xie-saining-research-taste

xie-saining-research-taste is a skill for Codex from ky-ji/xie-saining-research-taste-skills. It costs 63 tokens per session (999 once invoked), scanned A, original, MIT.

A research-mentoring guide for artificial intelligence and machine-learning ideas. It focuses on choosing worthwhile questions, testing ideas with small experiments, learning from unexpected results, and explaining research clearly.

In plain words
What is it for?
Use it to evaluate research ideas, choose directions, plan experiments, interpret results, or strengthen the explanation of a paper or project.
Why use it?
It helps replace trend-following and vague claims with a clearer problem, evidence, and story. It is especially useful when deciding whether an idea is worth pursuing or how to improve an experiment plan.

Skill for Codex

Written for Codex: agents/openai.yaml present.

Good fit Use it to evaluate research ideas, choose directions, plan experiments, interpret results, or strengthen the explanation of a paper or project.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ky-ji/xie-saining-research-taste-skills/xie-saining-research-taste
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 ky-ji/xie-saining-research-taste-skills --skill xie-saining-research-taste
Clone the repo
git clone --depth 1 https://github.com/ky-ji/xie-saining-research-taste-skills

Made for: Codex.

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 xie-saining-research-taste

README.md
[![agentmods](https://agentmods.dev/badge/skills/ky-ji/xie-saining-research-taste-skills/xie-saining-research-taste/github.svg)](https://agentmods.dev/skills/ky-ji/xie-saining-research-taste-skills/xie-saining-research-taste)
Your own site
<a href="https://agentmods.dev/skills/ky-ji/xie-saining-research-taste-skills/xie-saining-research-taste"><img src="https://agentmods.dev/badge/skills/ky-ji/xie-saining-research-taste-skills/xie-saining-research-taste/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 xie-saining-research-taste

Your own site · 80×15
<a href="https://agentmods.dev/skills/ky-ji/xie-saining-research-taste-skills/xie-saining-research-taste"><img src="https://agentmods.dev/badge/skills/ky-ji/xie-saining-research-taste-skills/xie-saining-research-taste.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 63 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 999 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 $0.00063 $0.00999
Opus 5 $0.00032 $0.00500
Sonnet 5 $0.00013 $0.00200
Haiku 4.5 $0.00006 $0.00100

Measured 12d ago against content hash 41e093ca92e8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

xie-saining-research-taste 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 12d 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.

xie-saining-research-taste/SKILL.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Xie Saining Research Taste

Overview

Use this skill as a research mentor for AI/ML work. It distills Saining Xie's long-form interview into reusable judgment patterns: define the right problem, explore before over-committing, cultivate research taste, and communicate work as a coherent story.

This skill is an interpretive synthesis, not an official Xie Saining resource. Separate source-derived principles from your own inference when the distinction matters.

Workflow

  1. Identify the user's artifact: raw idea, project direction, experiment plan, paper draft, career choice, or AI-worldview question.
  2. Reframe the goal from "impact" to understanding: what will become clearer if this work succeeds, and who will understand something new?
  3. Test the problem definition before optimizing the solution. Ask what the real problem is, who defines it, why now, and what current formulations hide.
  4. Turn idea search into exploration. Prefer baselines, small prototypes, ablations, and experiment logs over armchair ideation.
  5. Look for gradients. Treat surprising movement, including negative movement, as signal. Treat no movement as the warning sign.
  6. Build taste into the work. Make the paper, demo, figure, table, or design feel like a precise communication interface, not an afterthought.
  7. Question the fashionable assumption. Ask which consensus claim is being accepted without evidence.
  8. Output a compact judgment, concrete next experiments, and a story that explains the decision path.

Decision Guide

  • Idea selection or research direction: Load references/problem-framing.md and references/research-workflow.md.
  • Experiment design or stuck projects: Load references/research-workflow.md.
  • Paper, proposal, talk, or storytelling: Load references/research-taste-and-writing.md.
  • Vision, multimodal AI, robotics, world models, or AGI framing: Load references/world-models-and-ai.md.
  • Research career, lab/company culture, collaboration, or incentives: Load references/organization-and-career.md.
  • Attribution or source context: Load references/sources.md.

Read the full file on GitHub · 79 lines

Files

What ships with it

7 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. 12d ago First seen · 79 lines · 63 tokens per session scan A 41e093ca92e8

Subscribe to this mod's changes

xie-saining-research-taste is a skill published in the GitHub repository ky-ji/xie-saining-research-taste-skills (2 stars, last pushed 4mo ago), licensed MIT. It adds 63 tokens to every session and 999 once invoked, about $0.0003 per session on Opus 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 2026-08-31.

Related

Other skills, from other repositories

hugging-face-model-trainer

This skill should be used when users want to train or fine-tune language models using TRL (Transformer Reinforcement Learning) on Hugging Face Jobs infrastructure. Covers SFT, DPO, GRPO and reward modeling training methods, plus GGUF conversion for local deployment. Includes guidance on the TRL Jobs package, UV…

patchy631/ai-engineering-hub · 131 tokens

hugging-face-datasets

Create and manage datasets on Hugging Face Hub. Supports initializing repos, defining configs/system prompts, streaming row updates, and SQL-based dataset querying/transformation. Designed to work alongside HF MCP server for comprehensive dataset workflows.

patchy631/ai-engineering-hub · 49 tokens

training-check

Interactively monitor training metrics from the current Codex session, periodically checking WandB or fallback logs for NaN, divergence, plateaus, and broken runs.

wanshuiyin/Auto-claude-code-research-in-sleep · 35 tokens

pysr

Use when fitting equations to data with PySR or SymbolicRegression.jl, when a user wants an interpretable formula, symbolic model, scaling law, or empirical relation discovered from numeric data, or when debugging a PySR search that is slow, stuck, or giving poor equations.

astroautomata/PySR · 61 tokens

analyze-results

Analyze ML experiment results, compute statistics, generate comparison tables and insights. Use when user says "analyze results", "compare", or needs to interpret experimental data.

wanshuiyin/Auto-claude-code-research-in-sleep · 37 tokens

trulens-evaluation-setup

Configure feedback functions and selectors for TruLens evaluations.

truera/trulens · 17 tokens