The full procedure behind SKILL.md's "Judge Calibration Is a Prerequisite" section. Any grader routed to an LLM-judge follows this before its verdicts count toward a pass rate or a checkpoint promotion decision. Use it to give an agent explicit responsibilities, steps and constraints.
Runnable examples for the four grader shapes named in SKILL.md's Graders section: schema-compliance, exact-match with normalization, execution-based, and LLM-judge. Every grader returns a binary pass/fail — never a Likert score — per the plugin-wide rule. Wire each one to exact. Use it to give an agent explicit responsibilities, steps and constraints.
The Phase 0 gate for the whole plugin: finetuning-method-selection and every downstream skill assume this harness exists before a training config gets written. The harness is not a run-end side artifact — it is the data-curation engine. The same labeled traces that build the go. Use it to give an agent explicit responsibilities, steps and constraints.
Full detail backing SKILL.md's Synthetic Data Rules section: the generation-method ranking, the filter funnel candidate generations pass through before joining the training set, and the teacher→student distillation pattern. Base models are never named as recommendations here. Use it to give an agent explicit responsibilities, steps and constraints.
Concrete JSONL examples for every format in SKILL.md's Format Selection table, a template-application code sketch using current TRL conventions, and the ShareGPT→role/content conversion note. Base models are never named here — every code example uses a BASE MODEL placeholder;. Use it to give an agent explicit responsibilities, steps and constraints.
This skill assumes finetuning-method-selection already routed here — the next step is preparing data, not choosing a method. What follows: format selection by target method, the template/packing mechanics behind the most common silent training failures, rules for mixing in synt. Use it to give an agent explicit responsibilities, steps and constraints.
Complete promotion-report.md template, the drift-suite scoring table, the paired-arena protocol, and a replay-mix configuration example referenced from SKILL.md. BASE MODEL and CHECKPOINT are placeholders throughout — no base model family names appear in this file. Benchm. Use it to give an agent explicit responsibilities, steps and constraints.
The Phase 5 gate for the whole plugin: a checkpoint that trains cleanly and beats its task metric still doesn't ship without clearing all four stages below. eval-harness-first built the suite re-run here — this skill is where that suite's baseline decides something. Use it to give an agent explicit responsibilities, steps and constraints.
This command orchestrates the eval-gated fine-tuning lifecycle across seven phases, each owned by a specialist agent and gated by the artifact the prior phase produced:. Use it to give an agent explicit responsibilities, steps and constraints.
You are the fine-tuning training engineer: the workhorse who takes a training-brief.md someone else already justified and turns it into a dataset, a running job, and an exported artifact. You don't re- litigate method or model choice, and you don't decide whether a checkpoint s. Use it to give an agent explicit responsibilities, steps and constraints.
You are the fine-tuning eval engineer: the independent gatekeeper who builds the measuring stick before anyone trains against it, and reads that same measuring stick to decide whether a trained checkpoint ships. You own the two phases that bound the lifecycle — Phase 0 before a t. Use it to give an agent explicit responsibilities, steps and constraints.
You are the fine-tuning architect: a skeptical strategist who decides whether fine-tuning is the right tool at all before anyone opens a training config. You are the gate-keeper standing between "the user wants to fine-tune" and the first line of a training script — most requests. Use it to give an agent explicit responsibilities, steps and constraints.
Last verified: 2026-07-14 — refresh when CUDA, PyTorch, or the DGX Spark stack ships a new major version. Use it to give an agent explicit responsibilities, steps and constraints.
DGX Spark's GB10 chip (Grace Blackwell, SM121, 128GB unified memory, aarch64) has ten recurring failure modes across launch, memory, thermals, bandwidth, and precision. Each is named G1–G10 so it can be checked by number — the numbering is load-bearing for tooling that runs these. Use it to give an agent explicit responsibilities, steps and constraints.
DGX Spark ships a GB10 Grace Blackwell chip: aarch64 CPU, SM121 GPU, 128GB unified memory, CUDA 13. This is a narrower and younger platform than a standard x86 CUDA 12 box, so package selection and ABI matching matter more than usual — the wheel ecosystem for aarch64 + CUDA 13 is. Use it to give an agent explicit responsibilities, steps and constraints.
You are a PR optimization expert specializing in creating high-quality pull requests that facilitate efficient code reviews. Generate comprehensive PR descriptions, automate review processes, and ensure PRs follow best practices for clarity, size, and reviewability. Use it to give an agent explicit responsibilities, steps and constraints.
logo]: https://github.com/rohan-paul/rohan-paul/blob/master/assets/png. Use it when a task needs concrete terminology, constraints or implementation detail.
PremSQL is an open-source library designed to help developers create secure, fully local Text-to-SQL solutions using small language models. It provides all the essential tools to build and deploy end-to-end Text-to-SQL pipelines with customizable components, making it ideal for s. Use it to build a structured path from fundamentals to hands-on practice.
Plus ACID compliance, point-in-time recovery, JOINs, and all of the other great features of Postgres. Use it to make implementation decisions and avoid common dead ends.
A curated reference on training & fine-tuning centered on What is a good dataset?. Use it when a task needs concrete terminology, constraints or implementation detail.
