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.
curl -O https://raw.githubusercontent.com/vlasenkoalexey/tpu_performance_autoresearch_wiki/main/.claude/skills/formulate-kernel-hypothesis/SKILL.mdgit clone --depth 1 https://github.com/vlasenkoalexey/tpu_performance_autoresearch_wikiWrote 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.
[](https://agentmods.dev/skills/vlasenkoalexey/tpu_performance_autoresearch_wiki/formulate-kernel-hypothesis)<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.
<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>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once 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 |
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.
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.mdif 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.
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.
- 10d ago First seen · 142 lines · 0 tokens per session scan A 8f3631cb6c43
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.
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.
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.
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…
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…
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…
sematyp
SemaTyP combines two data sources into a knowledge graph for drug discovery / repositioning.