynamo-parsers crate from HuggingFace model chat templates. Use this when you need to add support for a new model's tool calling format. Takes a HuggingFace model name, analyzes its chat template, compares with existing parsers, and either maps to an existing parser or generates new Rust code with tests for the tool_calling library. The same workflow applies to reasoning parsers in parsers/v1/src/reasoning/.
- ▌ Audit Async Openai Update · ai-dynamo bundleAudit async-openai dependency upgrades in ai-dynamo/frontend-crates and Dynamo consumers. Use when bumping async-openai, reviewing an upgrade PR, checking whether locally owned or vendored OpenAI protocol types can be deleted or narrowed, detecting drift in mirrored structs and enums, or preparing validation evidence for an async-openai update.
- ▌ Grove Grep · ai-dynamoInteractive guide for authoring a Grove Enhancement Proposal (GREP). Leads a structured dialogue with the user, section by section, and writes the proposal file incrementally as each section is confirmed. Also supports continuing work on an existing GREP.
- ▌ Grove User Guide · ai-dynamo bundleInteractive guide for authoring or updating a Grove user guide. Leads a structured dialogue with the user, section by section, and writes the documentation incrementally as each section is confirmed. Also supports continuing work on an existing user guide. Use when the user wants to create, write, or update documentation in docs/user-guide/.
- ▌ Dco · ai-dynamo bundleKeep ModelExpress contributions compliant with the Developer Certificate of Origin. Use whenever creating, amending, rebasing, cherry-picking, or pushing commits, opening or updating a pull request, or diagnosing a failed DCO check in this repository.
- ▌ Add CLI Argument · ai-dynamoAdd or change a ModelExpress client CLI argument or environment variable. Use whenever touching ClientArgs, ClientConfig::load(), the Cli struct, or envs.rs/envs.py.
- ▌ Add Grpc Service · ai-dynamoAdd a new gRPC service to ModelExpress. Use whenever creating a .proto file, wiring a tonic service into the server, or extending modelexpress_common's generated grpc module.
- ▌ Aic Auto Collect · ai-dynamoUse when running long AIC/aiconfigurator GPU perf auto-collection for a specific GPU/framework/framework_version, including draft-PR checkpoints, resumable collect_xx.py runs, framework-version/kernel preflight, collector fixes/skips, special runtime images, validation, and PR handoff.
- ▌ Aic Silicon Align · ai-dynamoUse when validating AIC predictions against real GPU serving measurements and root-causing fidelity gaps (prediction-vs-measured issues, memory/concurrency mismatches, per-op latency divergence). Covers dummy-weight methodology, measurement parity traps, component-isolation ladders, and ledger reconciliation.
- ▌ Aic Version Slots · ai-dynamoUse when adding perf data for a new framework version, deciding which backend_version to query or pin in tests, bumping the maintained (current/previous) versions, retiring old version directories, or hitting "is not a queryable version" errors from the version-slot gate.
- ▌ Adapt Server Config · ai-dynamo bundleConvert InferenceX DB config/benchmark pairs, Dynamo recipe YAML, or confirmed custom serving configs into validated aiconfigurator estimate requests. Use when adapting server configuration, checking whether a recipe can be estimated, generating canonical request JSON, or explicitly running estimates from adapted requests.
- ▌ Aic Collector Op Development · ai-dynamo bundleDesign, add, review, or modify AIC Collector operations and their case population. Use for new Collector ops, backend registry entries, collector/cases YAML, case generators/getters, pruning or deduplication, persisted perf keys, framework-version routing, and audits of whether generated cases match Python/Rust consumers.
- ▌ Aitune Tune · ai-dynamo bundleUse when a user asks to tune, optimize, accelerate, or deploy a PyTorch model or inference pipeline for GPU performance.
- ▌ Aitune Commit · ai-dynamoUse when creating a git commit to ensure the message follows the Conventional Commits specification
- ▌ Aitune Inspect · ai-dynamoUse when inspecting a PyTorch model or pipeline to identify tunable submodules, detect dynamic shapes, and determine the recommended tuning mode before optimization.
- ▌
- ▌ Aitune Validate · ai-dynamoUse when verifying that a tuned model's outputs match the baseline eager model within numerical tolerance — run after each backend compilation before accepting it as a deployment candidate.
- ▌ Aitune Benchmark · ai-dynamoUse when measuring inference performance of a PyTorch model before and after AITune optimization — capturing baseline, compilation time, tuned throughput, and speedup.
- ▌
- ▌ Aiperf Code Review · ai-dynamoReview the current branch against origin/main, capture findings in artifacts/code-review.md as a living document, validate every finding against the actual code, reproduce confirmed issues with the aiperf CLI against the in-repo mock server, and draft inline GitHub PR review comments anchored to specific files and lines. Use when the user asks for a branch or PR code review.
- ▌ Aiperf Kube Triage · ai-dynamo bundleUse when an AIPerf benchmark on Kubernetes is stuck, failing, crash-looping, OOM-killed, pending, queued, stalled, showing a high error rate, or its results cannot be retrieved - diagnosing an AIPerfJob or AIPerfSweep from CR status, pod state, and logs.
- ▌ Aiperf LLM Ergonomics Review · ai-dynamo bundleUse when reviewing AIPerf code for the SEMANTIC qualities that mechanical linters cannot catch — error-message informativeness, type-hint descriptiveness, docstring example usefulness, naming disambiguation, convention explicitness, comment density, and reference-file exemplariness. Invoke after mechanical checks (`make check-ergonomics`, `make check-ruff-baselined`) are green, before shipping a branch or PR. Explicitly out of scope are correctness bugs, style (tabs/quotes), preferences, and anything the guardrails already catch.
- ▌ Aiperf Kube Run · ai-dynamo bundleUse when running, deploying, submitting, attaching to, or retrieving results from a single AIPerf benchmark on a Kubernetes cluster with the aiperf kube CLI (AIPerfJob CR, operator mode or direct mode).
- ▌ Aiperf Kube Setup · ai-dynamo bundleUse when preparing a real multi-node Kubernetes cluster for AIPerf - installing or upgrading the aiperf-operator Helm chart, installing JobSet, wiring a private registry pull secret, choosing node placement and a storage class for the results PVC, or scoping the operator to namespaces.
- ▌ Aiperf Kube Sweep · ai-dynamo bundleUse when running a parameter sweep, multi-run confidence trial, or adaptive/Bayesian search on Kubernetes with aiperf kube sweep and the AIPerfSweep CR - authoring sweep parameter axes, addressing child variations, or collecting sweep aggregates.
- ▌ Cherry Pick · ai-dynamoCherry-pick a commit from origin/main into a release branch using a temporary git worktree
- ▌ Bump Version · ai-dynamoBump the AIPerf package version (e.g. 0.10.0 -> 0.11.0) across pyproject.toml, the mock server, and the version strings shown in docs, then open a PR to main
- ▌ Docs To Fern · ai-dynamoMigrate a plain Markdown docs/ folder to a Fern documentation site from scratch. Use this skill when a project has no existing publishing framework and needs to scaffold Fern config, migrate content, and build navigation.
- ▌ Linear Issue · ai-dynamoThis skill should be used when the user asks to "create a linear issue", "add a linear issue", "track this in linear", "open a linear ticket", "log this in linear", "create a ticket", or mentions creating an issue for tracking work in Linear.