Menu
O SkillsMP coletou 30 skills de Tyler-R-Kendrick/slm-training. Abra uma skill para revisar a origem e os detalhes.
Mostrando 30 de 30 skills coletadas.
Discover and run the reasoning/revmath profile — reverse-mathematics / computability analysis over existing campaign, formal-preflight, evidence, and repair owners. Use when editing revmath schemas, fixtures, labeling, self-healing, four-axis ledgers, or…
Idioma do texto original: inglês
Use when the Linear In Review queue for team SLM is backed up and an agent session should claim the oldest issues, finish each in an isolated git worktree (reusing open PRs), fix CI in bounded rounds, and squash-merge once merge preflight passes
Idioma do texto original: inglês
Use when a scheduled or interactive session should report the current autotrain evidence state — open hypothesis families, closed approaches, preflight blocks, pending confirmations, promoted-model status — as a short read-only markdown brief in chat
Idioma do texto original: inglês
Use when refreshing the generated OpenWiki pages under docs/openwiki — a scheduled or manual session installs the pinned OpenWiki CLI, selects a provider key, runs scripts.update_openwiki, and opens a PR on branch openwiki/update (skips cleanly when no…
Idioma do texto original: inglês
Use when a screening positive appears in the continuous autotrain loop and before any confirmation spend — convene three independent skeptic lenses (statistical power, prior evidence, mechanism plausibility) to attempt refutation; majority-refute files the…
Idioma do texto original: inglês
Operate the OpenUI SLM training pipeline end to end, including a continuous hands-off model and harness improvement loop. Bare /autotrain is non-terminating and must not stop for user confirmation; an explicit phase or --once is finite. Code fixes during…
Idioma do texto original: inglês
Use when evaluating models, writing or interpreting ship gates, claiming readiness, changing parse/fidelity/reward metrics, or deciding fixture-demo vs production ship
Idioma do texto original: inglês
How to do multi-step engineering work in this repo: parent agents plan and stack PRs with official GitHub Stacked PRs (`gh stack` / `gs`); subagents implement layers with incremental check-ins; parent closes every PR bottom-up with rubber-duck adversarial…
Idioma do texto original: inglês
Improve, extend, debug, or review any canonical OpenUI training harness, including autoresearch/hypothesizer, annotations, distillation, experiment selection/promotion, model build/evaluation, preference learning, quality/retrieval, RL, held-out test data, or…
Idioma do texto original: inglês
Run or extend evidence-grounded OpenUI autoresearch and autotraining campaigns, including literature discovery, typed experiments, data repair, telemetry, researcher evaluation, persistence, and RL readiness.
Idioma do texto original: inglês
Diagnose and improve Lean4-calculated metric ranges when an autotraining, evaluation, benchmark, or promotion observation is outside its preregistered band. Use for metric_evidence/v2 and metric_certificate/v2 work, LeverProof theorem or assumption changes,…
Idioma do texto original: inglês
Use when running, extending, or interpreting quality (E*), grammar (X*), perf (P/Q/R), phase, scaling, or mixture experiment matrices
Idioma do texto original: inglês
Run the knowledge-driven OpenUI research loop that coordinates the training pipeline with curated knowledge. Read and update the repo + personal brains (OKF / Obsidian) and OpenWiki, run the prior-work discovery loop to find related research, drive the…
Idioma do texto original: inglês
Use when finishing any train, eval, benchmark, profile, telemetry, matrix, or reproduction run — or when a checkpoint was created/promoted without MODEL_CARD/README updates — or when results exist only under outputs/ or in chat without matching docs/design…
Idioma do texto original: inglês
Close the data-quality loop after any training-data synthesis or build. Use whenever build_train_data (or the build_train_data job) runs, when a quality_report.json shows warnings, when planning changes to producers/synthesizers, or when deciding what data…
Idioma do texto original: inglês
