agentmods.dev

vi-methodology-development

vi-methodology-development is a skill for Claude Code, Codex from CHENyiru3/AI-Skills-Collections. It costs 55 tokens per session (782 once invoked), scanned A, original, MIT.

A research-methodology helper for variational inference, a way to estimate hidden quantities from observed data, and VAEs, neural networks that learn such estimates. It connects the scientific question to the model, objective, implementation, posterior queries, and validation.

In plain words
What is it for?
Use it to formulate, implement, review, or debug variational-inference and VAE methods, including integration with scvi-tools. It also supports methods briefs and careful transfer of design ideas from papers.
Why use it?
Research code can use a mathematically plausible model that does not answer the intended scientific question. This helper keeps assumptions, data roles, inference choices, and evidence limits connected.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also agents/openai.yaml present.

Part of the ai-ml plugin — 14 skills shipped together

not rated 2repo 3d ago A scan 55 tokens original MIT

Good fit Use it to formulate, implement, review, or debug variational-inference and VAE methods, including integration with scvi-tools. It also supports methods briefs and careful transfer of design ideas from papers.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/chenyiru3/ai-skills-collections/vi-methodology-development
View source ↗ CHENyiru3/AI-Skills-Collections
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add CHENyiru3/AI-Skills-Collections --skill vi-methodology-development
Clone the repo
git clone --depth 1 https://github.com/CHENyiru3/AI-Skills-Collections

Made for: Claude Code, Codex.

Or install ai-ml, the plugin that ships this one along with the rest of its 14 skills.

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 vi-methodology-development

README.md
[![agentmods](https://agentmods.dev/badge/skills/chenyiru3/ai-skills-collections/vi-methodology-development/github.svg)](https://agentmods.dev/skills/chenyiru3/ai-skills-collections/vi-methodology-development)
Your own site
<a href="https://agentmods.dev/skills/chenyiru3/ai-skills-collections/vi-methodology-development"><img src="https://agentmods.dev/badge/skills/chenyiru3/ai-skills-collections/vi-methodology-development/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 vi-methodology-development

Your own site · 80×15
<a href="https://agentmods.dev/skills/chenyiru3/ai-skills-collections/vi-methodology-development"><img src="https://agentmods.dev/badge/skills/chenyiru3/ai-skills-collections/vi-methodology-development.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 55 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 782 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.
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 $0.00055 $0.00782
Opus 5.5 $0.00022 $0.00313
Sonnet 5.5 $0.00011 $0.00156
Haiku 4.5 $0.00006 $0.00078

Measured yesterday against content hash 43b58ee80bed, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

vi-methodology-development 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 yesterday.

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.

skills-market/ai-ml/theory/vi-methodology-development/SKILL.md · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

VI Methodology Development

Connect the scientific target, observations, generative model, inference, objective, implementation, posterior query, and evidence. VI is a family of inference methods; a VAE is one amortized construction, not the required answer. Respect existing scientific choices. Ask about missing intent only when it changes the target; otherwise state provisional assumptions and continue.

Choose the requested depth

Keep four objects explicit

First identify the observational/replication unit, estimand, available training and use-time information, missingness, and generalization setting. For each variable record role, support, shape/plate, conditioning, and whether it is observed, random, deterministic, or point-estimated.

  1. Generative specification: write a normalized joint and sampling story. Separate target signal from measurement effects and parameters from random variables. Add structure for a concrete failure of a simpler baseline.
  2. Approximate posterior: specify factorization and information access independently. An encoder edge is not automatically a generative dependency. Justify amortized, local/global, structured, or hybrid inference.
  3. Objective: derive the ELBO from the joint/posterior. List MAP and auxiliary terms, weights, reductions, schedules, stop-gradients, and estimators separately. A substituted loss is not an exact bound without the corresponding argument.
  4. Exported query: define the expectation, prediction, contrast, or decoding operation. State what is integrated out, fixed, resampled, or removed and which uncertainties are unrepresented.

Read the full file on GitHub · 68 lines

Files

What ships with it

6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. yesterday First seen · 68 lines · 55 tokens per session scan A 43b58ee80bed

Subscribe to this mod's changes

vi-methodology-development is a skill published in the GitHub repository CHENyiru3/AI-Skills-Collections (2 stars, last pushed 3d ago), licensed MIT. It adds 55 tokens to every session and 782 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-11-13.

Data and AIScientific
Related

vi-methodology-development compared with skills from other repositories

vi-methodology-development next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
vi-methodology-developmentCHENyiru3/AI-Skills-CollectionsSkill23d agoMITA55Claude Code, Codex
arboretoK-Dense-AI/scientific-agent-skillsSkill57k5d agoMITA55Claude Code, Codex
deepspot-mK-Dense-AI/scientific-agent-skillsSkill57k5d agoMITA70Claude Code
torchdrugK-Dense-AI/scientific-agent-skillsSkill57k5d agoMITA64Claude Code
pyhealthK-Dense-AI/scientific-agent-skillsSkill57k5d agoMITA84Claude Code, Codex
nemo-mbridge-perf-expert-parallel-overlapNVIDIA/skillsSkill4.0kyesterdayApache-2.0A56Claude Code
evo2aipoch/open-scienceSkill5.5ktodayApache-2.0A83Claude Code, Codex