tpu_performance_autoresearch_wiki: Skill for Claude Code

.claude/skills/formulate-kernel-hypothesis/SKILL.md

formulate-kernel-hypothesis is a skill for Claude Code from vlasenkoalexey/tpu_performance_autoresearch_wiki. It costs 0 tokens per session (2,633 once invoked), scanned A, original, MIT.

A proposal-writing step for improving a mathematical kernel. It uses measured bottlenecks, the kernel family's documented links between signals and possible changes, and previously rejected ideas to produce one structured hypothesis.

In plain words
What is it for?
It is used to create the next experiment proposal, including the suspected cause, the planned change, and the evidence needed to test it.
Why use it?
It prevents optimization ideas from being based only on guesses or from repeating changes that have already failed. The measured performance limit must be understood before proposing a change.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions Codex.

This is vlasenkoalexey/tpu_performance_autoresearch_wiki's own configuration. It tells Claude Code how to work on tpu_performance_autoresearch_wiki itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything tpu_performance_autoresearch_wiki configures →

Reuse

Borrowing it

Nothing to install: this file belongs to vlasenkoalexey/tpu_performance_autoresearch_wiki. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/vlasenkoalexey/tpu_performance_autoresearch_wiki/main/.claude/skills/formulate-kernel-hypothesis/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/vlasenkoalexey/tpu_performance_autoresearch_wiki

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for formulate-kernel-hypothesis

README.md
[![agentmods](https://agentmods.dev/badge/skills/vlasenkoalexey/tpu_performance_autoresearch_wiki/formulate-kernel-hypothesis/github.svg)](https://agentmods.dev/skills/vlasenkoalexey/tpu_performance_autoresearch_wiki/formulate-kernel-hypothesis)
Your own site
<a href="https://agentmods.dev/skills/vlasenkoalexey/tpu_performance_autoresearch_wiki/formulate-kernel-hypothesis"><img src="https://agentmods.dev/badge/skills/vlasenkoalexey/tpu_performance_autoresearch_wiki/formulate-kernel-hypothesis/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for formulate-kernel-hypothesis

Your own site · 80×15
<a href="https://agentmods.dev/skills/vlasenkoalexey/tpu_performance_autoresearch_wiki/formulate-kernel-hypothesis"><img src="https://agentmods.dev/badge/skills/vlasenkoalexey/tpu_performance_autoresearch_wiki/formulate-kernel-hypothesis.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,633 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.02633
Opus 5 $0.00000 $0.01316
Sonnet 5 $0.00000 $0.00527
Haiku 4.5 $0.00000 $0.00263

Measured 10d ago against content hash 8f3631cb6c43, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

formulate-kernel-hypothesis scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/skills/formulate-kernel-hypothesis/SKILL.md · 142 lines

How it starts

The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are formulating ONE kernel-optimization hypothesis (K2). The output is a structured proposal the master reviews and files as the K3 stub. Do not skip steps; do not formulate inline without this skill.

Step 1 — Gather inputs (most were just produced at K0/K1)

  • BRIEFS.md §1–§3 — READ THESE, they are what makes the proposal well-formed: §1 measurement (the 3σ frontier rule + between-launch σ that set your falsification bar), §2 K1 bound diagnosis (binding before you write the Mechanism), §3 author discipline (frontier bar, refute bar, plan-as-contract, stop rule). §4–§7 are the K4 author's. BRIEFS + the class page are the channel by which other families' experience reaches you.
  • The K1 bound diagnosis — the primary signal: the confirmed bound (memory / compute / dispatch), the HLO-confirmed sink structure (never the analytic guess — BRIEFS §2), the reference-envelope classification (inside / at / outside), and the naive's LLO digest (get_llo_fit_summary: spills/bundle, per-unit %util, top stalls).
  • The previous experiment's ## Headroom leads (verifier-authored) and the family page's Variant-specific open hypotheses — in the steady state, the hypothesis IS usually the top un-pulled lead. Pursuing a retrospective's recommendation (exploration mode) overrides.
  • The family frontier: best verified p50 + its mechanism (family page Current best row).
  • This family's own record only: its RESULTS.tsv + refuted-patterns.md if it exists.

Step 1.5 — describe the signal in your own words BEFORE reading the index

Two sentences: what is slow, and what the LLO/HLO evidence says binds it. Written before the index read, so the index informs rather than anchors (anti-TLDR-tunneling).

Step 2 — Read wiki/kernel-optimization-index.md IN FULL

The kernel lane's single catalog: the signal→lever map (the phase-ordering analog — there is no blueprint in this lane), the intervention-class table + escalation ladder, the "When NOT to Pallas" principles, category strategy, and the Load mandate (what K4's author must have read). Full read, no TLDR-skimming — the map's cross-references are the point.

Read the full file on GitHub · 142 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 10d ago First seen · 142 lines · 0 tokens per session scan A 8f3631cb6c43

Subscribe to this mod's changes

formulate-kernel-hypothesis is a skill published in the GitHub repository vlasenkoalexey/tpu_performance_autoresearch_wiki (55 stars, last pushed 6d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,633 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

ml_inference_optimization

This document describes the Leeroopedia MCP tools available during the with-KB benchmark run. It is a standalone reference and is not fed to the agents automatically.

Leeroo-AI/leeroopedia-mcp · 0 tokens

leeroopedia-mcp

Use Leeroopedia MCP to fetch grounded ML/AI best practices, build and review ML plans, debug failures, verify code/math correctness, and expand KB citations via getpage.

Leeroo-AI/leeroopedia-mcp · 42 tokens

ml-research-lab

Machine-learning research loop for dataset curation, fine-tuning, evaluation, inference deployment, experiment tracking, and model explainability. Use when working on ML experiments, training data, model benchmarks, RunPod/GPU runs, classifier quality, vLLM/GGUF serving, SHAP-style model explanations, or…

AnastasiyaW/codex-claude-code-config · 96 tokens

experiment-audit

Use this skill for scientific and ML-research reasoning work — evaluating experimental claims, auditing training runs or ablations, checking whether a statistical claim holds up, assessing reproducibility, reconciling contradictory results, reviewing a paper's methodology or results section, writing reviewer-style…

SreeDharshan-GJ/experiment-audit · 276 tokens

midmem-research-tracker

Keep the repo's RESEARCH.md ledger current from the research ingestions already in the MidMem store: for every unevaluated weekly research ingestion, evaluate each paper's feasibility and applicable improvement for MidMem, and record it as Paper (cite + link) · Finding (the empirical claim that matters) · Decision…

U4CSolutions/MidMem · 160 tokens

sematyp

SemaTyP combines two data sources into a knowledge graph for drug discovery / repositioning.

QSong-github/DrugClaw · 0 tokens