Use whenever a dashboard page changes — editing any src/apps/dashboard/src/pages/*.tsx or the shared components in src/apps/dashboard/src/components.tsx, or when adding/removing a route in main.tsx. The dashboard renders every page two ways (a…
Idioma do texto original: inglês
Create or refresh committed train-only frontier description bundles for OpenUI gold records. Use when filling src/slm_training/resources/frontier/worklist.jsonl with paraphrases, L1-L5 abstraction prompts, minimal edit instructions, or optional external-page…
Idioma do texto original: inglês
Keep this repository's tracked files and directories canonical, navigable, and free of redundant copies. Use before creating, moving, renaming, deleting, or duplicating tracked files or folders; when adding modules, scripts, docs, fixtures, tools, skills,…
Idioma do texto original: inglês
Autonomous NeMo-RL research agent workflow for directed hypothesis testing and open-ended discovery. Guides agents through the full experiment lifecycle: understanding recipes and environments, wiring RL or NeMo-gym runs, launching reproducible baselines and…
Idioma do texto original: inglês
Safely plan, submit, and reconcile pinned NVIDIA NeMo RL training on Hugging Face Jobs with durable OpenUI artifacts. Use for NeMo RL Jobs commands, recipes, credentials, checkpoint handling, or hardware-smoke claims.
Idioma do texto original: inglês
Manage durable working-session memory for coding agents. Use when a user asks to preserve or recover agent context across disconnects, VS Code restarts, long-running work, handoffs, or any session where important state should be written periodically under the…
Idioma do texto original: inglês
Token-reduction skill for coding agents. Compresses JSON tool output, build logs, grep/ripgrep search results, source code, and conversation history the same way the Headroom proxy does — but in-context, with no binary install. Use this skill whenever an…
Idioma do texto original: inglês
Hugging Face Hub CLI (`hf`) for downloading, uploading, and managing models, datasets, spaces, buckets, repos, papers, jobs, and more on the Hugging Face Hub. Use when: handling authentication; managing local cache; managing Hugging Face Buckets; running or…
Idioma do texto original: inglês
Plan and coordinate the deployment of a model to Amazon SageMaker AI. Use this skill whenever the user wants to deploy, host, serve, or expose a model on SageMaker or AWS — including phrases like "deploy a model", "host this LLM on AWS", "serve this embedding…
Idioma do texto original: inglês
Create a SageMaker endpoint (real-time or async) with autoscaling, CloudWatch alarms, and tagging enabled by default. Use this skill whenever about to create a SageMaker endpoint, write deployment code that calls `create_endpoint`, or finalize a deployment…
Idioma do texto original: inglês
Use when the user asks about finding the best, top, or recommended model for a task, wants to know what AI model to use, or wants to compare models by benchmark scores. Triggers on: "best model for X", "what model should I use for", "top models for [task]",…
Idioma do texto original: inglês
Build and publish a Gradio demo on Hugging Face Spaces for a user-provided LoRA. Use when someone asks to create, generate, ship, or publish a Space, demo, Gradio app, or playground for a LoRA — including LoRAs for Qwen-Image, Qwen-Image-Edit, LTX-Video, Wan,…
Idioma do texto original: inglês
Build, deploy, and maintain applications on Hugging Face Spaces — Gradio / Docker / Static SDKs, ZeroGPU and dedicated hardware, model loading, debugging, buckets, inference providers, community grants. Use whenever the user asks to create or host an app on…
Idioma do texto original: inglês
Rust Token Killer (rtk-ai/rtk) — compress shell/tool command output by 60–90% before it enters the LLM context. Use for git status/diff/log, pytest, ruff, ls, docker, kubectl, and other verbose CLI output. Prefer `rtk <cmd>` over raw commands when rtk is…
Idioma do texto original: inglês
Train and fine-tune transformer language models using TRL (Transformers Reinforcement Learning). Supports SFT, DPO, GRPO, KTO, RLOO and Reward Model training via CLI commands.
Idioma do texto original: inglês