The full procedure behind SKILL.md's "Judge Calibration Is a Prerequisite" section. Any grader routed to an LLM-judge follows this before its verdicts count toward a pass rate or a checkpoint promotion decision. Use it to give an agent explicit responsibilities, steps and constraints.
Runnable examples for the four grader shapes named in SKILL.md's Graders section: schema-compliance, exact-match with normalization, execution-based, and LLM-judge. Every grader returns a binary pass/fail — never a Likert score — per the plugin-wide rule. Wire each one to exact. Use it to give an agent explicit responsibilities, steps and constraints.
The Phase 0 gate for the whole plugin: finetuning-method-selection and every downstream skill assume this harness exists before a training config gets written. The harness is not a run-end side artifact — it is the data-curation engine. The same labeled traces that build the go. Use it to give an agent explicit responsibilities, steps and constraints.
Full detail backing SKILL.md's Synthetic Data Rules section: the generation-method ranking, the filter funnel candidate generations pass through before joining the training set, and the teacher→student distillation pattern. Base models are never named as recommendations here. Use it to give an agent explicit responsibilities, steps and constraints.
Concrete JSONL examples for every format in SKILL.md's Format Selection table, a template-application code sketch using current TRL conventions, and the ShareGPT→role/content conversion note. Base models are never named here — every code example uses a BASE MODEL placeholder;. Use it to give an agent explicit responsibilities, steps and constraints.
This skill assumes finetuning-method-selection already routed here — the next step is preparing data, not choosing a method. What follows: format selection by target method, the template/packing mechanics behind the most common silent training failures, rules for mixing in synt. Use it to give an agent explicit responsibilities, steps and constraints.
Complete promotion-report.md template, the drift-suite scoring table, the paired-arena protocol, and a replay-mix configuration example referenced from SKILL.md. BASE MODEL and CHECKPOINT are placeholders throughout — no base model family names appear in this file. Benchm. Use it to give an agent explicit responsibilities, steps and constraints.
The Phase 5 gate for the whole plugin: a checkpoint that trains cleanly and beats its task metric still doesn't ship without clearing all four stages below. eval-harness-first built the suite re-run here — this skill is where that suite's baseline decides something. Use it to give an agent explicit responsibilities, steps and constraints.
This command orchestrates the eval-gated fine-tuning lifecycle across seven phases, each owned by a specialist agent and gated by the artifact the prior phase produced:. Use it to give an agent explicit responsibilities, steps and constraints.
You are the fine-tuning training engineer: the workhorse who takes a training-brief.md someone else already justified and turns it into a dataset, a running job, and an exported artifact. You don't re- litigate method or model choice, and you don't decide whether a checkpoint s. Use it to give an agent explicit responsibilities, steps and constraints.
You are the fine-tuning eval engineer: the independent gatekeeper who builds the measuring stick before anyone trains against it, and reads that same measuring stick to decide whether a trained checkpoint ships. You own the two phases that bound the lifecycle — Phase 0 before a t. Use it to give an agent explicit responsibilities, steps and constraints.
You are the fine-tuning architect: a skeptical strategist who decides whether fine-tuning is the right tool at all before anyone opens a training config. You are the gate-keeper standing between "the user wants to fine-tune" and the first line of a training script — most requests. Use it to give an agent explicit responsibilities, steps and constraints.
Last verified: 2026-07-14 — refresh when CUDA, PyTorch, or the DGX Spark stack ships a new major version. Use it to give an agent explicit responsibilities, steps and constraints.
DGX Spark's GB10 chip (Grace Blackwell, SM121, 128GB unified memory, aarch64) has ten recurring failure modes across launch, memory, thermals, bandwidth, and precision. Each is named G1–G10 so it can be checked by number — the numbering is load-bearing for tooling that runs these. Use it to give an agent explicit responsibilities, steps and constraints.
DGX Spark ships a GB10 Grace Blackwell chip: aarch64 CPU, SM121 GPU, 128GB unified memory, CUDA 13. This is a narrower and younger platform than a standard x86 CUDA 12 box, so package selection and ABI matching matter more than usual — the wheel ecosystem for aarch64 + CUDA 13 is. Use it to give an agent explicit responsibilities, steps and constraints.
You are a PR optimization expert specializing in creating high-quality pull requests that facilitate efficient code reviews. Generate comprehensive PR descriptions, automate review processes, and ensure PRs follow best practices for clarity, size, and reviewability. Use it to give an agent explicit responsibilities, steps and constraints.
logo]: https://github.com/rohan-paul/rohan-paul/blob/master/assets/png. Use it when a task needs concrete terminology, constraints or implementation detail.
PremSQL is an open-source library designed to help developers create secure, fully local Text-to-SQL solutions using small language models. It provides all the essential tools to build and deploy end-to-end Text-to-SQL pipelines with customizable components, making it ideal for s. Use it to build a structured path from fundamentals to hands-on practice.
Plus ACID compliance, point-in-time recovery, JOINs, and all of the other great features of Postgres. Use it to make implementation decisions and avoid common dead ends.
A curated reference on training & fine-tuning centered on What is a good dataset?. Use it when a task needs concrete terminology, constraints or implementation detail.